Modality-Aware and Shift Mixer for Multi-modal Brain Tumor Segmentation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914701199278080 |
|---|---|
| author | Huang, Zhongzhen Wei, Linda Zhang, Shaoting Zhang, Xiaofan |
| author_facet | Huang, Zhongzhen Wei, Linda Zhang, Shaoting Zhang, Xiaofan |
| contents | Combining images from multi-modalities is beneficial to explore various information in computer vision, especially in the medical domain. As an essential part of clinical diagnosis, multi-modal brain tumor segmentation aims to delineate the malignant entity involving multiple modalities. Although existing methods have shown remarkable performance in the task, the information exchange for cross-scale and high-level representations fusion in spatial and modality are limited in these methods. In this paper, we present a novel Modality Aware and Shift Mixer that integrates intra-modality and inter-modality dependencies of multi-modal images for effective and robust brain tumor segmentation. Specifically, we introduce a Modality-Aware module according to neuroimaging studies for modeling the specific modality pair relationships at low levels, and a Modality-Shift module with specific mosaic patterns is developed to explore the complex relationships across modalities at high levels via the self-attention. Experimentally, we outperform previous state-of-the-art approaches on the public Brain Tumor Segmentation (BraTS 2021 segmentation) dataset. Further qualitative experiments demonstrate the efficacy and robustness of MASM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_02074 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Modality-Aware and Shift Mixer for Multi-modal Brain Tumor Segmentation Huang, Zhongzhen Wei, Linda Zhang, Shaoting Zhang, Xiaofan Computer Vision and Pattern Recognition Artificial Intelligence Combining images from multi-modalities is beneficial to explore various information in computer vision, especially in the medical domain. As an essential part of clinical diagnosis, multi-modal brain tumor segmentation aims to delineate the malignant entity involving multiple modalities. Although existing methods have shown remarkable performance in the task, the information exchange for cross-scale and high-level representations fusion in spatial and modality are limited in these methods. In this paper, we present a novel Modality Aware and Shift Mixer that integrates intra-modality and inter-modality dependencies of multi-modal images for effective and robust brain tumor segmentation. Specifically, we introduce a Modality-Aware module according to neuroimaging studies for modeling the specific modality pair relationships at low levels, and a Modality-Shift module with specific mosaic patterns is developed to explore the complex relationships across modalities at high levels via the self-attention. Experimentally, we outperform previous state-of-the-art approaches on the public Brain Tumor Segmentation (BraTS 2021 segmentation) dataset. Further qualitative experiments demonstrate the efficacy and robustness of MASM. |
| title | Modality-Aware and Shift Mixer for Multi-modal Brain Tumor Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2403.02074 |