ORCID Profile
0000-0002-7719-1103
Current Organisations
Special Research Centre for the Subatomic Structure of Matter
,
University of Adelaide
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.
Publisher: American Physical Society (APS)
Date: 09-07-2013
Publisher: American Physical Society (APS)
Date: 21-08-2018
Publisher: American Physical Society (APS)
Date: 24-01-2017
Publisher: Springer Science and Business Media LLC
Date: 12-05-2016
DOI: 10.1557/ADV.2016.342
Publisher: American Physical Society (APS)
Date: 25-03-2014
Publisher: The Optical Society
Date: 09-03-2017
DOI: 10.1364/OE.25.006192
Publisher: Sissa Medialab
Date: 04-05-2017
DOI: 10.22323/1.281.0288
Publisher: American Physical Society (APS)
Date: 04-2015
Publisher: SPIE
Date: 03-03-2015
DOI: 10.1117/12.2078526
Publisher: American Physical Society (APS)
Date: 28-03-2017
Publisher: The Optical Society
Date: 05-12-2016
Publisher: Sissa Medialab
Date: 04-05-2017
DOI: 10.22323/1.281.0291
Publisher: Wiley
Date: 03-2017
Publisher: Research Square Platform LLC
Date: 07-03-2023
DOI: 10.21203/RS.3.RS-2631746/V1
Abstract: Medical datasets inherently contain errors from subjective or inaccurate test results, or from confounding biological complexities. It is difficult for medical experts to detect these elusive errors manually, due to lack of contextual information, limiting data privacy regulations, and the sheer scale of data to be reviewed. Current methods for detecting errors in data typically focus only on minimizing the effects of random classification noise. More recent progress has focused on using deep-learning to capture errors stemming from subjective labelling and confounding variables, however, such methods can be computationally intensive and inefficient. In this work, a deep-learning based algorithm was used in conjunction with a label-clustering approach to automate error detection. Results demonstrated high performance and efficiency on both image- and record-based datasets. Errors were identified with an accuracy of up to 85%, while requiring up to 93% less computing resources to complete. The resulting trained AI models exhibited greater stability and up to a 45% improvement in accuracy, from 69% to over 99%. These results indicate that practical, automated detection of errors in medical data is possible without human oversight.
Publisher: AIP
Date: 2011
DOI: 10.1063/1.3587589
Publisher: The Optical Society
Date: 10-04-2015
DOI: 10.1364/OE.23.009924
Publisher: American Physical Society (APS)
Date: 09-12-2011
Publisher: American Physical Society (APS)
Date: 10-08-2010
Publisher: Elsevier BV
Date: 08-2013
Publisher: American Physical Society (APS)
Date: 04-11-2016
Publisher: Springer Science and Business Media LLC
Date: 11-2012
Publisher: American Physical Society (APS)
Date: 03-05-2012
Publisher: American Physical Society (APS)
Date: 20-05-2013
Publisher: The Optical Society
Date: 19-06-2015
DOI: 10.1364/OE.23.017067
Location: Australia
No related grants have been discovered for Dr Jonathan M M Hall, FRSA.