ORCID Profile
0000-0002-3930-6600
Current Organisations
University of Technology Sydney
,
UNSW Sydney
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
In Research Link Australia (RLA), "Research Topics" refer to ANZSRC FOR and SEO codes. These topics are either sourced from ANZSRC FOR and SEO codes listed in researchers' related grants or generated by a large language model (LLM) based on their publications.
Natural hazards | Geography education curriculum and pedagogy | Public health | Injury prevention
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: Springer Science and Business Media LLC
Date: 29-08-2023
DOI: 10.1038/S41598-023-40116-6
Abstract: Accurate identification of emphysema subtypes and severity is crucial for effective management of COPD and the study of disease heterogeneity. Manual analysis of emphysema subtypes and severity is laborious and subjective. To address this challenge, we present a deep learning-based approach for automating the Fleischner Society’s visual score system for emphysema subtyping and severity analysis. We trained and evaluated our algorithm using 9650 subjects from the COPDGene study. Our algorithm achieved the predictive accuracy at 52%, outperforming a previously published method’s accuracy of 45%. In addition, the agreement between the predicted scores of our method and the visual scores was good, where the previous method obtained only moderate agreement. Our approach employs a regression training strategy to generate categorical labels while simultaneously producing high-resolution localized activation maps for visualizing the network predictions. By leveraging these dense activation maps, our method possesses the capability to compute the percentage of emphysema involvement per lung in addition to categorical severity scores. Furthermore, the proposed method extends its predictive capabilities beyond centrilobular emphysema to include paraseptal emphysema subtypes.
Publisher: Springer Science and Business Media LLC
Date: 10-09-2020
Publisher: SPIE-Intl Soc Optical Eng
Date: 28-05-2022
Publisher: Springer Science and Business Media LLC
Date: 03-04-2016
Publisher: Radiological Society of North America (RSNA)
Date: 09-2021
Publisher: Radiological Society of North America (RSNA)
Date: 11-2021
Publisher: IEEE
Date: 18-07-2021
Publisher: Springer International Publishing
Date: 2016
Publisher: IEEE
Date: 05-11-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2023
Publisher: ACM
Date: 17-10-2022
Publisher: Elsevier BV
Date: 06-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: Springer Science and Business Media LLC
Date: 16-09-2017
Publisher: Springer Science and Business Media LLC
Date: 10-01-2022
Publisher: IEEE
Date: 18-07-2021
Publisher: IEEE
Date: 07-2018
Publisher: IEEE
Date: 07-2020
Publisher: Elsevier BV
Date: 2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: Radiological Society of North America (RSNA)
Date: 07-2020
Publisher: Elsevier BV
Date: 2016
Publisher: Elsevier BV
Date: 2016
Publisher: IEEE
Date: 18-07-2021
Publisher: Elsevier BV
Date: 09-2022
DOI: 10.1016/J.COMPBIOMED.2022.105817
Abstract: The development of deep learning (DL) models for prostate segmentation on magnetic resonance imaging (MRI) depends on expert-annotated data and reliable baselines, which are often not publicly available. This limits both reproducibility and comparability. Prostate158 consists of 158 expert annotated biparametric 3T prostate MRIs comprising T2w sequences and diffusion-weighted sequences with apparent diffusion coefficient maps. Two U-ResNets trained for segmentation of anatomy (central gland, peripheral zone) and suspicious lesions for prostate cancer (PCa) with a PI-RADS score of ≥4 served as baseline algorithms. Segmentation performance was evaluated using the Dice similarity coefficient (DSC), the Hausdorff distance (HD), and the average surface distance (ASD). The Wilcoxon test with Bonferroni correction was used to evaluate differences in performance. The generalizability of the baseline model was assessed using the open datasets Medical Segmentation Decathlon and PROSTATEx. Compared to Reader 1, the models achieved a DSC/HD/ASD of 0.88/18.3/2.2 for the central gland, 0.75/22.8/1.9 for the peripheral zone, and 0.45/36.7/17.4 for PCa. Compared with Reader 2, the DSC/HD/ASD were 0.88/17.5/2.6 for the central gland, 0.73/33.2/1.9 for the peripheral zone, and 0.4/39.5/19.1 for PCa. Interrater agreement measured in DSC/HD/ASD was 0.87/11.1/1.0 for the central gland, 0.75/15.8/0.74 for the peripheral zone, and 0.6/18.8/5.5 for PCa. Segmentation performances on the Medical Segmentation Decathlon and PROSTATEx were 0.82/22.5/3.4 0.86/18.6/2.5 for the central gland, and 0.64/29.2/4.7 0.71/26.3/2.2 for the peripheral zone. We provide an openly accessible, expert-annotated 3T dataset of prostate MRI and a reproducible benchmark to foster the development of prostate segmentation algorithms.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2021
Publisher: IEEE
Date: 10-2010
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2021
Publisher: ACM
Date: 17-10-2022
Publisher: Wiley
Date: 07-05-2020
DOI: 10.1111/EXSY.12565
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2019
Publisher: Springer Science and Business Media LLC
Date: 17-02-2016
Publisher: SPIE-Intl Soc Optical Eng
Date: 04-03-2020
Publisher: Elsevier BV
Date: 04-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 15-02-2023
Publisher: ACM
Date: 22-03-2016
Publisher: Elsevier BV
Date: 12-2021
Publisher: Springer Science and Business Media LLC
Date: 06-09-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2023
Publisher: IEEE
Date: 07-2020
Publisher: Springer Science and Business Media LLC
Date: 05-02-2020
Publisher: IEEE
Date: 07-2020
Publisher: Cold Spring Harbor Laboratory
Date: 22-12-2022
DOI: 10.1101/2022.12.20.22283748
Abstract: The surge of the COVID-19 pandemic challenged health services globally, and in Lesotho, the HIV and tuberculosis (TB) services were similarly affected. Integrated, multi-disease diagnostic services were proposed solutions to mitigate these disruptions. We describe and evaluate the effect of an integrated, hospital-based COVID-19, TB and HIV screening and diagnostic model in two rural districts in Lesotho, during the period between December 2020 and August 2022. Adults and children above 5 years attending two hospitals were screened for COVID-19 and TB symptoms. After a positive screening, participants were offered to enroll in a service model that included clinical evaluation, chest radiography, SARS-CoV-2, Xpert MTB/RIF Ultra and HIV testing. Participants diagnosed with COVID-19, TB, or HIV were contacted after 28 days evaluate their health status, and linkage to HIV or TB services. Of the 179160 participants screened, 6623(37%) screened positive, and 4371(66%) were enrolled in this service model, yielding a total of 458 diagnoses. One positive rapid antigen test for SARS-CoV-2 was found per 11 participants screened, one Xpert-positive TB case was diagnosed per 85 people screened, and 1 new HIV diagnosis was done per 182 people screened. Of the 321(82.9%) participants contacted after 28 days of diagnosis, 304(94.7%) reported to be healthy. Of the in iduals that were newly diagnosed with HIV or TB, 18/24(75.0%) and 46/51(90.1%) started treatment. This service showed no difference in the detection of new HIV and TB cases when compared to other hospitals, where no such integrated service model was provided. This screening and diagnostic model successfully maintained same-day, integrated COVID-19, TB, and HIV testing services through different COVID-19 incidence periods in a resource-limited context. There were positive effects in avoiding diagnostic delays and ensuring linkage to services, however, efficiencies were contingent on the successful adaptation to the changing environment.
