Abstract
Background and Objective: The use of computer-aided detection (CAD) systems can help radiologists make objective decisions and reduce the dependence on invasive techniques. In this study, a CAD system that detects and identifies prostate cancer from diffusion-weighted imaging (DWI) is developed. Methods: The proposed system first uses non-negative matrix factorization (NMF) to integrate three different types of features for the accurate segmentation of prostate regions. Then, discriminatory features in the form of apparent diffusion coefficient (ADC) volumes are estimated from the segmented regions. The ADC maps that constitute these volumes are labeled by a radiologist to identify the ADC maps with malignant or benign tumors. Finally, transfer learning is used to fine-tune two different previously-trained convolutional neural network (CNN) models (AlexNet and VGGNet) for detecting and identifying prostate cancer. Results: Multiple experiments were conducted to evaluate the accuracy of different CNN models using DWI datasets acquired at nine distinct b-values that included both high and low b-values. The average accuracy of AlexNet at the nine b-values was with average sensitivity and specificity of and . These results improved with the use of the deeper CNN model (VGGNet). The average accuracy of VGGNet was with sensitivity and specificity of and . Conclusions: The results of the conducted experiments emphasize the feasibility and accuracy of the developed system and the improvement of this accuracy using the deeper CNN.
Highlights
Prostate cancer is a major health problem, especially in western countries
70% of the apparent diffusion coefficient (ADC) maps of both the malignant and benign cases at each b-value were used for fine-tuning an AlexNet-based model
The ADC slices used for training were from different patients to the ADC slices used for testing to avoid any correlation that could exist between ADC slices of the same patient
Summary
Prostate cancer is a major health problem, especially in western countries. This disease is the second leading cause of mortality among males in the United States [1]. A CAD system that detects and identifies prostate cancer from diffusion-weighted imaging (DWI) is developed. Transfer learning is used to fine-tune two different previously-trained convolutional neural network (CNN) models (AlexNet and VGGNet) for detecting and identifying prostate cancer. The average accuracy of AlexNet at the nine b-values was 89.2 ± 1.5% with average sensitivity and specificity of 87.5 ± 2.3% and 90.9 ± 1.9% These results improved with the use of the deeper CNN model (VGGNet).
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
