Santiago Salimbeni
Santiago Nicolet
Abstract:
Advances in AI (AI) have greatly enhanced prostate cancer diagnosis (PCaD). This systematic review (2022–2025) evaluates recent developments, techniques, and the effectiveness of AI-based decision support tools. Convolutional neural networks and generative adversarial networks (GANs) are the most prevalent methods, applied to MRI image classification, lesion detection, segmentation, and image enhancement. These approaches improve lesion localisation, diagnostic precision, and consistency among radiologists and pathologists, while multi-modal systems help reduce unnecessary interven¬tions. Despite progress, key challenges include data heterogeneity, limited model generalisability, and lack of interpretability. Future directions highlight AI-driven risk stratification, streamlined MRI protocols, and integrated imaging pathways. Overall, AI offers promising tools for earlier detection and more personalised, efficient, and patient-centred management of prostate cancer.
International Scientific Multidisciplinary Conference: AI for a Smarter Tomorrow - AI-SMART , September 25-26, 2025
Creative Commons Non Commercial CC BY-NC: This article is distributed under the terms of the Creative Commons Attribution-Non-Commercial 4.0 License (https://creativecommons.org/licenses/by-nc/4.0/) which permits non-commercial use, reproduction and distribution of the work without further permission.
