Synthetic CT‐aided multiorgan segmentation for CBCT‐guided adaptive pancreatic radiotherapy

• Published in: Medical physics (Lancaster) 2021-11, Vol.48 (11), p.7063-7073
• Main Authors: Dai, Xianjin, Lei, Yang, Wynne, Jacob, Janopaul‐Naylor, James, Wang, Tonghe, Roper, Justin, Curran, Walter J., Liu, Tian, Patel, Pretesh, Yang, Xiaofeng
• Format: Article
• Language: English
• Subjects: adaptive radiation therapy; automated contouring; Cone-Beam Computed Tomography; deep learning; Humans; Image Processing, Computer-Assisted; mask R‐CNN; multiorgan segmentation; Organs at Risk; Pancreas; pancreatic cancer; Radiotherapy Planning, Computer-Assisted; Spiral Cone-Beam Computed Tomography
• ISSN: 0094-2405; 2473-4209
• DOI: 10.1002/mp.15264

Purpose The delineation of organs at risk (OARs) is fundamental to cone‐beam CT (CBCT)‐based adaptive radiotherapy treatment planning, but is time consuming, labor intensive, and subject to interoperator variability. We investigated a deep learning‐based rapid multiorgan delineation method for use in CBCT‐guided adaptive pancreatic radiotherapy. Methods To improve the accuracy of OAR delineation, two innovative solutions have been proposed in this study. First, instead of directly segmenting organs on CBCT images, a pretrained cycle‐consistent generative adversarial network (cycleGAN) was applied to generating synthetic CT images given CBCT images. Second, an advanced deep learning model called mask‐scoring regional convolutional neural network (MS R‐CNN) was applied on those synthetic CT to detect the positions and shapes of multiple organs simultaneously for final segmentation. The OAR contours delineated by the proposed method were validated and compared with expert‐drawn contours for geometric agreement using the Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), mean surface distance (MSD), and residual mean square distance (RMS). Results Across eight abdominal OARs including duodenum, large bowel, small bowel, left and right kidneys, liver, spinal cord, and stomach, the geometric comparisons between automated and expert contours are as follows: 0.92 (0.89–0.97) mean DSC, 2.90 mm (1.63–4.19 mm) mean HD95, 0.89 mm (0.61–1.36 mm) mean MSD, and 1.43 mm (0.90–2.10 mm) mean RMS. Compared to the competing methods, our proposed method had significant improvements (p