Going Beyond H&E and Oncology: How Do Histopathology Foundation Models Perform for Multi-stain IHC and Immunology?
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_ | 1866909369048760320 |
|---|---|
| author | Gallagher-Syed, Amaya Pontarini, Elena Lewis, Myles J. Barnes, Michael R. Slabaugh, Gregory |
| author_facet | Gallagher-Syed, Amaya Pontarini, Elena Lewis, Myles J. Barnes, Michael R. Slabaugh, Gregory |
| contents | This study evaluates the generalisation capabilities of state-of-the-art histopathology foundation models on out-of-distribution multi-stain autoimmune Immunohistochemistry datasets. We compare 13 feature extractor models, including ImageNet-pretrained networks, and histopathology foundation models trained on both public and proprietary data, on Rheumatoid Arthritis subtyping and Sjogren's Disease detection tasks. Using a simple Attention-Based Multiple Instance Learning classifier, we assess the transferability of learned representations from cancer H&E images to autoimmune IHC images. Contrary to expectations, histopathology-pretrained models did not significantly outperform ImageNet-pretrained models. Furthermore, there was evidence of both autoimmune feature misinterpretation and biased feature importance. Our findings highlight the challenges in transferring knowledge from cancer to autoimmune histopathology and emphasise the need for careful evaluation of AI models across diverse histopathological tasks. The code to run this benchmark is available at https://github.com/AmayaGS/ImmunoHistoBench. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_21560 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Going Beyond H&E and Oncology: How Do Histopathology Foundation Models Perform for Multi-stain IHC and Immunology? Gallagher-Syed, Amaya Pontarini, Elena Lewis, Myles J. Barnes, Michael R. Slabaugh, Gregory Computer Vision and Pattern Recognition Artificial Intelligence Quantitative Methods Tissues and Organs This study evaluates the generalisation capabilities of state-of-the-art histopathology foundation models on out-of-distribution multi-stain autoimmune Immunohistochemistry datasets. We compare 13 feature extractor models, including ImageNet-pretrained networks, and histopathology foundation models trained on both public and proprietary data, on Rheumatoid Arthritis subtyping and Sjogren's Disease detection tasks. Using a simple Attention-Based Multiple Instance Learning classifier, we assess the transferability of learned representations from cancer H&E images to autoimmune IHC images. Contrary to expectations, histopathology-pretrained models did not significantly outperform ImageNet-pretrained models. Furthermore, there was evidence of both autoimmune feature misinterpretation and biased feature importance. Our findings highlight the challenges in transferring knowledge from cancer to autoimmune histopathology and emphasise the need for careful evaluation of AI models across diverse histopathological tasks. The code to run this benchmark is available at https://github.com/AmayaGS/ImmunoHistoBench. |
| title | Going Beyond H&E and Oncology: How Do Histopathology Foundation Models Perform for Multi-stain IHC and Immunology? |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Quantitative Methods Tissues and Organs |
| url | https://arxiv.org/abs/2410.21560 |