SEGTRANSVAE: Hybrid CNN-Transformer with Regularization for Medical Image Segmentation
dc.contributor.author | Nguyen, Do Trung Chanh | |
dc.contributor.author | Pham, Quan Dung | |
dc.contributor.author | Nguyen, Truong Hai | |
dc.contributor.author | Nguyen, Phuong Nam | |
dc.contributor.author | Nguyen, Khoa N. A. | |
dc.contributor.author | Bui, Trung | |
dc.contributor.author | Truong, Steven Q.H. | |
dc.date.accessioned | 2024-07-25T16:24:14Z | |
dc.date.available | 2024-07-25T16:24:14Z | |
dc.date.issued | 2022 | |
dc.identifier.uri | https://vinspace.edu.vn/handle/VIN/124 | |
dc.description.abstract | Current research on deep learning for medical image segmentation highlights limitations in learning either global semantic information or local contextual information effectively. To address these challenges, this paper introduces a novel network named SegTransVAE. SegTransVAE utilizes an encoder-decoder architecture enhanced with a transformer and a variational autoencoder (VAE) branch to jointly reconstruct input images and perform segmentation. This approach represents a pioneering effort in combining the strengths of CNNs, transformers, and VAEs. Evaluation across various recent datasets demonstrates that SegTransVAE achieves superior performance in Dice Score and 95%-Hausdorff Distance compared to previous methods, while maintaining a comparable inference time to simpler CNN-based architectures. The source code is available at: https://github.com/itruonghai/SegTransVAE. | en_US |
dc.language.iso | en_US | en_US |
dc.subject | transformer | en_US |
dc.subject | variational autoencoder | en_US |
dc.subject | medical image segmentation | en_US |
dc.subject | mri brain tumor | en_US |
dc.subject | ct kidney | en_US |
dc.title | SEGTRANSVAE: Hybrid CNN-Transformer with Regularization for Medical Image Segmentation | en_US |
dc.type | Article | en_US |
Files in this item
This item appears in the following Collection(s)
-
Nguyen Do Trung Chanh, PhD [11]
Model Development Manager - College of Engineering and Computer Science