Abstract
BackgroundProstate cancer is one of the most common cancers worldwide. Currently, convolution neural networks (CNNs) are achieving remarkable success in various computer vision tasks, and in medical imaging research. Various CNN architectures and methodologies have been applied in the field of prostate cancer diagnosis. In this work, we evaluate the impact of the adaptation of a state-of-the-art CNN architecture on domain knowledge related to problems in the diagnosis of prostate cancer. The architecture of the final CNN model was optimised on the basis of the Prostate Imaging Reporting and Data System (PI-RADS) standard, which is currently the best available indicator in the acquisition, interpretation, and reporting of prostate multi-parametric magnetic resonance imaging (mpMRI) examinations.MethodsA dataset containing 330 suspicious findings identified using mpMRI was used. Two CNN models were subjected to comparative analysis. Both implement the concept of decision-level fusion for mpMRI data, providing a separate network for each multi-parametric series. The first model implements a simple fusion of multi-parametric features to formulate the final decision. The architecture of the second model reflects the diagnostic pathway of PI-RADS methodology, using information about a lesion’s primary anatomic location within the prostate gland. Both networks were experimentally tuned to successfully classify prostate cancer changes.ResultsThe optimised knowledge-encoded model achieved slightly better classification results compared with the traditional model architecture (AUC = 0.84 vs. AUC = 0.82). We found the proposed model to achieve convergence significantly faster.ConclusionsThe final knowledge-encoded CNN model provided more stable learning performance and faster convergence to optimal diagnostic accuracy. The results fail to demonstrate that PI-RADS-based modelling of CNN architecture can significantly improve performance of prostate cancer recognition using mpMRI.
Highlights
In 2018, it was estimated that prostate cancer (PCa) was the second most common type of cancer globally, contributing to 3.8% of all deaths from the disease (Rawla, 2019)
Reporting of lesions located in other zones, such as in the central zone (CZ), anterior fibromuscular stroma (AFS), or seminal vesicles (SV) is usually performed according to the rules applying to the nearest neighbouring zone, or to the zone from which the lesion appears most likely to have originated
In contrast to the M1 model architecture, in which multi-parametric magnetic resonance imaging (mpMRI) series are processed in parallel, and calculated features are concatenated to produce a final decision, the architecture of model M2 was optimised to encode domain knowledge, reflecting the Prostate Imaging Reporting and Data System (PI-RADS) diagnostic rules
Summary
In 2018, it was estimated that prostate cancer (PCa) was the second most common type of cancer globally, contributing to 3.8% of all deaths from the disease (Rawla, 2019). The architecture of the final CNN model was optimised on the basis of the Prostate Imaging Reporting and Data System (PI-RADS) standard, which is currently the best available indicator in the acquisition, interpretation, and reporting of prostate multi-parametric magnetic resonance imaging (mpMRI) examinations. The architecture of the second model reflects the diagnostic pathway of PI-RADS methodology, using information about a lesion’s primary anatomic location within the prostate gland. Both networks were experimentally tuned to successfully classify prostate cancer changes. The results fail to demonstrate that PI-RADS-based modelling of CNN architecture can significantly improve performance of prostate cancer recognition using mpMRI
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.
