Human-in-the-loop informed deep learning rectal tumor segmentation on pre-treatment MRI
Publication Title
Proceedings Volume 12927, Medical Imaging 2024: Computer-Aided Diagnosis; 1292707
Document Type
Presentation
Publication Date
4-3-2024
Keywords
oregon; chiles
Abstract
Precise segmentation of rectal cancer tumors on routine MRI is critical for accurate clinical staging and downstream computational analyses. While deep learning-based segmentation algorithms have shown much promise in automating the otherwise tedious, subjective, and costly process of manual segmentation, they require significant amounts of manually annotated data for training. To address these limitations of deep learning-based segmentation models, we present a novel deep learning framework that incorporates human-in-the-loop (HITL) refinement to automatically delineate rectal tumors on multi-plane pre-treatment MR imaging. When evaluated on multiple holdout validation cohorts including a clinical trial dataset, the post-HITL segmentation model significantly outperformed the pre-HITL model with median dice similarity coefficient of 0.763 and Hausdorff distance of 28.4mm in comparison to 0.601 and 31.8mm, respectively. HITL refinement learning also significantly accelerated the manual annotation process by 20 minutes. HITL learning represents a feasible, effective, and efficient solution to semi-automated tumor segmentation on routine rectal cancer MRI scans.
Area of Special Interest
Cancer
Area of Special Interest
Digestive Health
Specialty/Research Institute
Oncology
Specialty/Research Institute
Gastroenterology
Specialty/Research Institute
Surgery
Comments
Michael Kong, Thomas DeSilvio, Leo Bao, Brennan Flannery, Benjamin N. Parker, Stephen Tang, Murad Labbad, Gregory O'Connor, Amit Gupta, Emily Steinhagen M.D., Andrei S. Purysko, William Hall, David Liska, Eric L. Marderstein M.D., Aaron Carroll M.D., Marka Crittenden M.D., Michael Gough M.D., Kristina Young M.D., Satish E. Viswanath