Publisher: IEEE
Date: 04-2017
Publisher: Springer London
Date: 2014
Publisher: SPIE-Intl Soc Optical Eng
Date: 29-03-2021
Publisher: Springer Nature Switzerland
Date: 2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-06-2021
DOI: 10.36227/TECHRXIV.14722854
Abstract: Future Smart Cities
Publisher: IEEE
Date: 11-2021
Publisher: IEEE
Date: 18-07-2021
Publisher: Radiological Society of North America (RSNA)
Date: 2021
Publisher: Springer Science and Business Media LLC
Date: 14-01-2022
Publisher: Atlantis Press
Date: 2016
Publisher: Springer Nature Switzerland
Date: 2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2022
Publisher: Public Library of Science (PLoS)
Date: 28-07-2022
DOI: 10.1371/JOURNAL.PONE.0267539
Abstract: We propose a deep learning system to automatically detect four explainable emphysema signs on frontal and lateral chest radiographs. Frontal and lateral chest radiographs from 3000 studies were retrospectively collected. Two radiologists annotated these with 4 radiological signs of pulmonary emphysema identified from the literature. A patient with ≥2 of these signs present is considered emphysema positive. Using separate deep learning systems for frontal and lateral images we predict the presence of each of the four visual signs and use these to determine emphysema positivity. The ROC and AUC results on a set of 422 held-out cases, labeled by both radiologists, are reported. Comparison with a black-box model which predicts emphysema without the use of explainable visual features is made on the annotations from both radiologists, as well as the subset that they agreed on. DeLong’s test is used to compare with the black-box model ROC and McNemar’s test to compare with radiologist performance. In 422 test cases, emphysema positivity was predicted with AUCs of 0.924 and 0.946 using the reference standard from each radiologist separately. Setting model sensitivity equivalent to that of the second radiologist, our model has a comparable specificity ( p = 0.880 and p = 0.143 for each radiologist respectively). Our method is comparable with the black-box model with AUCs of 0.915 ( p = 0.407) and 0.935 ( p = 0.291), respectively. On the 370 cases where both radiologists agreed (53 positives), our model achieves an AUC of 0.981, again comparable to the black-box model AUC of 0.972 ( p = 0.289). Our proposed method can predict emphysema positivity on chest radiographs as well as a radiologist or a comparable black-box method. It additionally produces labels for four visual signs to ensure the explainability of the result. The dataset is publicly available at 0.5281/zenodo.6373392 .
Publisher: Mary Ann Liebert Inc
Date: 08-2021
Publisher: Springer Science and Business Media LLC
Date: 27-03-2023
Publisher: Elsevier BV
Date: 10-2021
Publisher: Elsevier BV
Date: 10-2021
Publisher: Springer Science and Business Media LLC
Date: 25-11-2016
Publisher: Elsevier BV
Date: 02-2021
Publisher: Elsevier BV
Date: 07-2021
Publisher: Cold Spring Harbor Laboratory
Date: 26-02-2022
DOI: 10.1101/2022.02.25.22271520
Abstract: COVID-19, a severe acute respiratory syndrome aggressively spread among global populations in just a few months. Since then, it has had four dominant variants (Alpha, Beta, Gamma and Delta) that are far more contagious than original. Accurate and timely diagnosis of COVID-19 is critical for analysis of damage to lungs, treatment, as well as quarantine management [7]. CT, MRI or X-rays image analysis using deep learning provide an efficient and accurate diagnosis of COVID-19 that could help to counter its outbreak. With the aim to provide efficient multi-class COVID-19 detection, recently, COVID-19 Detection challenge using X-ray is organized [12]. In this paper, the late-fusion of features is extracted from pre-trained various convolutional neural networks and fine-tuned these models using the challenge dataset. The DensNet201 with Adam optimizer and EffecientNet-B3 are fine-tuned on the challenge dataset and ensembles the features to get the final prediction. Besides, we also considered the test time augmentation technique after the late-ensembling approach to further improve the performance of our proposed solution. Evaluation on Chest XR COVID-19 showed that our model achieved overall accuracy is 95.67%. We made the code is publicly available 1 . The proposed approach was ranked 6th in Chest XR COVID-19 detection Challenge [1].
Publisher: Springer Science and Business Media LLC
Date: 16-03-2020
Publisher: AME Publishing Company
Date: 05-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2023
Publisher: IEEE
Date: 06-2010
DOI: 10.1109/CIT.2010.252
Publisher: Springer Science and Business Media LLC
Date: 19-08-2023
DOI: 10.1007/S00521-023-08930-1
Abstract: Skin cancer, primarily resulting from the abnormal growth of skin cells, is among the most common cancer types. In recent decades, the incidence of skin cancer cases worldwide has risen significantly (one in every three newly diagnosed cancer cases is a skin cancer). Such an increase can be attributed to changes in our social and lifestyle habits coupled with devastating man-made alterations to the global ecosystem. Despite such a notable increase, diagnosis of skin cancer is still challenging, which becomes critical as its early detection is crucial for increasing the overall survival rate. This calls for advancements of innovative computer-aided systems to assist medical experts with their decision making. In this context, there has been a recent surge of interest in machine learning (ML), in particular, deep neural networks (DNNs), to provide complementary assistance to expert physicians. While DNNs have a high processing capacity far beyond that of human experts, their outputs are deterministic, i.e., providing estimates without prediction confidence. Therefore, it is of paramount importance to develop DNNs with uncertainty-awareness to provide confidence in their predictions. Monte Carlo dropout (MCD) is vastly used for uncertainty quantification however, MCD suffers from overconfidence and being miss calibrated. In this paper, we use MCD algorithm to develop an uncertainty-aware DNN that assigns high predictive entropy to erroneous predictions and enable the model to optimize the hyper-parameters during training, which leads to more accurate uncertainty quantification. We use two synthetic (two moons and blobs) and a real dataset (skin cancer) to validate our algorithm. Our experiments on these datasets prove effectiveness of our approach in quantifying reliable uncertainty. Our method achieved 85.65 ± 0.18 prediction accuracy, 83.03 ± 0.25 uncertainty accuracy, and 1.93 ± 0.3 expected calibration error outperforming vanilla MCD and MCD with loss enhanced based on predicted entropy.
