Zhi Wang1,2, Yankui Chang1, Zhao Peng1, Yin Lv2, Weijiong Shi2, Fan Wang2, Xi Pei1,3, X George Xu1. 1. Center of Radiological Medical Physics, University of Science and Technology of China, Hefei, China. 2. Department of Radiation Oncology, First Affiliated Hospital of Anhui Medical University, Hefei, China. 3. Anhui Wisdom Technology Co., Ltd., Hefei, Anhui, China.
Abstract
OBJECTIVE: 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. METHODS: 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. RESULTS: 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. CONCLUSION: 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.
OBJECTIVE: 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. METHODS: This study included 125 cervical cancerpatients 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. RESULTS: 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. CONCLUSION: 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.
Authors: Elisabeth Weiss; Susanne Richter; Thomas Krauss; Silke I Metzelthin; Andrea Hille; Olivier Pradier; Birgit Siekmeyer; Hilke Vorwerk; Clemens F Hess Journal: Radiother Oncol Date: 2003-04 Impact factor: 6.280
Authors: Xabier Artaechevarria; Arrate Munoz-Barrutia; Carlos Ortiz-de-Solorzano Journal: IEEE Trans Med Imaging Date: 2009-02-18 Impact factor: 10.048
Authors: Jason W Chan; Vasant Kearney; Samuel Haaf; Susan Wu; Madeleine Bogdanov; Mariah Reddick; Nayha Dixit; Atchar Sudhyadhom; Josephine Chen; Sue S Yom; Timothy D Solberg Journal: Med Phys Date: 2019-04-04 Impact factor: 4.071
Authors: M Kosmin; J Ledsam; B Romera-Paredes; R Mendes; S Moinuddin; D de Souza; L Gunn; C Kelly; C O Hughes; A Karthikesalingam; C Nutting; R A Sharma Journal: Radiother Oncol Date: 2019-03-22 Impact factor: 6.280
Authors: X Allen Li; An Tai; Douglas W Arthur; Thomas A Buchholz; Shannon Macdonald; Lawrence B Marks; Jean M Moran; Lori J Pierce; Rachel Rabinovitch; Alphonse Taghian; Frank Vicini; Wendy Woodward; Julia R White Journal: Int J Radiat Oncol Biol Phys Date: 2009-03-01 Impact factor: 7.038
Authors: Bo Yang; Yankui Chang; Yongguang Liang; Zhiqun Wang; Xi Pei; Xie George Xu; Jie Qiu Journal: Front Oncol Date: 2022-05-30 Impact factor: 5.738
Authors: Antonio Otal; Francisco Celada; Jose Chimeno; Javier Vijande; Santiago Pellejero; Maria-Jose Perez-Calatayud; Elena Villafranca; Naiara Fuentemilla; Francisco Blazquez; Silvia Rodriguez; Jose Perez-Calatayud Journal: Cancers (Basel) Date: 2022-07-17 Impact factor: 6.575