Clinical evaluation of deep learning–based clinical target volume three-channel auto-segmentation algorithm for adaptive radiotherapy in cervical cancer

• Published in: BMC medical imaging Vol. 22; no. 1; pp. 1 - 10
• Main Authors: Ma, Chen-ying, Zhou, Ju-ying, Xu, Xiao-ting, Qin, Song-bing, Han, Miao-fei, Cao, Xiao-huan, Gao, Yao-zong, Xu, Lu, Zhou, Jing-jie, Zhang, Wei, Jia, Le-cheng
• Format: Journal Article
• Language: English
• Published: London BioMed Central 09.07.2022; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Adaptive algorithms; Algorithms; Auto-segmentation; Cancer; Cancer therapies; Cervical cancer; Cervical cancer CTV; Cervix; Computed tomography; Contouring; CT imaging; Datasets; Deep learning; Formability; Image segmentation; Imaging; Lymphatic system; Machine learning; Medical imaging; Medical screening; Medicine; Medicine & Public Health; Metastasis; Methods; Metric space; Patients; Planning; Radiation; Radiation therapy; Radiology; Radiotherapy; Registration; Similarity coefficient method; Tumors; Vagina; Deep learning; Cervical cancer CTV; Auto-segmentation; Registration
• ISSN: 1471-2342; 1471-2342
• DOI: 10.1186/s12880-022-00851-0

Objectives Accurate contouring of the clinical target volume (CTV) is a key element of radiotherapy in cervical cancer. We validated a novel deep learning (DL)-based auto-segmentation algorithm for CTVs in cervical cancer called the three-channel adaptive auto-segmentation network (TCAS). Methods A total of 107 cases were collected and contoured by senior radiation oncologists (ROs). Each case consisted of the following: (1) contrast-enhanced CT scan for positioning, (2) the related CTV, (3) multiple plain CT scans during treatment and (4) the related CTV. After registration between (1) and (3) for the same patient, the aligned image and CTV were generated. Method 1 is rigid registration, method 2 is deformable registration, and the aligned CTV is seen as the result. Method 3 is rigid registration and TCAS, method 4 is deformable registration and TCAS, and the result is generated by a DL-based method. Results From the 107 cases, 15 pairs were selected as the test set. The dice similarity coefficient (DSC) of method 1 was 0.8155 ± 0.0368; the DSC of method 2 was 0.8277 ± 0.0315; the DSCs of method 3 and 4 were 0.8914 ± 0.0294 and 0.8921 ± 0.0231, respectively. The mean surface distance and Hausdorff distance of methods 3 and 4 were markedly better than those of method 1 and 2. Conclusions The TCAS achieved comparable accuracy to the manual delineation performed by senior ROs and was significantly better than direct registration.