Publisher: Springer Science and Business Media LLC
Date: 04-11-2021
Publisher: Elsevier BV
Date: 04-2022
DOI: 10.1016/J.ULTRASMEDBIO.2021.12.006
Abstract: Placenta localization from obstetric 2-D ultrasound (US) imaging is unattainable for many pregnant women in low-income countries because of a severe shortage of trained sonographers. To address this problem, we present a method to automatically detect low-lying placenta or placenta previa from 2-D US imaging. Two-dimensional US data from 280 pregnant women were collected in Ethiopia using a standardized acquisition protocol and low-cost equipment. The detection method consists of two parts. First, 2-D US segmentation of the placenta is performed using a deep learning model with a U-Net architecture. Second, the segmentation is used to classify each placenta as either normal or a class including both low-lying placenta and placenta previa. The segmentation model was trained and tested on 6574 2-D US images, achieving a median test Dice coefficient of 0.84 (interquartile range = 0.23). The classifier achieved a sensitivity of 81% and a specificity of 82% on a holdout test set of 148 cases. Additionally, the model was found to segment in real time (19 ± 2 ms per 2-D US image) using a smartphone paired with a low-cost 2-D US device. This work illustrates the feasibility of using automated placenta localization in a resource-limited setting.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: IEEE
Date: 18-07-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2022
Publisher: American Scientific Publishers
Date: 10-2016
Publisher: Elsevier BV
Date: 02-2022
Publisher: American Scientific Publishers
Date: 10-2016
Publisher: Springer Nature Singapore
Date: 2022
Publisher: Springer Science and Business Media LLC
Date: 2022
DOI: 10.1007/S11280-021-00992-2
Abstract: The ability to explain why the model produced results in such a way is an important problem, especially in the medical domain. Model explainability is important for building trust by providing insight into the model prediction. However, most existing machine learning methods provide no explainability, which is worrying. For instance, in the task of automatic depression prediction, most machine learning models lead to predictions that are obscure to humans. In this work, we propose explainable Multi-Aspect Depression Detection with Hierarchical Attention Network MDHAN , for automatic detection of depressed users on social media and explain the model prediction. We have considered user posts augmented with additional features from Twitter. Specifically, we encode user posts using two levels of attention mechanisms applied at the tweet-level and word-level, calculate each tweet and words’ importance, and capture semantic sequence features from the user timelines (posts). Our hierarchical attention model is developed in such a way that it can capture patterns that leads to explainable results. Our experiments show that MDHAN outperforms several popular and robust baseline methods, demonstrating the effectiveness of combining deep learning with multi-aspect features. We also show that our model helps improve predictive performance when detecting depression in users who are posting messages publicly on social media. MDHAN achieves excellent performance and ensures adequate evidence to explain the prediction.
Publisher: Elsevier BV
Date: 05-2023
Publisher: Springer International Publishing
Date: 2019
Publisher: Springer International Publishing
Date: 2014
Publisher: Elsevier BV
Date: 02-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2022
Publisher: Association for Computing Machinery (ACM)
Date: 30-06-2022
DOI: 10.1145/3537899
Abstract: Federated Learning (FL), as an emerging form of distributed machine learning (ML), can protect participants’ private data from being substantially disclosed to cyber adversaries. It has potential uses in many large-scale, data-rich environments, such as the Internet of Things (IoT), Industrial IoT, Social Media (SM), and the emerging SM 3.0. However, federated learning is susceptible to some forms of data leakage through model inversion attacks. Such attacks occur through the analysis of participants’ uploaded model updates. Model inversion attacks can reveal private data and potentially undermine some critical reasons for employing federated learning paradigms. This article proposes novel differential privacy (DP)-based deep federated learning framework. We theoretically prove that our framework can fulfill DP’s requirements under distinct privacy levels by appropriately adjusting scaled variances of Gaussian noise. We then develop a Differentially Private Data-Level Perturbation (DP-DLP) mechanism to conceal any single data point’s impact on the training phase. Experiments on real-world datasets, specifically the social media 3.0, Iris, and Human Activity Recognition (HAR) datasets, demonstrate that the proposed mechanism can offer high privacy, enhanced utility, and elevated efficiency. Consequently, it simplifies the development of various DP-based FL models with different tradeoff preferences on data utility and privacy levels.
Publisher: Elsevier BV
Date: 08-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2022
Publisher: IEEE
Date: 29-10-2021
Publisher: European Respiratory Society (ERS)
Date: 14-10-2021
DOI: 10.1183/13993003.01613-2021
Abstract: A baseline computed tomography (CT) scan for lung cancer (LC) screening may reveal information indicating that certain LC screening participants can be screened less, and instead require dedicated early cardiac and respiratory clinical input. We aimed to develop and validate competing death (CD) risk models using CT information to identify participants with a low LC risk and a high CD risk. Participant demographics and quantitative CT measures of LC, cardiovascular disease and chronic obstructive pulmonary disease were considered for deriving a logistic regression model for predicting 5-year CD risk using a s le from the National Lung Screening Trial (n=15 000). Multicentric Italian Lung Detection data were used to perform external validation (n=2287). Our final CD model outperformed an external pre-scan model (CD Risk Assessment Tool) in both the derivation (area under the curve (AUC) 0.744 (95% CI 0.727–0.761) and 0.677 (95% CI 0.658–0.695), respectively) and validation cohorts (AUC 0.744 (95% CI 0.652–0.835) and 0.725 (95% CI 0.633–0.816), respectively). By also taking LC incidence risk into consideration, we suggested a risk threshold where a subgroup (6258/23 096 (27%)) was identified with a number needed to screen to detect one LC of 216 ( versus 23 in the remainder of the cohort) and ratio of 5.41 CDs per LC case ( versus 0.88). The respective values in the validation cohort subgroup (774/2287 (34%)) were 129 ( versus 29) and 1.67 ( versus 0.43). Evaluating both LC and CD risks post-scan may improve the efficiency of LC screening and facilitate the initiation of multidisciplinary trajectories among certain participants.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: Elsevier BV
Date: 2022
Publisher: Springer Science and Business Media LLC
Date: 20-03-2023
Publisher: Springer International Publishing
Date: 2020
Publisher: IEEE
Date: 07-2020
Publisher: Springer International Publishing
Date: 2020
Publisher: Hindawi Limited
Date: 08-11-2021
DOI: 10.1002/INT.22729
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2022
Publisher: Springer Science and Business Media LLC
Date: 10-09-2023
Publisher: Springer International Publishing
Date: 14-11-2018
Publisher: Springer International Publishing
Date: 2023
Publisher: Public Library of Science (PLoS)
Date: 30-07-2021
DOI: 10.1371/JOURNAL.PONE.0255301
Abstract: In the context of the current global pandemic and the limitations of the RT-PCR test, we propose a novel deep learning architecture, DFCN (Denoising Fully Connected Network). Since medical facilities around the world differ enormously in what laboratory tests or chest imaging may be available, DFCN is designed to be robust to missing input data. An ablation study extensively evaluates the performance benefits of the DFCN as well as its robustness to missing inputs. Data from 1088 patients with confirmed RT-PCR results are obtained from two independent medical facilities. The data includes results from 27 laboratory tests and a chest x-ray scored by a deep learning model. Training and test datasets are taken from different medical facilities. Data is made publicly available. The performance of DFCN in predicting the RT-PCR result is compared with 3 related architectures as well as a Random Forest baseline. All models are trained with varying levels of masked input data to encourage robustness to missing inputs. Missing data is simulated at test time by masking inputs randomly. DFCN outperforms all other models with statistical significance using random subsets of input data with 2-27 available inputs. When all 28 inputs are available DFCN obtains an AUC of 0.924, higher than any other model. Furthermore, with clinically meaningful subsets of parameters consisting of just 6 and 7 inputs respectively, DFCN achieves higher AUCs than any other model, with values of 0.909 and 0.919.
