Signal-based AI-driven software solution for automated quantification of metastatic bone disease and treatment response assessment using Whole-Body Diffusion-Weighted MRI (WB-DWI) biomarkers in Advanced Prostate Cancer

2025-05-13

AI Summary

This study addresses the challenge of quantitative assessment of bone metastatic burden and treatment response in advanced prostate cancer. Methodologically, we propose a fully automated AI framework based on whole-body diffusion-weighted MRI (WB-DWI): (1) a weakly supervised Residual U-Net generates skeletal probability maps to guide lesion detection; (2) a WB-DWI intensity statistical normalization strategy is introduced; and (3) a lightweight CNN enables end-to-end lesion segmentation, followed by registration with gADC maps to extract tumor diffusion volume (TDV) and median gADC—key quantitative biomarkers. Our key contribution is enabling bone metastasis quantification without per-lesion annotation. Validation demonstrates skeletal segmentation Dice scores of 0.6 (pelvis/spine), coefficient of variation (CV) of 4.6% for log-TDV and 3.6% for median gADC, and treatment response classification accuracy of 80.5%, sensitivity of 84.3%, and specificity of 85.7%. Processing time per case is 90 seconds.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Adversarial Attacks & Robustness
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

We developed an AI-driven software solution to quantify metastatic bone disease from WB-DWI scans. Core technologies include: (i) a weakly-supervised Residual U-Net model generating a skeleton probability map to isolate bone; (ii) a statistical framework for WB-DWI intensity normalisation, obtaining a signal-normalised b=900s/mm^2 (b900) image; and (iii) a shallow convolutional neural network that processes outputs from (i) and (ii) to generate a mask of suspected bone lesions, characterised by higher b900 signal intensity due to restricted water diffusion. This mask is applied to the gADC map to extract TDV and gADC statistics. We tested the tool using expert-defined metastatic bone disease delineations on 66 datasets, assessed repeatability of imaging biomarkers (N=10), and compared software-based response assessment with a construct reference standard based on clinical, laboratory and imaging assessments (N=118). Dice score between manual and automated delineations was 0.6 for lesions within pelvis and spine, with an average surface distance of 2mm. Relative differences for log-transformed TDV (log-TDV) and median gADC were below 9% and 5%, respectively. Repeatability analysis showed coefficients of variation of 4.57% for log-TDV and 3.54% for median gADC, with intraclass correlation coefficients above 0.9. The software achieved 80.5% accuracy, 84.3% sensitivity, and 85.7% specificity in assessing response to treatment compared to the construct reference standard. Computation time generating a mask averaged 90 seconds per scan. Our software enables reproducible TDV and gADC quantification from WB-DWI scans for monitoring metastatic bone disease response, thus providing potentially useful measurements for clinical decision-making in APC patients.

Problem

• Automated quantification of metastatic bone disease using AI
• Assessment of treatment response in advanced prostate cancer
• Signal normalization and lesion detection in WB-DWI scans

Innovation

• Weakly-supervised Residual U-Net for bone isolation
• WB-DWI intensity normalization via statistical framework
• Shallow CNN for lesion detection using normalized signals