Advancing Brain Tumor Segmentation in MRI Scans: Hybrid Attention-Residual UNET with Transformer Blocks
- Title
- Advancing Brain Tumor Segmentation in MRI Scans: Hybrid Attention-Residual UNET with Transformer Blocks
- Creator
- Sobha Xavier P.; Sathish P.K.; Raju G.
- Description
- Accurate segmentation of brain tumors is vital for effective treatment planning, disease diagnosis, and monitoring treatment outcomes. Post-surgical monitoring, particularly for recurring tumors, relies on MRI scans, presenting challenges in segmenting small residual tumors due to surgical artifacts. This emphasizes the need for a robust model with superior feature extraction capabilities for precise segmentation in both pre-and post-operative scenarios. The study introduces the Hybrid Attention-Residual UNET with Transformer Blocks (HART-UNet), enhancing the U-Net architecture with a spatial self-attention module, deep residual connections, and RESNET50 weights. Trained on BRATS20 and validated on Kaggle LGG and BTC_ postop datasets, HART-UNet outperforms established models (UNET, Attention UNET, UNET++, and RESNET 50), achieving Dice Coefficients of 0.96, 0.97, and 0.88, respectively. These results underscore the models superior segmentation performance, marking a significant advancement in brain tumor analysis across pre-and post-operative MRI scans. 2024 by the authors of this article.
- Source
- International journal of online and biomedical engineering, Vol-20, No. 6, pp. 103-115.
- Date
- 2024-01-01
- Publisher
- International Federation of Engineering Education Societies (IFEES)
- Subject
- attention UNET; post-operative MRI; residual tumors; RESNET-50; UNET; UNET++
- Coverage
- Sobha Xavier P., Department of Computer Science, Christ (Deemed to be University), Karnataka, Bengaluru, India; Sathish P.K., Department of Computer Science, Christ (Deemed to be University), Karnataka, Bengaluru, India; Raju G., Department of Computer Science, Christ (Deemed to be University), Karnataka, Bengaluru, India
- Rights
- All Open Access; Gold Open Access
- Relation
- ISSN: 26268493
- Format
- Online
- Language
- English
- Type
- Article
Collection
Citation
Sobha Xavier P.; Sathish P.K.; Raju G., “Advancing Brain Tumor Segmentation in MRI Scans: Hybrid Attention-Residual UNET with Transformer Blocks,” CHRIST (Deemed To Be University) Institutional Repository, accessed March 6, 2025, https://archives.christuniversity.in/items/show/13651.