🤖 AI Summary
Clinical whole-body diffusion-weighted imaging (WB-DWI) requires precise anatomical segmentation for accurate ADC quantification and tumor volume (TDV) measurement. However, manual delineation of the entire skeleton, visceral organs (liver, spleen, kidneys, bladder), and spinal canal is prohibitively time-consuming and clinically infeasible. To address this, we propose the first weakly supervised segmentation framework tailored for WB-DWI: a soft-label–guided 3D residual U-Net enabling simultaneous probabilistic segmentation of multiple structures without voxel-level annotations. Leveraging multi-center data, patch-based training, and probabilistic output maps, our method achieves clinical efficiency—25 seconds per case (12× faster than conventional approaches)—while attaining mean Dice scores of 0.66 (skeleton), 0.80 (organs), and 0.85 (spinal canal), with surface distances <3 mm. Quantitative errors in ADC and volume measurements are <10% and <4%, respectively. Radiologists rated the results as “good to excellent.”
📝 Abstract
Background: Apparent Diffusion Coefficient (ADC) values and Total Diffusion Volume (TDV) from Whole-body diffusion-weighted MRI (WB-DWI) are recognized cancer imaging biomarkers. However, manual disease delineation for ADC and TDV measurements is unfeasible in clinical practice, demanding automation. As a first step, we propose an algorithm to generate fast and reproducible probability maps of the skeleton, adjacent internal organs (liver, spleen, urinary bladder, and kidneys), and spinal canal. Methods: We developed an automated deep-learning pipeline based on a 3D patch-based Residual U-Net architecture that localizes and delineates these anatomical structures on WB-DWI. The algorithm was trained using"soft-labels"(non-binary segmentations) derived from a computationally intensive atlas-based approach. For training and validation, we employed a multi-center WB-DWI dataset comprising 532 scans from patients with Advanced Prostate Cancer (APC) or Multiple Myeloma (MM), with testing on 45 patients. Results: Our weakly-supervised deep learning model achieved an average dice score/precision/recall of 0.66/0.6/0.73 for skeletal delineations, 0.8/0.79/0.81 for internal organs, and 0.85/0.79/0.94 for spinal canal, with surface distances consistently below 3 mm. Relative median ADC and log-transformed volume differences between automated and manual expert-defined full-body delineations were below 10% and 4%, respectively. The computational time for generating probability maps was 12x faster than the atlas-based registration algorithm (25 s vs. 5 min). An experienced radiologist rated the model's accuracy"good"or"excellent"on test datasets. Conclusion: Our model offers fast and reproducible probability maps for localizing and delineating body regions on WB-DWI, enabling ADC and TDV quantification, potentially supporting clinicians in disease staging and treatment response assessment.