Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2506.10006 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916872010596352 |
|---|---|
| author | Qin, Jie Yang, Wei Su, Yan Zhu, Yiran Li, Weizhen Pan, Yunyue Pan, Chengchang Qi, Honggang |
| author_facet | Qin, Jie Yang, Wei Su, Yan Zhu, Yiran Li, Weizhen Pan, Yunyue Pan, Chengchang Qi, Honggang |
| contents | In breast cancer HER2 assessment, clinical evaluation relies on combined H&E and IHC images, yet acquiring both modalities is often hindered by clinical constraints and cost. We propose an adaptive bimodal prediction framework that flexibly supports single- or dual-modality inputs through two core innovations: a dynamic branch selector activating modality completion or joint inference based on input availability, and a cross-modal GAN (CM-GAN) enabling feature-space reconstruction of missing modalities. This design dramatically improves H&E-only accuracy from 71.44% to 94.25%, achieves 95.09% with full dual-modality inputs, and maintains 90.28% reliability under single-modality conditions. The "dual-modality preferred, single-modality compatible" architecture delivers near-dual-modality accuracy without mandatory synchronized acquisition, offering a cost-effective solution for resource-limited regions and significantly improving HER2 assessment accessibility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_10006 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HER2 Expression Prediction with Flexible Multi-Modal Inputs via Dynamic Bidirectional Reconstruction Qin, Jie Yang, Wei Su, Yan Zhu, Yiran Li, Weizhen Pan, Yunyue Pan, Chengchang Qi, Honggang Multimedia Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning In breast cancer HER2 assessment, clinical evaluation relies on combined H&E and IHC images, yet acquiring both modalities is often hindered by clinical constraints and cost. We propose an adaptive bimodal prediction framework that flexibly supports single- or dual-modality inputs through two core innovations: a dynamic branch selector activating modality completion or joint inference based on input availability, and a cross-modal GAN (CM-GAN) enabling feature-space reconstruction of missing modalities. This design dramatically improves H&E-only accuracy from 71.44% to 94.25%, achieves 95.09% with full dual-modality inputs, and maintains 90.28% reliability under single-modality conditions. The "dual-modality preferred, single-modality compatible" architecture delivers near-dual-modality accuracy without mandatory synchronized acquisition, offering a cost-effective solution for resource-limited regions and significantly improving HER2 assessment accessibility. |
| title | HER2 Expression Prediction with Flexible Multi-Modal Inputs via Dynamic Bidirectional Reconstruction |
| topic | Multimedia Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2506.10006 |