• Ying-Chou Sun, Ang-Ting Hsieh, Ssu-Ting Fang, Hsiu-Mei Wu, Liang-Wei Kao, Wen-Yuh Chung, Hung-Hsun Chen, Kang-Du Liou, Yu-Shiou Lin, Wan-Yuo Guo, and Henry Horng-Shing Lu.
• Department of Radiology, Taipei Veterans General Hospital, Taipei, Taiwan, ROC.
• J Chin Med Assoc. 2021 Oct 1; 84 (10): 956962956-962.

BackgroundThis study aimed to compare the prediction performance of two-dimensional (2D) and three-dimensional (3D) semantic segmentation models for intracranial metastatic tumors with a volume ≥ 0.3 mL.MethodsWe used postcontrast T1 whole-brain magnetic resonance (MR), which was collected from Taipei Veterans General Hospital (TVGH). Also, the study was approved by the institutional review board (IRB) of TVGH. The 2D image segmentation model does not fully use the spatial information between neighboring slices, whereas the 3D segmentation model does. We treated the U-Net as the basic model for 2D and 3D architectures.ResultsFor the prediction of intracranial metastatic tumors, the area under the curve (AUC) of the 3D model was 87.6% and that of the 2D model was 81.5%.ConclusionBuilding a semantic segmentation model based on 3D deep convolutional neural networks might be crucial to achieve a high detection rate in clinical applications for intracranial metastatic tumors.Copyright © 2021, the Chinese Medical Association.

9 keywords...

hide…