Multihead Neural Network for Multiple Segmented Images-based Diagnosis of Thyroid-associated Orbitopathy Activityopen access
- Authors
- Lee, Sanghyuck; Lee, Jeong Kyu; Lee, Jaesung
- Issue Date
- Mar-2024
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- Artificial neural networks; Computed tomography; Computed tomography; Eyes; Feature extraction; Image segmentation; Multihead neural network; Optical imaging; Orbits; Thyroid-associated orbitopathy
- Citation
- IEEE Access, v.12, pp 43862 - 43873
- Pages
- 12
- Journal Title
- IEEE Access
- Volume
- 12
- Start Page
- 43862
- End Page
- 43873
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/73151
- DOI
- 10.1109/ACCESS.2024.3379886
- ISSN
- 2169-3536
- Abstract
- Thyroid-associated orbitopathy is an autoimmune disease that causes changes in various structures close to the eye. Medical images, such as three-dimensional computed tomography scans, can be used by medical experts to diagnose thyroid-associated orbitopathy. Meanwhile, image segmentation has been widely used in medical imaging owing to its significant impact on improving model performance by filtering out unnecessary pixel values. In this study, a neural network specialized in processing multiple segmented images was proposed to evaluate thyroid orbitopathy activity, focusing on the fact that multiple segmented images can be extracted from orbital computed tomography scans. The proposed neural network consists of multiple convolutional embedding heads, a group squeeze-and-excitation block, and a classifier stage. Our empirical study shows that the proposed model outperforms four baseline models on a thyroid-associated orbitopathy activity dataset obtained from a cohort of 1,068 patients at Chung-Ang University Hospital between January 2008 and October 2019. The proposed model achieved an average area under the receiver operating characteristic curve of 0.800, accuracy of 0.721, F1 score of 0.416, sensitivity of 0.728, and specificity of 0.720 across 50 replicate experiments. The source code for the proposed model is available at https://github.com/tkdgur658/MultiheadGroupSENet. Authors
- Files in This Item
-
- Appears in
Collections - College of Software > Department of Artificial Intelligence > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/73151)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.