Deep Learning Role in Early Diagnosis of Prostate Cancer

The objective of this work is to develop a computer-aided diagnostic system for early diagnosis of prostate cancer. The presented system integrates both clinical biomarkers (prostate-specific antigen) and extracted features from diffusion-weighted magnetic resonance imaging collected at multiple b v...

Full description

Saved in:
Bibliographic Details
Published in:Technology in cancer research & treatment Vol. 17; p. 1533034618775530
Main Authors: Reda, Islam, Khalil, Ashraf, Elmogy, Mohammed, Abou El-Fetouh, Ahmed, Shalaby, Ahmed, Abou El-Ghar, Mohamed, Elmaghraby, Adel, Ghazal, Mohammed, El-Baz, Ayman
Format: Journal Article
Language:English
Published: Los Angeles, CA SAGE Publications 01.01.2018
Sage Publications Ltd
Subjects:
Algorithms
Antigens
Deep Learning
Diffusion Magnetic Resonance Imaging
Early Detection of Cancer - methods
Humans
Image Interpretation, Computer-Assisted
Male
NMR
Nuclear magnetic resonance
Prostate cancer
Prostatic Neoplasms - diagnosis
Reproducibility of Results
ROC Curve
Sensitivity and Specificity
Special Collection on Deep Learning in Molecular Imaging–Research Paper
ADC
prostate cancer
SNCSAE
CAD
PSA
ISSN:1533-0346, 1533-0338, 1533-0338
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The objective of this work is to develop a computer-aided diagnostic system for early diagnosis of prostate cancer. The presented system integrates both clinical biomarkers (prostate-specific antigen) and extracted features from diffusion-weighted magnetic resonance imaging collected at multiple b values. The presented system performs 3 major processing steps. First, prostate delineation using a hybrid approach that combines a level-set model with nonnegative matrix factorization. Second, estimation and normalization of diffusion parameters, which are the apparent diffusion coefficients of the delineated prostate volumes at different b values followed by refinement of those apparent diffusion coefficients using a generalized Gaussian Markov random field model. Then, construction of the cumulative distribution functions of the processed apparent diffusion coefficients at multiple b values. In parallel, a K-nearest neighbor classifier is employed to transform the prostate-specific antigen results into diagnostic probabilities. Finally, those prostate-specific antigen–based probabilities are integrated with the initial diagnostic probabilities obtained using stacked nonnegativity constraint sparse autoencoders that employ apparent diffusion coefficient–cumulative distribution functions for better diagnostic accuracy. Experiments conducted on 18 diffusion-weighted magnetic resonance imaging data sets achieved 94.4% diagnosis accuracy (sensitivity = 88.9% and specificity = 100%), which indicate the promising results of the presented computer-aided diagnostic system.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1533-0346
1533-0338
1533-0338
DOI:10.1177/1533034618775530