Semi-Supervised Contrastive VAE for Disentanglement of Digital Pathology Images
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913528853561344 |
|---|---|
| author | Hasan, Mahmudul Hu, Xiaoling Abousamra, Shahira Prasanna, Prateek Saltz, Joel Chen, Chao |
| author_facet | Hasan, Mahmudul Hu, Xiaoling Abousamra, Shahira Prasanna, Prateek Saltz, Joel Chen, Chao |
| contents | Despite the strong prediction power of deep learning models, their interpretability remains an important concern. Disentanglement models increase interpretability by decomposing the latent space into interpretable subspaces. In this paper, we propose the first disentanglement method for pathology images. We focus on the task of detecting tumor-infiltrating lymphocytes (TIL). We propose different ideas including cascading disentanglement, novel architecture, and reconstruction branches. We achieve superior performance on complex pathology images, thus improving the interpretability and even generalization power of TIL detection deep learning models. Our codes are available at https://github.com/Shauqi/SS-cVAE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02012 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Semi-Supervised Contrastive VAE for Disentanglement of Digital Pathology Images Hasan, Mahmudul Hu, Xiaoling Abousamra, Shahira Prasanna, Prateek Saltz, Joel Chen, Chao Image and Video Processing Computer Vision and Pattern Recognition Despite the strong prediction power of deep learning models, their interpretability remains an important concern. Disentanglement models increase interpretability by decomposing the latent space into interpretable subspaces. In this paper, we propose the first disentanglement method for pathology images. We focus on the task of detecting tumor-infiltrating lymphocytes (TIL). We propose different ideas including cascading disentanglement, novel architecture, and reconstruction branches. We achieve superior performance on complex pathology images, thus improving the interpretability and even generalization power of TIL detection deep learning models. Our codes are available at https://github.com/Shauqi/SS-cVAE. |
| title | Semi-Supervised Contrastive VAE for Disentanglement of Digital Pathology Images |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.02012 |