{"@context":"https://schema.org","@type":"ScholarlyArticle","headline":"AI-driven software for automated quantification of skeletal metastases and treatment response evaluation using whole-body diffusion-weighted MRI (WB-DWI) in advanced prostate cancer.","author":[{"@type":"Person","name":"Antonio Candito"},{"@type":"Person","name":"Matthew D Blackledge"},{"@type":"Person","name":"Richard Holbrey"},{"@type":"Person","name":"Nuria Porta"},{"@type":"Person","name":"Ana Ribeiro"},{"@type":"Person","name":"Fabio Zugni"},{"@type":"Person","name":"Luca D'Erme"},{"@type":"Person","name":"Francesca Castagnoli"},{"@type":"Person","name":"Alina Dragan"},{"@type":"Person","name":"Ricardo Donners"},{"@type":"Person","name":"Christina Messiou"},{"@type":"Person","name":"Nina Tunariu"},{"@type":"Person","name":"Dow-Mu Koh"}],"datePublished":"2025","isPartOf":{"@type":"Periodical","name":"Physics in medicine and biology"},"identifier":"https://doi.org/10.1088/1361-6560/ae19c5","description":"Abstract\n \n Objective\n . Quantitative assessment of treatment response in advanced prostate cancer (APC) with bone metastases remains an unmet clinical need. Whole-body diffusion-weighted MRI (WB-DWI) provides two response biomarkers: total diffusion volume (TDV) and global apparent diffusion coefficient (gADC). However, tracking post-treatment changes of TDV and gADC from manually delineated lesions is cumbersome and increases inter-reader variability. We developed a software to automate this process.\n Approach\n . 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\n b\n = 900 s mm\n −2\n (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 N\n = 10), and compared software-based response assessment with a\n construct reference standard\n , defined as multidisciplinary consensus based on ⩾12 months of imaging, clinical, and laboratory follow-up (\n N\n = 118).\n Main results\n . Average dice score between manual and automated delineations was 0.6 for lesions within pelvis and spine, with an average surface distance of 2 mm. Relative differences for log-transformed TDV (log-TDV) and median gADC were 8.8% and 5%, respectively. Repeatability analysis showed coefficients of variation of 4.6% for log-TDV and 3.5% for median gADC, with intraclass correlation coefficients of 0.94 or higher. The software achieved 80.5% accuracy, 84.3% sensitivity, and 85.7% specificity in assessing response to treatment. Average computation time was 90 s per scan.\n Significance\n . 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.\n ","url":"https://innscience.ca/es/community/literature/58b731b2-c850-400f-8d2a-9b818dc77eca"}