Publisher: Elsevier BV
Date: 12-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: Mary Ann Liebert Inc
Date: 10-2021
Publisher: Elsevier BV
Date: 08-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2023
Publisher: Indian Society for Education and Environment
Date: 12-08-2015
Publisher: Hindawi Limited
Date: 18-02-2052
DOI: 10.1002/INT.22856
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2022
Publisher: Springer Science and Business Media LLC
Date: 15-03-2023
Publisher: Springer Science and Business Media LLC
Date: 05-07-2022
DOI: 10.1007/S40747-022-00802-W
Abstract: Deep exploration of histone occupancy and covalent post-translational modifications (e.g., acetylation, methylation) is essential to decode gene expression regulation, chromosome packaging, DNA damage, and transcriptional activation. Existing computational approaches are unable to precisely predict histone occupancy and modifications mainly due to the use of sub-optimal statistical representation of histone sequences. For the establishment of an improved histone occupancy and modification landscape for multiple histone markers, the paper in hand presents an end-to-end computational multi-paradigm framework “Histone-Net”. To learn local and global residue context aware sequence representation, Histone-Net generates unsupervised higher order residue embeddings (DNA2Vec) and presents a different application of language modelling, where it encapsulates histone occupancy and modification information while generating higher order residue embeddings (SuperDNA2Vec) in a supervised manner. We perform an intrinsic and extrinsic evaluation of both presented distributed representation learning schemes. A comprehensive empirical evaluation of Histone-Net over ten benchmark histone markers data sets for three different histone sequence analysis tasks indicates that SuperDNA2Vec sequence representation and softmax classifier-based approach outperforms state-of-the-art approach by an average accuracy of 7%. To eliminate the overhead of training separate binary classifiers for all ten histone markers, Histone-Net is evaluated in multi-label classification paradigm, where it produces decent performance for simultaneous prediction of histone occupancy, acetylation, and methylation.
Publisher: Radiological Society of North America (RSNA)
Date: 04-2021
Publisher: Springer Science and Business Media LLC
Date: 03-07-2018
Publisher: Association for Computing Machinery (ACM)
Date: 26-09-2022
DOI: 10.1145/3539577
Abstract: Abstract: A fascinating challenge in robotics-human interaction is imitating the emotion recognition capability of humans to robots with the aim to make human-robotics interaction natural, genuine and intuitive. To achieve the natural interaction in affective robots, human-machine interfaces, and autonomous vehicles, understanding our attitudes and opinions is very important, and it provides a practical and feasible path to realize the connection between machine and human. Multimodal interface that includes voice along with facial expression can manifest a large range of nuanced emotions compared to purely textual interfaces and provide a great value to improve the intelligence level of effective communication. Interfaces that fail to manifest or ignore user emotions may significantly impact the performance and risk being perceived as cold, socially inept, untrustworthy, and incompetent. To equip a child well for life, we need to help our children identify their feelings, manage them well, and express their needs in healthy, respectful, and direct ways. Early identification of emotional deficits can help to prevent low social functioning in children. In this work, we analyzed the child’s spontaneous behavior using multimodal facial expression and voice signal presenting multimodal transformer-based last feature fusion for facial behavior analysis in children to extract contextualized representations from RGB video sequence and Hematoxylin and eosin video sequence and then using these representations followed by pairwise concatenations of contextualized representations using cross-feature fusion technique to predict users emotions. To validate the performance of the proposed framework, we have performed experiments with the different pairwise concatenations of contextualized representations that showed significantly better performance than state of the art method. Besides, we perform t-distributed stochastic neighbor embedding visualization to visualize the discriminative feature in lower dimension space and probability density estimation to visualize the prediction capability of our proposed model.
Publisher: Elsevier BV
Date: 02-2016
Publisher: Springer Science and Business Media LLC
Date: 28-07-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Elsevier
Date: 2018
Publisher: Wiley
Date: 18-04-2022
DOI: 10.1002/MP.15655
Abstract: Total lung volume is an important quantitative biomarker and is used for the assessment of restrictive lung diseases. In this study, we investigate the performance of several deep‐learning approaches for automated measurement of total lung volume from chest radiographs. About 7621 posteroanterior and lateral view chest radiographs (CXR) were collected from patients with chest CT available. Similarly, 928 CXR studies were chosen from patients with pulmonary function test (PFT) results. The reference total lung volume was calculated from lung segmentation on CT or PFT data, respectively. This dataset was used to train deep‐learning architectures to predict total lung volume from chest radiographs. The experiments were constructed in a stepwise fashion with increasing complexity to demonstrate the effect of training with CT‐derived labels only and the sources of error. The optimal models were tested on 291 CXR studies with reference lung volume obtained from PFT. Mean absolute error (MAE), mean absolute percentage error (MAPE), and Pearson correlation coefficient (Pearson's r ) were computed. The optimal deep‐learning regression model showed an MAE of 408 ml and an MAPE of 8.1% using both frontal and lateral chest radiographs as input. The predictions were highly correlated with the reference standard (Pearson's r = 0.92). CT‐derived labels were useful for pretraining but the optimal performance was obtained by fine‐tuning the network with PFT‐derived labels. We demonstrate, for the first time, that state‐of‐the‐art deep‐learning solutions can accurately measure total lung volume from plain chest radiographs. The proposed model is made publicly available and can be used to obtain total lung volume from routinely acquired chest radiographs at no additional cost. This deep‐learning system can be a useful tool to identify trends over time in patients referred regularly for chest X‐ray.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2022
Publisher: Springer International Publishing
Date: 2021
Publisher: Elsevier BV
Date: 07-2021
Publisher: Elsevier BV
Date: 2020
DOI: 10.1016/J.NEUNET.2019.08.030
Abstract: Since the principal component analysis and its variants are sensitive to outliers that affect their performance and applicability in real world, several variants have been proposed to improve the robustness. However, most of the existing methods are still sensitive to outliers and are unable to select useful features. To overcome the issue of sensitivity of PCA against outliers, in this paper, we introduce two-dimensional outliers-robust principal component analysis (ORPCA) by imposing the joint constraints on the objective function. ORPCA relaxes the orthogonal constraints and penalizes the regression coefficient, thus, it selects important features and ignores the same features that exist in other principal components. It is commonly known that square Frobenius norm is sensitive to outliers. To overcome this issue, we have devised an alternative way to derive objective function. Experimental results on four publicly available benchmark datasets show the effectiveness of joint feature selection and provide better performance as compared to state-of-the-art dimensionality-reduction methods.
