DeepTarget: Gross tumor and clinical target volume segmentation in esophageal cancer radiotherapy

• Published in: Medical image analysis 2021-02, Vol.68, p.101909-101909, Article 101909
• Main Authors: Jin, Dakai, Guo, Dazhou, Ho, Tsung-Ying, Harrison, Adam P., Xiao, Jing, Tseng, Chen-kan, Lu, Le
• Format: Article
• Language: English
• Subjects: Cancer; Clinical target volume; Computed tomography; Contouring; Delineation; Distance transform; Esophageal cancer; Esophagus; Gross tumor volume; Image contrast; Image segmentation; Lymph nodes; Metric space; Multi-modality fusion; PET/CT; Positron emission; Positron emission tomography; Radiation therapy; Radiotherapy; Reduction; RTCT; Segmentation; Target recognition; Tomography; Tumors
• ISSN: 1361-8415; 1361-8423
• DOI: 10.1016/j.media.2020.101909

•Segment esophageal GTV using a new CT/PET based two-stream chained deep fusion method.•Propose a simple yet powerful progressive semantically-nested network to segment GTV.•Segment esophageal CTV using a novel spatial-context encoded deep framework.•Establish significant GTV and CTV improvements over prior arts by extensive experiments.•Study the impact of GTV on the CTV segmentation making the whole workflow more interconnected. [Display omitted] Gross tumor volume (GTV) and clinical target volume (CTV) delineation are two critical steps in the cancer radiotherapy planning. GTV defines the primary treatment area of the gross tumor, while CTV outlines the sub-clinical malignant disease. Automatic GTV and CTV segmentation are both challenging for distinct reasons: GTV segmentation relies on the radiotherapy computed tomography (RTCT) image appearance, which suffers from poor contrast with the surrounding tissues, while CTV delineation relies on a mixture of predefined and judgement-based margins. High intra- and inter-user variability makes this a particularly difficult task. We develop tailored methods solving each task in the esophageal cancer radiotherapy, together leading to a comprehensive solution for the target contouring task. Specifically, we integrate the RTCT and positron emission tomography (PET) modalities together into a two-stream chained deep fusion framework taking advantage of both modalities to facilitate more accurate GTV segmentation. For CTV segmentation, since it is highly context-dependent—it must encompass the GTV and involved lymph nodes while also avoiding excessive exposure to the organs at risk—we formulate it as a deep contextual appearance-based problem using encoded spatial distances of these anatomical structures. This better emulates the margin- and appearance-based CTV delineation performed by oncologists. Adding to our contributions, for the GTV segmentation we propose a simple yet effective progressive semantically-nested network (PSNN) backbone that outperforms more complicated models. Our work is the first to provide a comprehensive solution for the esophageal GTV and CTV segmentation in radiotherapy planning. Extensive 4-fold cross-validation on 148 esophageal cancer patients, the largest analysis to date, was carried out for both tasks. The results demonstrate that our GTV and CTV segmentation approaches significantly improve the performance over previous state-of-the-art works, e.g., by 8.7% increases in Dice score