Automatic cartilage segmentation in magnetic resonance imaging. Osteoarthritis (OA) is the most common form of arthritis, affecting nearly 1.4 million Australians. This research aims at engineering new tools for use in Magnetic Resonance Imaging systems to enable automated analyses of the cartilage and bones in joint images. The goals of the work are to assist with improved diagnosis and treatment planning for both chronic disease, such as OA, and acute injuries, such as cartilage and ligament ....Automatic cartilage segmentation in magnetic resonance imaging. Osteoarthritis (OA) is the most common form of arthritis, affecting nearly 1.4 million Australians. This research aims at engineering new tools for use in Magnetic Resonance Imaging systems to enable automated analyses of the cartilage and bones in joint images. The goals of the work are to assist with improved diagnosis and treatment planning for both chronic disease, such as OA, and acute injuries, such as cartilage and ligament tears in sporting injuries and other traumas.
The software developed will be provided on the project’s partner (Siemens) platform and will therefore be available worldwide and have a consequently large impact on the field.
Read moreRead less
Learning Medical Image Knowledge. We aim to develop Machine Learning and Knowledge Acquisition techniques for automated recognition of features in medical images, and to provide decision support for diagnosis from medical images. The project is innovative in its use of layered learning, where the computer first learns to recognise low-level image features that are then used to learn more complex features. The project is also innovative in combining a variety of automatic learning methods, includ ....Learning Medical Image Knowledge. We aim to develop Machine Learning and Knowledge Acquisition techniques for automated recognition of features in medical images, and to provide decision support for diagnosis from medical images. The project is innovative in its use of layered learning, where the computer first learns to recognise low-level image features that are then used to learn more complex features. The project is also innovative in combining a variety of automatic learning methods, including relational learning, with human-assisted knowledge acquisition methods. The expected outcomes will be new techniques for image understanding, particularly for our test domain, namely, High Resolution Computed Tomography scans of the lung.Read moreRead less
Quantitative measurement of Schizophrenia using Electrovestibulography. Schizophrenia was estimated to cost approximately $1.85billion in 2001 (0.3% of GDP and nearly $50k for each of the 37,000 Australians with the illness). Over one third of the cost is borne by sufferers and their carers. Misdiagnosis and incorrect therapy are common. To date quantitative assessment of Schizophrenics has been impossible making this tool potentially invaluable. An accurate diagnostic test could facilitate earl ....Quantitative measurement of Schizophrenia using Electrovestibulography. Schizophrenia was estimated to cost approximately $1.85billion in 2001 (0.3% of GDP and nearly $50k for each of the 37,000 Australians with the illness). Over one third of the cost is borne by sufferers and their carers. Misdiagnosis and incorrect therapy are common. To date quantitative assessment of Schizophrenics has been impossible making this tool potentially invaluable. An accurate diagnostic test could facilitate earlier diagnosis, more accurate treatment plans, and prevention of debilitating psychotic episodes for the sufferer. By being able to monitor drug efficacy the community can benefit by reduced drug costs, confinement times and hastened new drug development. Read moreRead less
Structural-functional connectivity in the brain. This project aims to develop magnetic resonance imaging analysis methods to non-invasively study brain connectivity. Recent advances in imaging can comprehensively describe the brain’s complex network of functional and structural connections (the brain ‘connectome’). This project will simultaneously investigate structural and functional connectivity, and characterise the dynamic properties of the connectome using graph-theoretic approaches. This p ....Structural-functional connectivity in the brain. This project aims to develop magnetic resonance imaging analysis methods to non-invasively study brain connectivity. Recent advances in imaging can comprehensively describe the brain’s complex network of functional and structural connections (the brain ‘connectome’). This project will simultaneously investigate structural and functional connectivity, and characterise the dynamic properties of the connectome using graph-theoretic approaches. This project should give neuroscientists computational tools to comprehensively map the network architecture of the human brain.Read moreRead less
Automatic Brain Tissue Segmentation in Magnetic Resonance Images based on Knowledge-guided Constrained Clustering. Accurate volumetric measurement of brain tissues is of critical importance in the study of many brain disorders, disease diagnosis, disease progression tracking and treatment monitoring. The study in this research will result in the development of a powerful computational technique that allows automatic volumetric measurement and analysis of brain tissues. The software developed in ....Automatic Brain Tissue Segmentation in Magnetic Resonance Images based on Knowledge-guided Constrained Clustering. Accurate volumetric measurement of brain tissues is of critical importance in the study of many brain disorders, disease diagnosis, disease progression tracking and treatment monitoring. The study in this research will result in the development of a powerful computational technique that allows automatic volumetric measurement and analysis of brain tissues. The software developed in this project will expedite early clinical diagnosis and treatment of neural diseases for patients, hence saving life and reducing health cost both at the personal and the national level. Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE150101655
Funder
Australian Research Council
Funding Amount
$297,036.00
Summary