Publisher: Wiley
Date: 10-01-2021
DOI: 10.1002/ETT.4210
Publisher: Springer Nature Switzerland
Date: 2023
Publisher: Springer Science and Business Media LLC
Date: 19-08-2019
Publisher: Informa UK Limited
Date: 28-04-2016
Publisher: American Scientific Publishers
Date: 08-2019
Publisher: IEEE
Date: 10-2009
Publisher: IEEE
Date: 18-07-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: Springer Science and Business Media LLC
Date: 09-04-2011
Publisher: Elsevier BV
Date: 12-2022
Publisher: Springer Science and Business Media LLC
Date: 19-10-2021
DOI: 10.1007/S12083-020-00981-8
Abstract: Data stored in physical storage or transferred over a communication channel includes substantial redundancy. Compression techniques cut down the data redundancy to reduce space and communication time. Nevertheless, compression techniques lack proper security measures, e.g., secret key control, leaving the data susceptible to attack. Data encryption is therefore needed to achieve data security in keeping the data unreadable and unaltered through a secret key. This work concentrates on the problems of data compression and encryption collectively without negatively affecting each other. Towards this end, an efficient, secure data compression technique is introduced, which provides cryptographic capabilities for use in combination with an adaptive Huffman coding, pseudorandom keystream generator, and S-Box to achieve confusion and diffusion properties of cryptography into the compression process and overcome the performance issues. Thus, compression is carried out according to a secret key such that the output will be both encrypted and compressed in a single step. The proposed work demonstrated a congruent fit for real-time implementation, providing robust encryption quality and acceptable compression capability. Experiment results are provided to show that the proposed technique is efficient and produces similar space-saving (%) to standard techniques. Security analysis discloses that the proposed technique is susceptible to the secret key and plaintext. Moreover, the ciphertexts produced by the proposed technique successfully passed all NIST tests, which confirm that the 99% confidence level on the randomness of the ciphertext.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2023
Publisher: Elsevier BV
Date: 07-2022
Publisher: Elsevier BV
Date: 11-2020
Publisher: Springer Science and Business Media LLC
Date: 20-06-2023
DOI: 10.1007/S00330-023-09826-3
Abstract: To study trends in the incidence of reported pulmonary nodules and stage I lung cancer in chest CT. We analyzed the trends in the incidence of detected pulmonary nodules and stage I lung cancer in chest CT scans in the period between 2008 and 2019. Imaging metadata and radiology reports from all chest CT studies were collected from two large Dutch hospitals. A natural language processing algorithm was developed to identify studies with any reported pulmonary nodule. Between 2008 and 2019, a total of 74,803 patients underwent 166,688 chest CT examinations at both hospitals combined. During this period, the annual number of chest CT scans increased from 9955 scans in 6845 patients in 2008 to 20,476 scans in 13,286 patients in 2019. The proportion of patients in whom nodules (old or new) were reported increased from 38% (2595/6845) in 2008 to 50% (6654/13,286) in 2019. The proportion of patients in whom significant new nodules (≥ 5 mm) were reported increased from 9% (608/6954) in 2010 to 17% (1660/9883) in 2017. The number of patients with new nodules and corresponding stage I lung cancer diagnosis tripled and their proportion doubled, from 0.4% (26/6954) in 2010 to 0.8% (78/9883) in 2017. The identification of incidental pulmonary nodules in chest CT has steadily increased over the past decade and has been accompanied by more stage I lung cancer diagnoses. These findings stress the importance of identifying and efficiently managing incidental pulmonary nodules in routine clinical practice. • The number of patients who underwent chest CT examinations substantially increased over the past decade, as did the number of patients in whom pulmonary nodules were identified. • The increased use of chest CT and more frequently identified pulmonary nodules were associated with more stage I lung cancer diagnoses.
Publisher: Elsevier BV
Date: 10-2022
Publisher: Radiological Society of North America (RSNA)
Date: 2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Springer Science and Business Media LLC
Date: 07-03-2023
Publisher: IEEE
Date: 2008
Publisher: IEEE
Date: 04-2015
Publisher: MDPI AG
Date: 21-10-2022
DOI: 10.3390/S22208058
Abstract: Sensor fusion is the process of merging data from many sources, such as radar, lidar and camera sensors, to provide less uncertain information compared to the information collected from single source [...]
Publisher: Radiological Society of North America (RSNA)
Date: 08-2020
Publisher: Springer Science and Business Media LLC
Date: 19-12-2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Springer Nature Singapore
Date: 2022
Publisher: IEEE
Date: 12-2014
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2023
Publisher: Springer Science and Business Media LLC
Date: 03-07-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: Springer Science and Business Media LLC
Date: 12-06-2021
DOI: 10.1007/S00247-021-05114-8
Abstract: Since the introduction of artificial intelligence (AI) in radiology, the promise has been that it will improve health care and reduce costs. Has AI been able to fulfill that promise? We describe six clinical objectives that can be supported by AI: a more efficient workflow, shortened reading time, a reduction of dose and contrast agents, earlier detection of disease, improved diagnostic accuracy and more personalized diagnostics. We provide ex les of use cases including the available scientific evidence for its impact based on a hierarchical model of efficacy. We conclude that the market is still maturing and little is known about the contribution of AI to clinical practice. More real-world monitoring of AI in clinical practice is expected to aid in determining the value of AI and making informed decisions on development, procurement and reimbursement.
Publisher: Elsevier BV
Date: 04-2023
Publisher: Springer Science and Business Media LLC
Date: 15-11-2022
DOI: 10.1007/S00330-022-09205-4
Abstract: To assess how an artificial intelligence (AI) algorithm performs against five experienced musculoskeletal radiologists in diagnosing scaphoid fractures and whether it aids their diagnosis on conventional multi-view radiographs. Four datasets of conventional hand, wrist, and scaphoid radiographs were retrospectively acquired at two hospitals (hospitals A and B). Dataset 1 (12,990 radiographs from 3353 patients, hospital A) and dataset 2 (1117 radiographs from 394 patients, hospital B) were used for training and testing a scaphoid localization and laterality classification component. Dataset 3 (4316 radiographs from 840 patients, hospital A) and dataset 4 (688 radiographs from 209 patients, hospital B) were used for training and testing the fracture detector. The algorithm was compared with the radiologists in an observer study. Evaluation metrics included sensitivity, specificity, positive predictive value (PPV), area under the characteristic operating curve (AUC), Cohen’s kappa coefficient (κ), fracture localization precision, and reading time. The algorithm detected scaphoid fractures with a sensitivity of 72%, specificity of 93%, PPV of 81%, and AUC of 0.88. The AUC of the algorithm did not differ from each radiologist (0.87 [radiologists’ mean], p ≥ .05). AI assistance improved five out of ten pairs of inter-observer Cohen’s κ agreements ( p .05) and reduced reading time in four radiologists ( p .001), but did not improve other metrics in the majority of radiologists ( p ≥ .05). The AI algorithm detects scaphoid fractures on conventional multi-view radiographs at the level of five experienced musculoskeletal radiologists and could significantly shorten their reading time. • An artificial intelligence algorithm automatically detects scaphoid fractures on conventional multi-view radiographs at the same level of five experienced musculoskeletal radiologists. • There is preliminary evidence that automated scaphoid fracture detection can significantly shorten the reading time of musculoskeletal radiologists.
Publisher: Springer Science and Business Media LLC
Date: 28-05-2019
Publisher: Informa UK Limited
Date: 25-01-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: Elsevier BV
Date: 08-2023
Publisher: Springer Science and Business Media LLC
Date: 25-04-2022
DOI: 10.1007/S10669-022-09855-1
Abstract: For mission critical (MC) applications such as bushfire emergency management systems (EMS), understanding the current situation as a disaster unfolds is critical to saving lives, infrastructure and the environment. Incident control-room operators manage complex information and systems, especially with the emergence of Big Data. They are increasingly making decisions supported by artificial intelligence (AI) and machine learning (ML) tools for data analysis, prediction and decision-making. As the volume, speed and complexity of information increases due to more frequent fire events, greater availability of myriad IoT sensors, smart devices, satellite data and burgeoning use of social media, the advances in AI and ML that help to manage Big Data and support decision-making are increasingly perceived as “Black Box”. This paper aims to scope the requirements for bushfire EMS to improve Big Data management and governance of AI/ML. An analysis of ModelOps technology, used increasingly in the commercial sector, is undertaken to determine what components might be fit-for-purpose. The result is a novel set of ModelOps features, EMS requirements and an EMS-ModelOps framework that resolves more than 75% of issues whilst being sufficiently generic to apply to other types of mission-critical applications.
