Fetal Cortical Plate Segmentation Using Fully Convolutional Networks With Multiple Plane Aggregation
- Title
- Fetal Cortical Plate Segmentation Using Fully Convolutional Networks With Multiple Plane Aggregation
- Author
- 이종민
- Keywords
- deep learning; fetal brain; cortical plate; segmentation; hybrid loss; MR
- Issue Date
- 2020-12
- Publisher
- FRONTIERS MEDIA SA
- Citation
- FRONTIERS IN NEUROSCIENCE, v. 14, article no. 591683, page. 1-13
- Abstract
- Fetal magnetic resonance imaging (MRI) has the potential to advance our understanding of human brain development by providing quantitative information of cortical plate (CP) development in vivo. However, for a reliable quantitative analysis of cortical volume and sulcal folding, accurate and automated segmentation of the CP is crucial. In this study, we propose a fully convolutional neural network for the automatic segmentation of the CP. We developed a novel hybrid loss function to improve the segmentation accuracy and adopted multi-view (axial, coronal, and sagittal) aggregation with a test-time augmentation method to reduce errors using three-dimensional (3D) information and multiple predictions. We evaluated our proposed method using the ten-fold cross-validation of 52 fetal brain MR images (22.9-31.4 weeks of gestation). The proposed method obtained Dice coefficients of 0.907 +/- 0.027 and 0.906 +/- 0.031 as well as a mean surface distance error of 0.182 +/- 0.058 mm and 0.185 +/- 0.069 mm for the left and right, respectively. In addition, the left and right CP volumes, surface area, and global mean curvature generated by automatic segmentation showed a high correlation with the values generated by manual segmentation (R-2 ˃ 0.941). We also demonstrated that the proposed hybrid loss function and the combination of multi-view aggregation and test-time augmentation significantly improved the CP segmentation accuracy. Our proposed segmentation method will be useful for the automatic and reliable quantification of the cortical structure in the fetal brain.
- URI
- https://www.frontiersin.org/articles/10.3389/fnins.2020.591683/fullhttps://repository.hanyang.ac.kr/handle/20.500.11754/172979
- ISSN
- 1662-453X
- DOI
- 10.3389/fnins.2020.591683
- Appears in Collections:
- COLLEGE OF ENGINEERING[S](공과대학) > ELECTRICAL AND BIOMEDICAL ENGINEERING(전기·생체공학부) > Articles
- Files in This Item:
- Fetal Cortical Plate Segmentation Using Fully Convolutional Networks With Multiple Plane Aggregation.pdfDownload
- Export
- RIS (EndNote)
- XLS (Excel)
- XML