Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

A Voting Ensemble Method to Assist the Diagnosis of Prostate Cancer Using Multiparametric MRI

Riley, P, Olier, I, Rea, M, Lisboa, P and Ortega-Martorell, S (2019) A Voting Ensemble Method to Assist the Diagnosis of Prostate Cancer Using Multiparametric MRI. In: Advances in Intelligent Systems and Computing , 976. (13th International Workshop, WSOM+ 2019, 26th-28th June 2019, Barcelona, Spain).

[img]
Preview
Text
wsom_SVM_GTM_paper_cameraready.pdf - Accepted Version

Download (580kB) | Preview

Abstract

© 2020, Springer Nature Switzerland AG. Prostate cancer is the second most commonly occurring cancer in men. Diagnosis through Magnetic Resonance Imaging (MRI) is limited, yet current practice holds a relatively low specificity. This paper extends a previous SPIE ProstateX challenge study in three ways (1) to include healthy tissue analysis, creating a solution suitable for clinical practice, which has been requested and validated by collaborating clinicians; (2) by using a voting ensemble method to assist prostate cancer diagnosis through a supervised SVM approach; and (3) using the unsupervised GTM to provide interpretability to understand the supervised SVM classification results. Pairwise classifiers of clinically significant lesion, non-significant lesion, and healthy tissue, were developed. Results showed that when combining multiparametric MRI and patient level metadata, classification of significant lesions against healthy tissue attained an AUC of 0.869 (10-fold cross-validation).

Item Type: Conference or Workshop Item (Paper)
Subjects: Q Science > QA Mathematics > QA76 Computer software
R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine
Divisions: Applied Mathematics (merged with Comp Sci 10 Aug 20)
Publisher: Springer
Date Deposited: 24 Jul 2019 09:11
Last Modified: 13 Apr 2022 15:17
DOI or ID number: 10.1007/978-3-030-19642-4_29
URI: https://researchonline.ljmu.ac.uk/id/eprint/11087
View Item View Item