Publisher: IEEE
Date: 07-2020
Publisher: Elsevier BV
Date: 03-2022
Publisher: Elsevier BV
Date: 03-2014
Publisher: Springer Science and Business Media LLC
Date: 07-06-2021
Publisher: Radiological Society of North America (RSNA)
Date: 08-2021
Publisher: Springer International Publishing
Date: 2015
Publisher: American Scientific Publishers
Date: 06-2016
Publisher: ACM
Date: 11-07-2021
Publisher: Elsevier BV
Date: 12-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2022
Publisher: Springer Science and Business Media LLC
Date: 31-05-2022
Publisher: Springer Science and Business Media LLC
Date: 15-11-2022
DOI: 10.1038/S41598-022-23445-W
Abstract: Mandibular fractures are among the most frequent facial traumas in oral and maxillofacial surgery, accounting for 57% of cases. An accurate diagnosis and appropriate treatment plan are vital in achieving optimal re-establishment of occlusion, function and facial aesthetics. This study aims to detect mandibular fractures on panoramic radiographs (PR) automatically. 1624 PR with fractures were manually annotated and labelled as a reference. A deep learning approach based on Faster R-CNN and Swin-Transformer was trained and validated on 1640 PR with and without fractures. Subsequently, the trained algorithm was applied to a test set consisting of 149 PR with and 171 PR without fractures. The detection accuracy and the area-under-the-curve (AUC) were calculated. The proposed method achieved an F1 score of 0.947 and an AUC of 0.977. Deep learning-based assistance of clinicians may reduce the misdiagnosis and hence the severe complications.
Publisher: Springer Science and Business Media LLC
Date: 11-01-2022
Publisher: Springer Science and Business Media LLC
Date: 15-04-2021
DOI: 10.1007/S00330-021-07892-Z
Abstract: Map the current landscape of commercially available artificial intelligence (AI) software for radiology and review the availability of their scientific evidence. We created an online overview of CE-marked AI software products for clinical radiology based on vendor-supplied product specifications ( www.aiforradiology.com ). Characteristics such as modality, subspeciality, main task, regulatory information, deployment, and pricing model were retrieved. We conducted an extensive literature search on the available scientific evidence of these products. Articles were classified according to a hierarchical model of efficacy. The overview included 100 CE-marked AI products from 54 different vendors. For 64/100 products, there was no peer-reviewed evidence of its efficacy. We observed a large heterogeneity in deployment methods, pricing models, and regulatory classes. The evidence of the remaining 36/100 products comprised 237 papers that predominantly (65%) focused on diagnostic accuracy (efficacy level 2). From the 100 products, 18 had evidence that regarded level 3 or higher, validating the (potential) impact on diagnostic thinking, patient outcome, or costs. Half of the available evidence (116/237) were independent and not (co-)funded or (co-)authored by the vendor. Even though the commercial supply of AI software in radiology already holds 100 CE-marked products, we conclude that the sector is still in its infancy. For 64/100 products, peer-reviewed evidence on its efficacy is lacking. Only 18/100 AI products have demonstrated (potential) clinical impact. • Artificial intelligence in radiology is still in its infancy even though already 100 CE-marked AI products are commercially available. • Only 36 out of 100 products have peer-reviewed evidence of which most studies demonstrate lower levels of efficacy. • There is a wide variety in deployment strategies, pricing models, and CE marking class of AI products for radiology.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2021
Publisher: Elsevier BV
Date: 03-2021
Publisher: Wiley
Date: 18-10-2022
DOI: 10.1111/JDV.17711
Abstract: The Psoriasis Area and Severity Index (PASI) score is commonly used in clinical practice and research to monitor disease severity and determine treatment efficacy. Automating the PASI score with deep learning algorithms, like Convolutional Neural Networks (CNNs), could enable objective and efficient PASI scoring. To assess the performance of image‐based automated PASI scoring in anatomical regions by CNNs and compare the performance of CNNs to image‐based scoring by physicians. Imaging series were matched to PASI subscores determined in real life by the treating physician. CNNs were trained using standardized imaging series of 576 trunk, 614 arm and 541 leg regions. CNNs were separately trained for each PASI subscore (erythema, desquamation, induration and area) in each anatomical region (trunk, arms and legs). The head region was excluded for anonymity. Additionally, PASI‐trained physicians retrospectively determined image‐based subscores on the test set images of the trunk. Agreement with the real‐life scores was determined with the intraclass correlation coefficient (ICC) and compared between the CNNs and physicians. Intraclass correlation coefficients between the CNN and real‐life scores of the trunk region were 0.616, 0.580, 0.580 and 0.793 for erythema, desquamation, induration and area, respectively, with similar results for the arms and legs region. PASI‐trained physicians ( N = 5) were in moderate–good agreement (ICCs 0.706–0.793) with each other for image‐based PASI scoring of the trunk region. ICCs between the CNN and real‐life scores were slightly higher for erythema (0.616 vs. 0.558), induration (0.580 vs. 0.573) and area scoring (0.793 vs. 0.694) than image‐based scoring by physicians. Physicians slightly outperformed the CNN on desquamation scoring (0.580 vs. 0.589). Convolutional Neural Networks have the potential to automatically and objectively perform image‐based PASI scoring at an anatomical region level. For erythema, desquamation and induration scoring, CNNs performed similar to physicians, while for area scoring CNNs outperformed physicians on image‐based PASI scoring.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2023
Publisher: Elsevier BV
Date: 05-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2022
Publisher: Springer International Publishing
Date: 2018
Publisher: Springer Science and Business Media LLC
Date: 26-10-2021
Publisher: Springer Science and Business Media LLC
Date: 17-09-2019
Publisher: Association for Computing Machinery (ACM)
Date: 30-06-2021
DOI: 10.1145/3434237
Abstract: Word representation has always been an important research area in the history of natural language processing (NLP). Understanding such complex text data is imperative, given that it is rich in information and can be used widely across various applications. In this survey, we explore different word representation models and its power of expression, from the classical to modern-day state-of-the-art word representation language models (LMS). We describe a variety of text representation methods, and model designs have blossomed in the context of NLP, including SOTA LMs. These models can transform large volumes of text into effective vector representations capturing the same semantic information. Further, such representations can be utilized by various machine learning (ML) algorithms for a variety of NLP-related tasks. In the end, this survey briefly discusses the commonly used ML- and DL-based classifiers, evaluation metrics, and the applications of these word embeddings in different NLP tasks.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2023
Publisher: Springer International Publishing
Date: 2018
Publisher: IEEE
Date: 06-2011
Publisher: Elsevier BV
Date: 2023
DOI: 10.1016/J.ISATRA.2022.05.015
Abstract: Rip Currents are contributing around 25 fatal drownings each year in Australia. Previous research has indicated that most of beachgoers cannot correctly identify a rip current, leaving them at risk of experiencing a drowning incident. Automated detection of rip currents could help to reduce drownings and assist lifeguards in supervision planning however, varying beach conditions have made this challenging. This work presents the effectiveness of an improved lightweight framework for detecting rip currents: RipDet+
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2020
