Can 3D artificial intelligence models outshine 2D ones in the detection of intracranial metastatic tumors on magnetic resonance images?. Issue 10 (1st September 2021)

• Record Type: Journal Article
• Authors: Sun, Ying-Chou; Hsieh, Ang-Ting; Fang, Ssu-Ting; Wu, Hsiu-Mei; Kao, Liang-Wei; Chung, Wen-Yuh; Chen, Hung-Hsun; Liou, Kang-Du; Lin, Yu-Shiou; Guo, Wan-Yuo; Lu, Henry Horng-Shing
• Is Part Of: Journal of the Chinese Medical Association. Volume 84:Issue 10(2021)
• Page Start: 956
• Page End: 962
• Publication Date: 2021-09-01
• Subjects: Area under the curve -- Deep learning -- Neural networks -- Semantic; Medicine -- Periodicals; 610.5
• DOI: 10.1097/JCMA.0000000000000614
• Languages: English
• ISSNs: 1726-4901

Abstract

Abstract : Background: This 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. Methods: We 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. Results: For 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%. Conclusion: Building 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.