# Explainable Anatomy-Guided AI for Prostate MRI: Foundation Models and In Silico Clinical Trials for Virtual Biopsy-based Risk Assessment

arXiv: https://arxiv.org/abs/2505.17971 · HTML: https://mlsanity.com/paper/2505.17971/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 28 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 5 of 5)

- [Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods](https://mlsanity.com/paper/2111.02398/) (2021)
- [Overcoming Data Scarcity in Biomedical Imaging with a Foundational Multi-Task Model](https://mlsanity.com/paper/2311.09847/) (2023)
- [Tissue Concepts: supervised foundation models in computational pathology](https://mlsanity.com/paper/2409.03519/) (2024)
- [DiffExplainer: Unveiling Black Box Models Via Counterfactual Generation](https://mlsanity.com/paper/2406.15182/) (2024)
- [Counterfactuals and Uncertainty-Based Explainable Paradigm for the Automated Detection and Segmentation of Renal Cysts in Computed Tomography Images: A Multi-Center Study](https://mlsanity.com/paper/2408.03789/) (2024)

## Abstract (arXiv)

We present a fully automated, anatomically guided deep learning pipeline for prostate cancer (PCa) risk stratification using routine MRI. The pipeline integrates three key components: an nnU-Net module for segmenting the prostate gland and its zones on axial T2-weighted MRI; a classification module based on the UMedPT Swin Transformer foundation model, fine-tuned on 3D patches with optional anatomical priors and clinical data; and a VAE-GAN framework for generating counterfactual heatmaps that localize decision-driving image regions. The system was developed using 1,500 PI-CAI cases for segmentation and 617 biparametric MRIs with metadata from the CHAIMELEON challenge for classification (split into 70% training, 10% validation, and 20% testing). Segmentation achieved mean Dice scores of 0.95 (gland), 0.94 (peripheral zone), and 0.92 (transition zone). Incorporating gland priors improved AUC from 0.69 to 0.72, with a three-scale ensemble achieving top performance (AUC = 0.79, composite score = 0.76), outperforming the 2024 CHAIMELEON challenge winners. Counterfactual heatmaps reliably highlighted lesions within segmented regions, enhancing model interpretability. In a prospective multi-center in-silico trial with 20 clinicians, AI assistance increased diagnostic accuracy from 0.72 to 0.77 and Cohen's kappa from 0.43 to 0.53, while reducing review time per case by 40%. These results demonstrate that anatomy-aware foundation models with counterfactual explainability can enable accurate, interpretable, and efficient PCa risk assessment, supporting their potential use as virtual biopsies in clinical practice.