DOI: 10.36227/TECHRXIV.12743933
Abstract: Artificial intelligence (AI) has been applied widely in our daily lives in a variety of ways with numerous successful stories. AI has also contributed to dealing with the coronavirus disease (COVID-19) pandemic, which has been happening around the globe. This paper presents a survey of AI methods being used in various applications in the fight against the COVID-19 outbreak and outlines the crucial roles of AI research in this unprecedented battle. We touch on a number of areas where AI plays as an essential component, from medical image processing, data analytics, text mining and natural language processing, the Internet of Things, to computational biology and medicine. A summary of COVID-19 related data sources that are available for research purposes is also presented. Research directions on exploring the potentials of AI and enhancing its capabilities and power in the battle are thoroughly discussed. We highlight 13 groups of problems related to the COVID-19 pandemic and point out promising AI methods and tools that can be used to solve those problems. It is envisaged that this study will provide AI researchers and the wider community an overview of the current status of AI applications and motivate researchers in harnessing AI potentials in the fight against COVID-19.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: Elsevier BV
Date: 12-2010
Publisher: Elsevier BV
Date: 2023
Publisher: Oxford University Press (OUP)
Date: 2022
DOI: 10.1093/RAP/RKAC060
Abstract: DISH has been associated with increased coronary artery calcifications and incident ischaemic stroke. The formation of bone along the spine may share pathways with calcium deposition in the aorta. We hypothesized that patients with DISH have increased vascular calcifications. Therefore we aimed to investigate the presence and extent of DISH in relation to thoracic aortic calcification (TAC) severity. This cross-sectional study included 4703 patients from the Second Manifestation of ARTerial disease cohort, consisting of patients with cardiovascular events or risk factors for cardiovascular disease. Chest radiographs were scored for DISH using the Resnick criteria. Different severities of TAC were scored arbitrarily from no TAC to mild, moderate or severe TAC. Using multivariate logistic regression, the associations between DISH and TAC were analysed with adjustments for age, sex, BMI, diabetes, smoking status, non-high-density lipoprotein cholesterol, cholesterol lowering drug usage, renal function and blood pressure. A total of 442 patients (9.4%) had evidence of DISH and 1789 (38%) patients had TAC. The prevalence of DISH increased from 6.6% in the no TAC group to 10.8% in the mild, 14.3% in the moderate and 17.1% in the severe TAC group. After adjustments, DISH was significantly associated with the presence of TAC [odds ratio (OR) 1.46 [95% CI 1.17, 1.82)]. In multinomial analyses, DISH was associated with moderate TAC [OR 1.43 (95% CI 1.06, 1.93)] and severe TAC [OR 1.67 (95% CI 1.19, 2.36)]. Subjects with DISH have increased TACs, providing further evidence that patients with DISH have an increased burden of vascular calcifications.
Publisher: American Scientific Publishers
Date: 06-2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: IEEE
Date: 07-2020
Publisher: Springer Science and Business Media LLC
Date: 23-01-2021
Publisher: MDPI AG
Date: 15-07-2021
DOI: 10.3390/JPM11070663
Abstract: Background: Diffuse idiopathic skeletal hyperostosis (DISH) is associated with both obesity and type 2 diabetes. Our objective was to investigate the relation between DISH and visceral adipose tissue (VAT) in particular, as this would support a causal role of insulin resistance and low grade inflammation in the development of DISH. Methods: In 4334 patients with manifest vascular disease, the relation between different adiposity measures and the presence of DISH was compared using z-scores via standard deviation logistic regression analyses. Analyses were stratified by sex and adjusted for age, systolic blood pressure, diabetes, non-HDL cholesterol, smoking status, and renal function. Results: DISH was present in 391 (9%) subjects. The presence of DISH was associated with markers of adiposity and had a strong relation with VAT in males (OR: 1.35 95%CI: 1.20–1.54) and females (OR: 1.43 95%CI: 1.06–1.93). In males with the most severe DISH (extensive ossification of seven or more vertebral bodies) the association between DISH and VAT was stronger (OR: 1.61 95%CI: 1.31–1.98), while increased subcutaneous fat was negatively associated with DISH (OR: 0.65 95%CI: 0.49–0.95). In females, increased subcutaneous fat was associated with the presence of DISH (OR: 1.43 95%CI: 1.14–1.80). Conclusion: Markers of adiposity, including VAT, are strongly associated with the presence of DISH. Subcutaneous adipose tissue thickness was negatively associated with more severe cases of DISH in males, while in females, increased subcutaneous adipose tissue was associated with the presence of DISH.
Publisher: Springer International Publishing
Date: 2019
Publisher: Cold Spring Harbor Laboratory
Date: 17-04-2020
DOI: 10.1101/2020.04.11.20054643
Abstract: Coronavirus disease (COVID-19) is an infectious disease caused by a new virus. Exponential growth is not only threatening lives, but also impacting businesses and disrupting travel around the world. The aim of this work is to develop an efficient diagnosis of COVID-19 disease by differentiating it from viral pneumonia, bacterial pneumonia and healthy cases using deep learning techniques. In this work, we have used pre-trained knowledge to improve the diagnostic performance using transfer learning techniques and compared the performance different CNN architectures. Evaluation results using K-fold (10) showed that we have achieved state of the art performance with overall accuracy of 98.75% on the perspective of CT and X-ray cases as a whole. Quantitative evaluation showed high accuracy for automatic diagnosis of COVID-19. Pre-trained deep learning models develop in this study could be used early screening of coronavirus, however it calls for extensive need to CT or X-rays dataset to develop a reliable application.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2022
Publisher: IEEE
Date: 18-07-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2022
Publisher: SPIE
Date: 04-03-2010
DOI: 10.1117/12.843813
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: Elsevier BV
Date: 12-2020
Publisher: Springer Science and Business Media LLC
Date: 25-09-2021
DOI: 10.1186/S13244-021-01077-4
Abstract: Limited evidence is available on the clinical impact of artificial intelligence (AI) in radiology. Early health technology assessment (HTA) is a methodology to assess the potential value of an innovation at an early stage. We use early HTA to evaluate the potential value of AI software in radiology. As a use-case, we evaluate the cost-effectiveness of AI software aiding the detection of intracranial large vessel occlusions (LVO) in stroke in comparison to standard care. We used a Markov based model from a societal perspective of the United Kingdom predominantly using stroke registry data complemented with pooled outcome data from large, randomized trials. Different scenarios were explored by varying missed diagnoses of LVOs, AI costs and AI performance. Other input parameters were varied to demonstrate model robustness. Results were reported in expected incremental costs (IC) and effects (IE) expressed in quality adjusted life years (QALYs). Applying the base case assumptions (6% missed diagnoses of LVOs by clinicians, $40 per AI analysis, 50% reduction of missed LVOs by AI), resulted in cost-savings and incremental QALYs over the projected lifetime (IC: − $156, − 0.23% IE: + 0.01 QALYs, + 0.07%) per suspected ischemic stroke patient. For each yearly cohort of patients in the UK this translates to a total cost saving of $11 million. AI tools for LVO detection in emergency care have the potential to improve healthcare outcomes and save costs. We demonstrate how early HTA may be applied for the evaluation of clinically applied AI software for radiology.