Discriminative detection and quantification of cancer imaging biomarkers. This project aims to develop a new framework for the detection and quantification of cancer biomarkers in diagnostic and histopathology images with discriminative modelling of intrinsic structures. The framework will be the first computerised solution to provide automated, quantitative annotations of cancer imaging biomarkers at the macroscopic and microscopic levels to support standardised reporting of image interpretatio ....Discriminative detection and quantification of cancer imaging biomarkers. This project aims to develop a new framework for the detection and quantification of cancer biomarkers in diagnostic and histopathology images with discriminative modelling of intrinsic structures. The framework will be the first computerised solution to provide automated, quantitative annotations of cancer imaging biomarkers at the macroscopic and microscopic levels to support standardised reporting of image interpretation. It will help to alleviate the inter-observer variability and time-consuming process of manual analysis. The project aims to advance fundamental biomedical imaging research in generalised visual structure extraction and classification, and enable large-scale translational research in systems pathology for personalised cancer care.Read moreRead less
Automatic detection of the circle of Willis in neuro-images using multi-scale gradient calculation and knowledge-based genetic algorithms. Stroke is the third most common cause of death and a major contributor to long term disability in Australia. The most efficient way of preventing stroke from happening is to detect related symptoms early. The group of cerebral blood vessels that closely related to strokes is the circle of Willis (CoW). We build a system that can automatically detect and quan ....Automatic detection of the circle of Willis in neuro-images using multi-scale gradient calculation and knowledge-based genetic algorithms. Stroke is the third most common cause of death and a major contributor to long term disability in Australia. The most efficient way of preventing stroke from happening is to detect related symptoms early. The group of cerebral blood vessels that closely related to strokes is the circle of Willis (CoW). We build a system that can automatically detect and quantify CoW in neuroimages, providing ways of preventing strokes from happening. The project will enhance Australia¡¯s leading position in promoting and maintaining good health, especially in preventive healthcare.Read moreRead less
Novel Motion Correction Technologies for Simultaneous Positron Emission Tomography and Magnetic Resonance Imaging. The recent development of the world's first prototype combined MR-PET scanner for human use has prompted immense interest. MR-PET is likely to revolutionize clinical diagnosis and basic research, by providing exquisite structural images co-registered with simultaneous functional PET images. We will exploit the as yet unexplored potential for motion information derived from the MR sy ....Novel Motion Correction Technologies for Simultaneous Positron Emission Tomography and Magnetic Resonance Imaging. The recent development of the world's first prototype combined MR-PET scanner for human use has prompted immense interest. MR-PET is likely to revolutionize clinical diagnosis and basic research, by providing exquisite structural images co-registered with simultaneous functional PET images. We will exploit the as yet unexplored potential for motion information derived from the MR system to be used to correct the simultaneously acquired PET data for patient motion. This research is an excellent opportunity for Australian researchers to make important contributions to an emerging technology with high economic potential, and will strengthen Australia's international position in engineering and biomedical systems development.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE160101518
Funder
Australian Research Council
Funding Amount
$294,111.00
Summary
Multi-Object Recognition of Biomedical Images via Holistic Ontology. This project seeks to advance the development of new biomedical image recognition and analysis solutions by associating biomedical images with biomedical knowledge and personalised data. The provision of accurate and robust multi-object recognition and analysis from biomedical image data is a fundamental requirement for biomedical imaging applications. This project aims to improve the recognition and analysis of anatomical and ....Multi-Object Recognition of Biomedical Images via Holistic Ontology. This project seeks to advance the development of new biomedical image recognition and analysis solutions by associating biomedical images with biomedical knowledge and personalised data. The provision of accurate and robust multi-object recognition and analysis from biomedical image data is a fundamental requirement for biomedical imaging applications. This project aims to improve the recognition and analysis of anatomical and functional structures from biomedical images with ‘holistic ontology’ modelling that represents a multi-level biological, physiological, and anatomical knowledge base. The project will potentially have application in many health care areas, such as computer aided diagnosis, image-guided surgery planning, and image-based disease modelling.Read moreRead less
Determination of lung morphology from X-ray phase contrast radiographs. Current methods of imaging the lung rely heavily on low contrast images obtained with chest radiography or computed tomography. This research will develop new X-ray phase contrast imaging techniques capable of providing a tenfold contrast increase over conventional chest radiography at a fraction of the X-ray dose of computed tomography. Methods of extracting quantitative information on lung morphology and pathology from pha ....Determination of lung morphology from X-ray phase contrast radiographs. Current methods of imaging the lung rely heavily on low contrast images obtained with chest radiography or computed tomography. This research will develop new X-ray phase contrast imaging techniques capable of providing a tenfold contrast increase over conventional chest radiography at a fraction of the X-ray dose of computed tomography. Methods of extracting quantitative information on lung morphology and pathology from phase contrast chest radiographs will be developed during this research. Eventual outcomes are likely to lead to improved methods of detecting lung disease and injury for both biomedical and clinical studies.Read moreRead less