Fangjie Liu1, Wanqi Chen2, Zhikai Liu2, Yinjie Tao2, Xia Liu2, Fuquan Zhang2, Jing Shen2, Hui Guan2, Hongnan Zhen2, Shaobin Wang3, Qi Chen3, Yu Chen3, Xiaorong Hou2. 1. Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, 510060, People's Republic of China. 2. Department of Radiation Oncology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Beijing, 100730, People's Republic of China. 3. MedMind Technology Co., Ltd., Beijing, 100055, People's Republic of China.
Abstract
OBJECTIVE: Delineation of clinical target volume (CTV) and organs at risk (OARs) is important for radiotherapy but is time-consuming. We trained and evaluated a U-ResNet model to provide fast and consistent auto-segmentation. METHODS: We collected 160 patients' CT scans with breast cancer who underwent breast-conserving surgery (BCS) and were treated with radiotherapy. CTV and OARs were delineated manually and were used for model training. The dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (95HD) were used to assess the performance of our model. CTV and OARs were randomly selected as ground truth (GT) masks, and artificial intelligence (AI) masks were generated by the proposed model. Two clinicians randomly compared CTV score differences of the contour. The consistency between two clinicians was tested. Time cost for auto-delineation was evaluated. RESULTS: The mean DSC values of the proposed method were 0.94, 0.95, 0.94, 0.96, 0.96 and 0.93 for breast CTV, contralateral breast, heart, right lung, left lung and spinal cord, respectively. The mean 95HD values were 4.31mm, 3.59mm, 4.86mm, 3.18mm, 2.79mm and 4.37mm for the above structures, respectively. The average CTV scores for AI and GT were 2.89 versus 2.92 when evaluated by oncologist A (P=0.612), and 2.75 versus 2.83 by oncologist B (P=0.213), with no statistically significant differences. The consistency between two clinicians was poor (kappa=0.282). The time for auto-segmentation of CTV and OARs was 10.03 s. CONCLUSION: Our proposed model (U-ResNet) can improve the efficiency and accuracy of delineation compared with U-Net, performing equally well with the segmentation generated by oncologists.
OBJECTIVE: Delineation of clinical target volume (CTV) and organs at risk (OARs) is important for radiotherapy but is time-consuming. We trained and evaluated a U-ResNet model to provide fast and consistent auto-segmentation. METHODS: We collected 160 patients' CT scans with breast cancer who underwent breast-conserving surgery (BCS) and were treated with radiotherapy. CTV and OARs were delineated manually and were used for model training. The dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (95HD) were used to assess the performance of our model. CTV and OARs were randomly selected as ground truth (GT) masks, and artificial intelligence (AI) masks were generated by the proposed model. Two clinicians randomly compared CTV score differences of the contour. The consistency between two clinicians was tested. Time cost for auto-delineation was evaluated. RESULTS: The mean DSC values of the proposed method were 0.94, 0.95, 0.94, 0.96, 0.96 and 0.93 for breast CTV, contralateral breast, heart, right lung, left lung and spinal cord, respectively. The mean 95HD values were 4.31mm, 3.59mm, 4.86mm, 3.18mm, 2.79mm and 4.37mm for the above structures, respectively. The average CTV scores for AI and GT were 2.89 versus 2.92 when evaluated by oncologist A (P=0.612), and 2.75 versus 2.83 by oncologist B (P=0.213), with no statistically significant differences. The consistency between two clinicians was poor (kappa=0.282). The time for auto-segmentation of CTV and OARs was 10.03 s. CONCLUSION: Our proposed model (U-ResNet) can improve the efficiency and accuracy of delineation compared with U-Net, performing equally well with the segmentation generated by oncologists.
Authors: V Batumalai; E S Koh; G P Delaney; L C Holloway; M G Jameson; G Papadatos; D M Lonergan Journal: Clin Oncol (R Coll Radiol) Date: 2010-11-18 Impact factor: 4.126
Authors: Peter Steenbergen; Karin Haustermans; Evelyne Lerut; Raymond Oyen; Liesbeth De Wever; Laura Van den Bergh; Linda G W Kerkmeijer; Frank A Pameijer; Wouter B Veldhuis; Jochem R N van der Voort van Zyp; Floris J Pos; Stijn W Heijmink; Robin Kalisvaart; Hendrik J Teertstra; Cuong V Dinh; Ghazaleh Ghobadi; Uulke A van der Heide Journal: Radiother Oncol Date: 2015-04-29 Impact factor: 6.280
Authors: Nikolaj K G Jensen; Danielle Mulder; Michael Lock; Barbara Fisher; Rebecca Zener; Ben Beech; Roman Kozak; Jeff Chen; Ting-Yim Lee; Eugene Wong Journal: Radiother Oncol Date: 2014-03-13 Impact factor: 6.280
Authors: Kuo Men; Tao Zhang; Xinyuan Chen; Bo Chen; Yu Tang; Shulian Wang; Yexiong Li; Jianrong Dai Journal: Phys Med Date: 2018-05-19 Impact factor: 2.685