Premium
Automatic segmentation of hippocampus in hippocampal sparing whole brain radiotherapy: A multitask edge‐aware learning
Author(s) -
Qiu Qingtao,
Yang Ziduo,
Wu Shuyu,
Qian Dongdong,
Wei Jun,
Gong Guanzhong,
Wang Lizhen,
Yin Yong
Publication year - 2021
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1002/mp.14760
Subject(s) - hausdorff distance , wilcoxon signed rank test , segmentation , artificial intelligence , sørensen–dice coefficient , dice , computer science , normalization (sociology) , pattern recognition (psychology) , multi task learning , binary classification , image segmentation , mathematics , statistics , mann–whitney u test , task (project management) , support vector machine , management , sociology , anthropology , economics
Purpose This study aimed to improve the accuracy of the hippocampus segmentation through multitask edge‐aware learning. Method We developed a multitask framework for computerized hippocampus segmentation. We used three‐dimensional (3D) U‐net as our backbone model with two training objectives: (a) to minimize the difference between the targeted binary mask and the model prediction; and (b) to optimize an auxiliary edge‐prediction task which is designed to guide the model detection of the weak boundary of the hippocampus in model optimization. To balance the multiple task objectives, we proposed an improved gradient normalization by adaptively adjusting the weight of losses from different tasks. A total of 247 T1‐weighted MRIs including 131 without contrast and 116 with contrast were collected from 247 patients to train and validate the proposed method. Segmentation was quantitatively evaluated with the dice coefficient (Dice), Hausdorff distance (HD), and average Hausdorff distance (AVD). The 3D U‐net was used for baseline comparison. We used a Wilcoxon signed‐rank test to compare repeated measurements (Dice, HD, and AVD) by different segmentations. Results Through fivefold cross‐validation, our multitask edge‐aware learning achieved Dice of 0.8483 ± 0.0036, HD of 7.5706 ± 1.2330 mm, and AVD of 0.1522 ± 0.0165 mm, respectively. Conversely, the baseline results were 0.8340 ± 0.0072, 10.4631 ± 2.3736 mm, and 0.1884 ± 0.0286 mm, respectively. With a Wilcoxon signed‐rank test, we found that the differences between our method and the baseline were statistically significant ( P < 0.05 ). Conclusion Our results demonstrated the efficiency of multitask edge‐aware learning in hippocampus segmentation for hippocampal sparing whole‐brain radiotherapy. The proposed framework may also be useful for other low‐contrast small organ segmentations on medical imaging modalities.