Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.03277 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908479241846784 |
|---|---|
| author | Guo, Hang Zhang, Qing Gao, Zixuan Yang, Siyuan Peng, Shulin Tao, Xiang Yu, Ting Wang, Yan Li, Qingli |
| author_facet | Guo, Hang Zhang, Qing Gao, Zixuan Yang, Siyuan Peng, Shulin Tao, Xiang Yu, Ting Wang, Yan Li, Qingli |
| contents | Accurate prediction of placental diseases via whole slide images (WSIs) is critical for preventing severe maternal and fetal complications. However, WSI analysis presents significant computational challenges due to the massive data volume. Existing WSI classification methods encounter critical limitations: (1) inadequate patch selection strategies that either compromise performance or fail to sufficiently reduce computational demands, and (2) the loss of global histological context resulting from patch-level processing approaches. To address these challenges, we propose an Efficient multimodal framework for Patient-level placental disease Diagnosis, named EmmPD. Our approach introduces a two-stage patch selection module that combines parameter-free and learnable compression strategies, optimally balancing computational efficiency with critical feature preservation. Additionally, we develop a hybrid multimodal fusion module that leverages adaptive graph learning to enhance pathological feature representation and incorporates textual medical reports to enrich global contextual understanding. Extensive experiments conducted on both a self-constructed patient-level Placental dataset and two public datasets demonstrating that our method achieves state-of-the-art diagnostic performance. The code is available at https://github.com/ECNU-MultiDimLab/EmmPD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_03277 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Multi-Slide Visual-Language Feature Fusion for Placental Disease Classification Guo, Hang Zhang, Qing Gao, Zixuan Yang, Siyuan Peng, Shulin Tao, Xiang Yu, Ting Wang, Yan Li, Qingli Computer Vision and Pattern Recognition Accurate prediction of placental diseases via whole slide images (WSIs) is critical for preventing severe maternal and fetal complications. However, WSI analysis presents significant computational challenges due to the massive data volume. Existing WSI classification methods encounter critical limitations: (1) inadequate patch selection strategies that either compromise performance or fail to sufficiently reduce computational demands, and (2) the loss of global histological context resulting from patch-level processing approaches. To address these challenges, we propose an Efficient multimodal framework for Patient-level placental disease Diagnosis, named EmmPD. Our approach introduces a two-stage patch selection module that combines parameter-free and learnable compression strategies, optimally balancing computational efficiency with critical feature preservation. Additionally, we develop a hybrid multimodal fusion module that leverages adaptive graph learning to enhance pathological feature representation and incorporates textual medical reports to enrich global contextual understanding. Extensive experiments conducted on both a self-constructed patient-level Placental dataset and two public datasets demonstrating that our method achieves state-of-the-art diagnostic performance. The code is available at https://github.com/ECNU-MultiDimLab/EmmPD. |
| title | Efficient Multi-Slide Visual-Language Feature Fusion for Placental Disease Classification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.03277 |