Multi-View Hypercomplex Learning for Breast Cancer Screening
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908559348858880 |
|---|---|
| author | Lopez, Eleonora Grassucci, Eleonora Comminiello, Danilo |
| author_facet | Lopez, Eleonora Grassucci, Eleonora Comminiello, Danilo |
| contents | Radiologists interpret mammography exams by jointly analyzing all four views, as correlations among them are crucial for accurate diagnosis. Recent methods employ dedicated fusion blocks to capture such dependencies, but these are often hindered by view dominance, training instability, and computational overhead. To address these challenges, we introduce multi-view hypercomplex learning, a novel learning paradigm for multi-view breast cancer classification based on parameterized hypercomplex neural networks (PHNNs). Thanks to hypercomplex algebra, our models intrinsically capture both intra- and inter-view relations. We propose PHResNets for two-view exams and two complementary four-view architectures: PHYBOnet, optimized for efficiency, and PHYSEnet, optimized for accuracy. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art multi-view models, while also generalizing across radiographic modalities and tasks such as disease classification from chest X-rays and multimodal brain tumor segmentation. Full code and pretrained models are available at https://github.com/ispamm/PHBreast. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2204_05798 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Multi-View Hypercomplex Learning for Breast Cancer Screening Lopez, Eleonora Grassucci, Eleonora Comminiello, Danilo Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Radiologists interpret mammography exams by jointly analyzing all four views, as correlations among them are crucial for accurate diagnosis. Recent methods employ dedicated fusion blocks to capture such dependencies, but these are often hindered by view dominance, training instability, and computational overhead. To address these challenges, we introduce multi-view hypercomplex learning, a novel learning paradigm for multi-view breast cancer classification based on parameterized hypercomplex neural networks (PHNNs). Thanks to hypercomplex algebra, our models intrinsically capture both intra- and inter-view relations. We propose PHResNets for two-view exams and two complementary four-view architectures: PHYBOnet, optimized for efficiency, and PHYSEnet, optimized for accuracy. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art multi-view models, while also generalizing across radiographic modalities and tasks such as disease classification from chest X-rays and multimodal brain tumor segmentation. Full code and pretrained models are available at https://github.com/ispamm/PHBreast. |
| title | Multi-View Hypercomplex Learning for Breast Cancer Screening |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2204.05798 |