MM-SurvNet: Deep Learning-Based Survival Risk Stratification in Breast Cancer Through Multimodal Data Fusion
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_ | 1866911779402022912 |
|---|---|
| author | Mondol, Raktim Kumar Millar, Ewan K. A. Sowmya, Arcot Meijering, Erik |
| author_facet | Mondol, Raktim Kumar Millar, Ewan K. A. Sowmya, Arcot Meijering, Erik |
| contents | Survival risk stratification is an important step in clinical decision making for breast cancer management. We propose a novel deep learning approach for this purpose by integrating histopathological imaging, genetic and clinical data. It employs vision transformers, specifically the MaxViT model, for image feature extraction, and self-attention to capture intricate image relationships at the patient level. A dual cross-attention mechanism fuses these features with genetic data, while clinical data is incorporated at the final layer to enhance predictive accuracy. Experiments on the public TCGA-BRCA dataset show that our model, trained using the negative log likelihood loss function, can achieve superior performance with a mean C-index of 0.64, surpassing existing methods. This advancement facilitates tailored treatment strategies, potentially leading to improved patient outcomes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_11788 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MM-SurvNet: Deep Learning-Based Survival Risk Stratification in Breast Cancer Through Multimodal Data Fusion Mondol, Raktim Kumar Millar, Ewan K. A. Sowmya, Arcot Meijering, Erik Computer Vision and Pattern Recognition Artificial Intelligence Survival risk stratification is an important step in clinical decision making for breast cancer management. We propose a novel deep learning approach for this purpose by integrating histopathological imaging, genetic and clinical data. It employs vision transformers, specifically the MaxViT model, for image feature extraction, and self-attention to capture intricate image relationships at the patient level. A dual cross-attention mechanism fuses these features with genetic data, while clinical data is incorporated at the final layer to enhance predictive accuracy. Experiments on the public TCGA-BRCA dataset show that our model, trained using the negative log likelihood loss function, can achieve superior performance with a mean C-index of 0.64, surpassing existing methods. This advancement facilitates tailored treatment strategies, potentially leading to improved patient outcomes. |
| title | MM-SurvNet: Deep Learning-Based Survival Risk Stratification in Breast Cancer Through Multimodal Data Fusion |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2402.11788 |