Deep learning assisted atlas-based delineation of the skeleton from Whole-Body Diffusion Weighted MRI in patients with malignant bone disease.

• Deep-learning assisted, atlas-based registration methods for skeleton segmentation in whole-body diffusion weighted imaging (WBDWI) can automate disease delineation of bony metastases. • Automated segmentation provides two potential biomarkers of response: median Apparent Diffusion Coefficient (ADC) and total Diffusion Volume (tDV). • The method is evaluated on a multi-center, dataset of patients diagnosed with metastatic prostate cancer or multiple myeloma. • Automated slice detection and spinal segmentation using deep-learning improves the performance of conventional atlas-based registration techniques in WBDWI. Whole-Body Diffusion Weighted MRI (WBDWI) can provide a basis for quantifying disease volume and apparent diffusion coefficient (ADC) to aid disease staging and response assessment of metastatic bone disease. In this study, we develop atlas-based registration assisted by two AI-based models (i) body-region classification for automatic identification of legs, pelvis, lumbar/thoracic/cervical spine and head, and (ii) automated spinal cord segmentation, to automatically delineate the whole skeleton on WBDWI. Training and validation of AI-based models were performed on 40 patients (32:8 split) with confirmed Advanced Prostate Cancer (APC) who underwent baseline and after treatment WBDWI scans. Consequent atlas-based skeleton segmentation accuracy was validated using leave-one-out cross-validation in a cohort of 15 patients with Multiple Myeloma (MM). Atlas-based registration in combination with AI-based models demonstrated higher performance in segmenting the spinal column when compared with the traditional techniques (average dice score for the lumbar, thoracic and cervical spine of 0.77/0.78/0.68 compared to 0.71/0.69/0.51 from the conventional method, respectively). Similar performances were observed for long bones, pelvic girdle and ribcage (average dice score of 0.65/0.7/0.47, respectively). Our approach demonstrated lower relative median ADC and skeleton volume difference between estimation and ground truth compared to conventional atlas-based methods (average relative median ADC and skeleton volume difference of 10.3/2.1% compared to 13/2.7%, respectively). AI-augmented atlas-based registration substantially improves the accuracy of derived skeletal segmentations from WBDWI compared with traditional atlas-based registration. [ABSTRACT FROM AUTHOR]