Automatic segmentation of the uterus on MRI using a convolutional neural network. (November 2019)

• Record Type: Journal Article
• Authors: Kurata, Yasuhisa; Nishio, Mizuho; Kido, Aki; Fujimoto, Koji; Yakami, Masahiro; Isoda, Hiroyoshi; Togashi, Kaori
• Is Part Of: Computers in biology and medicine. Volume 114(2019)
• Publication Date: 2019-11
• Subjects: Uterus -- Segmentation -- Convolutional neural network -- CNN -- U-net; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2019.103438
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Background: This study was performed to evaluate the clinical feasibility of a U-net for fully automatic uterine segmentation on MRI by using images of major uterine disorders. Methods: This study included 122 female patients (14 with uterine endometrial cancer, 15 with uterine cervical cancer, and 55 with uterine leiomyoma). U-net architecture optimized for our research was used for automatic segmentation. Three-fold cross-validation was performed for validation. The results of manual segmentation of the uterus by a radiologist on T2-weighted sagittal images were used as the gold standard. Dice similarity coefficient (DSC) and mean absolute distance (MAD) were used for quantitative evaluation of the automatic segmentation. Visual evaluation using a 4-point scale was performed by two radiologists. DSC, MAD, and the score of the visual evaluation were compared between uteruses with and without uterine disorders. Results: The mean DSC of our model for all patients was 0.82. The mean DSCs for patients with and without uterine disorders were 0.84 and 0.78, respectively (p = 0.19). The mean MADs for patients with and without uterine disorders were 18.5 and 21.4 [pixels], respectively (p = 0.39). The scores of the visual evaluation were not significantly different between uteruses with and without uterine disorders. Conclusions: Fully automatic uterine segmentation with our modified U-net was clinically feasible. The performance of the segmentation of our model was not influenced by the presence of uterine disorders. Highlights: This study evaluated a U-net for uterine segmentation on images of uterine disorders. Dice similarity coefficient (DSC) and mean absolute distance (MAD) were used. Mean DSCs for presence and absence of uterine disorders were 0.84 and 0.78. Mean MADs for presence and absence of uterine disorders were 18.5 and 21.4 pixels. Uterine segmentation with our U-net was feasible and unaffected by uterine disorders.