As Artificial Intelligence (AI) has boomed with countless applications in virtually every field of technology and learning, medicine is also benefitting. A branch of AI called Deep Learning (DL) is modeled after the layers of neural networks involved in the brain’s learning processes. By layering algorithms, to process data, DL mimics how the brain thinks, learning to recognize patterns and project features. Thus, DL can enhance prostate cancer (PCa) identification in magnetic resonance imaging (MRI) of the prostate.
A new study out of Japan reports the use of DL to diagnose PCa based on MRI imaging[i]. The authors applied their algorithms to both multiparametric MRI (mpMRI) scans (T2 weights, diffusion weighted, and dynamic contrast enhanced sequences) and biparametric MRI (bpMRI) scans which do not involve dynamic contrast enhancement. Their purpose was to compare diagnostic performance of mpMRI vs. bpMRI via DL.
They found that the use of all three parameters gave better results. They wrote, “When using deep learning, multiparametric imaging provides superior performance to biparametric imaging in the specificity and positive predictive value, especially in the peripheral zone. Dynamic contrast-enhanced imaging helps reduce overdiagnosis in multiparametric imaging.”
Their results are consistent with our own experience of mpMRI. Although the algorithms developed by the authors for this comparison study are not available for our use, we do integrate AI in our detection and diagnostic scans on our powerful 3T magnet. AI is a valuable resource for both efficiency and confirmation in our patient services. It’s a pleasure to find research that validates the merits of our own pioneering work with both MRI and AI.
NOTE: This content is solely for purposes of information and does not substitute for diagnostic or medical advice. Talk to your doctor if you are experiencing pelvic pain, or have any other health concerns or questions of a personal medical nature.
[i] Matsuoka Y, Ueno Y, Uehara S, Tanaka H et al. Deep-learning prostate cancer detection and segmentation on biparametric versus multiparametric magnetic resonance imaging: Added value of dynamic contrast-enhanced imaging. Int J Urol. 2023 Aug 22.