Publisher: Radiological Society of North America (RSNA)
Date: 07-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-08-2021
DOI: 10.36227/TECHRXIV.13904099
Abstract: Our work aims to conduct a comprehensive literature review of deep learning methods applied in the fashion industry and, especially, the image-based virtual fitting task by citing research works published in the last years. We have summarized their challenges, their main frameworks, the popular benchmark datasets, and the different evaluation metrics. Also, some promising future research directions are discussed to propose improvements in this research field.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2022
Publisher: Springer International Publishing
Date: 2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: MDPI AG
Date: 10-01-2019
DOI: 10.3390/APP9020236
Abstract: This paper presents a comprehensive survey on Arabic cursive scene text recognition. The recent years’ publications in this field have witnessed the interest shift of document image analysis researchers from recognition of optical characters to recognition of characters appearing in natural images. Scene text recognition is a challenging problem due to the text having variations in font styles, size, alignment, orientation, reflection, illumination change, blurriness and complex background. Among cursive scripts, Arabic scene text recognition is contemplated as a more challenging problem due to joined writing, same character variations, a large number of ligatures, the number of baselines, etc. Surveys on the Latin and Chinese script-based scene text recognition system can be found, but the Arabic like scene text recognition problem is yet to be addressed in detail. In this manuscript, a description is provided to highlight some of the latest techniques presented for text classification. The presented techniques following a deep learning architecture are equally suitable for the development of Arabic cursive scene text recognition systems. The issues pertaining to text localization and feature extraction are also presented. Moreover, this article emphasizes the importance of having benchmark cursive scene text dataset. Based on the discussion, future directions are outlined, some of which may provide insight about cursive scene text to researchers.
Publisher: Springer Science and Business Media LLC
Date: 21-01-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2022
Publisher: MDPI AG
Date: 31-08-2020
DOI: 10.3390/A13090215
Abstract: This paper proposes a novel approach for selecting a subset of features in semi-supervised datasets where only some of the patterns are labeled. The whole process is completed in two phases. In the first phase, i.e., Phase-I, the whole dataset is ided into two parts: The first part, which contains labeled patterns, and the second part, which contains unlabeled patterns. In the first part, a small number of features are identified using well-known maximum relevance (from first part) and minimum redundancy (whole dataset) based feature selection approaches using the correlation coefficient. The subset of features from the identified set of features, which produces a high classification accuracy using any supervised classifier from labeled patterns, is selected for later processing. In the second phase, i.e., Phase-II, the patterns belonging to the first and second part are clustered separately into the available number of classes of the dataset. In the clusters of the first part, take the majority of patterns belonging to a cluster as the class for that cluster, which is given already. Form the pairs of cluster centroids made in the first and second part. The centroid of the second part nearest to a centroid of the first part will be paired. As the class of the first centroid is known, the same class can be assigned to the centroid of the cluster of the second part, which is unknown. The actual class of the patterns if known for the second part of the dataset can be used to test the classification accuracy of patterns in the second part. The proposed two-phase approach performs well in terms of classification accuracy and number of features selected on the given benchmarked datasets.
Publisher: Elsevier BV
Date: 12-2021
Publisher: IEEE
Date: 06-2022
Publisher: IEEE
Date: 06-2013
Publisher: IEEE
Date: 06-2013
Publisher: Institution of Engineering and Technology (IET)
Date: 10-05-2023
DOI: 10.1049/CIT2.12223
Abstract: Three‐dimensional (3D) image reconstruction of tumours can visualise their structures with precision and high resolution. In this article, GAN‐LSTM‐3D method is proposed for 3D reconstruction of lung cancer tumours from 2D CT images. Our method consists of three phases: lung segmentation, tumour segmentation, and tumour 3D reconstruction. Lung segmentation is done using snake optimisation followed by tumour segmentation using Gustafson‐Kessel (GK) clustering method. The outputs of GK (2D lung cancer images) are fed to a pre‐trained Visual Geometry Group (VGG) for feature extraction. The VGG outputs are used as input for an attention‐based LSTM which performs feature unpacking. The output of LSTM units is given to generator network of a Generative Adversarial Networks (GAN) model to carry out 3D reconstruction of (normal/cancerous) images with high quality. During training, the discriminator network of the GAN is used to judge the generator outputs. The authors to the best of their knowledge were the first to use GAN for 3D reconstruction of lung cancer tumours which is the primary contribution of this article. Moreover, existing studies are mostly focused on brain tumours and are not suitable for lung tumour reconstruction. Focusing on lung tumours is the second contribution of this article. Evaluation on LUNA data collection against existing methods like MC, MC + fairing etc. reveals the superiority of our method in terms of Hamming and Euclidean distance metrics. Additionally, the computational complexity of the proposed method is lower compared to evaluated methods.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2022
Publisher: Springer Berlin Heidelberg
Date: 2010
Publisher: Wiley
Date: 10-03-2021
DOI: 10.1002/ETT.4241
Abstract: Next‐generation wireless communication networks, in particular, the densified 5G will bring many developments to the existing telecommunications industry. The key benefits will be the higher throughput and very low latency. In this context, the usage of unmanned aerial vehicle (UAV) is becoming a feasible option for deploying 5G services on demand. At the same time, the immense bandwidth potential of mmWave has strengthened its performance in radio communication. In this article, we provide a consolidated synthesis on the role of UAVs and mmWave in 5G, emphasis on recent developments and challenges. The review focuses on UAV relay architectures, identifies the relevant problems and limitations in the deployment of UAVs using mmWave in both access and backhaul links simultaneously. There is a critical analysis of the optimum placement of the UAVs as a relay with a focus on the mmWave band. The distinctive rich characteristics of the mmWave propagation and scattering are presented. We also synthesis mmWave path loss models. Then, the scope of artificial intelligence and machine learning techniques as an efficient solution for combating the dynamic and complex nature of UAV‐based cellular communication networks are discussed. In the end, security and privacy issues in UAV‐based cellular network are spotlighted. It is believed that the literature discussed, and the findings reached in this article are of significant importance to researchers, application engineers and decision‐makers in the designing and deployment of UAV‐supported 5G network.
Publisher: Elsevier BV
Date: 04-2021
Publisher: Springer Nature Switzerland
Date: 2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: ScopeMed
Date: 2015
Publisher: IEEE
Date: 07-2020
Publisher: Elsevier BV
Date: 08-2023
Publisher: Springer Science and Business Media LLC
Date: 10-03-2022
Publisher: Springer Science and Business Media LLC
Date: 15-07-2022
DOI: 10.1038/S41467-022-30695-9
Abstract: International challenges have become the de facto standard for comparative assessment of image analysis algorithms. Although segmentation is the most widely investigated medical image processing task, the various challenges have been organized to focus only on specific clinical tasks. We organized the Medical Segmentation Decathlon (MSD)—a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities to investigate the hypothesis that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. MSD results confirmed this hypothesis, moreover, MSD winner continued generalizing well to a wide range of other clinical problems for the next two years. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms generalize well when retrained on unseen tasks (2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability (3) the training of accurate AI segmentation models is now commoditized to scientists that are not versed in AI model training.
Publisher: IEEE
Date: 07-2020
Publisher: IEEE
Date: 07-2017
Location: Saudi Arabia
Start Date: 12-2023
End Date: 12-2026
Amount: $342,924.00
Funder: Australian Research Council
View Funded Activity