Wang Zhi, Chang Yankui, Peng Zhao, Lv Yin, Shi Weijiong, Wang Fan, Pei Xi, Xu X George
Center of Radiological Medical Physics, University of Science and Technology of China, Hefei, China.
Department of Radiation Oncology, First Affiliated Hospital of Anhui Medical University, Hefei, China.
J Appl Clin Med Phys. 2020 Dec;21(12):272-279. doi: 10.1002/acm2.13097. Epub 2020 Nov 25.
To evaluate the accuracy of a deep learning-based auto-segmentation mode to that of manual contouring by one medical resident, where both entities tried to mimic the delineation "habits" of the same clinical senior physician.
This study included 125 cervical cancer patients whose clinical target volumes (CTVs) and organs at risk (OARs) were delineated by the same senior physician. Of these 125 cases, 100 were used for model training and the remaining 25 for model testing. In addition, the medical resident instructed by the senior physician for approximately 8 months delineated the CTVs and OARs for the testing cases. The dice similarity coefficient (DSC) and the Hausdorff Distance (HD) were used to evaluate the delineation accuracy for CTV, bladder, rectum, small intestine, femoral-head-left, and femoral-head-right.
The DSC values of the auto-segmentation model and manual contouring by the resident were, respectively, 0.86 and 0.83 for the CTV (P < 0.05), 0.91 and 0.91 for the bladder (P > 0.05), 0.88 and 0.84 for the femoral-head-right (P < 0.05), 0.88 and 0.84 for the femoral-head-left (P < 0.05), 0.86 and 0.81 for the small intestine (P < 0.05), and 0.81 and 0.84 for the rectum (P > 0.05). The HD (mm) values were, respectively, 14.84 and 18.37 for the CTV (P < 0.05), 7.82 and 7.63 for the bladder (P > 0.05), 6.18 and 6.75 for the femoral-head-right (P > 0.05), 6.17 and 6.31 for the femoral-head-left (P > 0.05), 22.21 and 26.70 for the small intestine (P > 0.05), and 7.04 and 6.13 for the rectum (P > 0.05). The auto-segmentation model took approximately 2 min to delineate the CTV and OARs while the resident took approximately 90 min to complete the same task.
The auto-segmentation model was as accurate as the medical resident but with much better efficiency in this study. Furthermore, the auto-segmentation approach offers additional perceivable advantages of being consistent and ever improving when compared with manual approaches.
评估基于深度学习的自动分割模式与一名住院医师手动勾画轮廓的准确性，两者均试图模仿同一位临床主任医师的勾画“习惯”。
本研究纳入了125例宫颈癌患者，其临床靶区（CTV）和危及器官（OAR）由同一位主任医师勾画。在这125例病例中，100例用于模型训练，其余25例用于模型测试。此外，由主任医师指导约8个月的住院医师对测试病例的CTV和OAR进行了勾画。采用骰子相似系数（DSC）和豪斯多夫距离（HD）来评估CTV、膀胱、直肠、小肠、左侧股骨头和右侧股骨头的勾画准确性。
自动分割模型和住院医师手动勾画的CTV的DSC值分别为0.86和0.83（P<0.05），膀胱为0.91和0.91（P>0.05），右侧股骨头为0.88和0.84（P<0.05），左侧股骨头为0.88和0.84（P<0.05），小肠为0.86和0.81（P<0.05），直肠为0.81和0.84（P>0.05）。CTV的HD（mm）值分别为14.84和18.37（P<0.05），膀胱为7.82和7.63（P>0.05），右侧股骨头为6.18和6.75（P>0.05），左侧股骨头为6.17和6.31（P>0.05），小肠为22.21和26.70（P>0.05），直肠为7.04和6.13（P>0.05）。自动分割模型勾画CTV和OAR大约需要2分钟，而住院医师完成相同任务大约需要90分钟。
在本研究中，自动分割模型与住院医师的准确性相当，但效率更高。此外，与手动方法相比，自动分割方法具有一致性和不断改进等额外的明显优势。
