ContriMix: Scalable stain color augmentation for domain generalization without domain labels in digital pathology
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911791175434240 |
|---|---|
| author | Nguyen, Tan H. Juyal, Dinkar Li, Jin Prakash, Aaditya Nofallah, Shima Shah, Chintan Gullapally, Sai Chowdary Yu, Limin Griffin, Michael Sampat, Anand Abel, John Lee, Justin Taylor-Weiner, Amaro |
| author_facet | Nguyen, Tan H. Juyal, Dinkar Li, Jin Prakash, Aaditya Nofallah, Shima Shah, Chintan Gullapally, Sai Chowdary Yu, Limin Griffin, Michael Sampat, Anand Abel, John Lee, Justin Taylor-Weiner, Amaro |
| contents | Differences in staining and imaging procedures can cause significant color variations in histopathology images, leading to poor generalization when deploying deep-learning models trained from a different data source. Various color augmentation methods have been proposed to generate synthetic images during training to make models more robust, eliminating the need for stain normalization during test time. Many color augmentation methods leverage domain labels to generate synthetic images. This approach causes three significant challenges to scaling such a model. Firstly, incorporating data from a new domain into deep-learning models trained on existing domain labels is not straightforward. Secondly, dependency on domain labels prevents the use of pathology images without domain labels to improve model performance. Finally, implementation of these methods becomes complicated when multiple domain labels (e.g., patient identification, medical center, etc) are associated with a single image. We introduce ContriMix, a novel domain label free stain color augmentation method based on DRIT++, a style-transfer method. Contrimix leverages sample stain color variation within a training minibatch and random mixing to extract content and attribute information from pathology images. This information can be used by a trained ContriMix model to create synthetic images to improve the performance of existing classifiers. ContriMix outperforms competing methods on the Camelyon17-WILDS dataset. Its performance is consistent across different slides in the test set while being robust to the color variation from rare substances in pathology images. We make our code and trained ContriMix models available for research use. The code for ContriMix can be found at https://gitlab.com/huutan86/contrimix |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_04527 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | ContriMix: Scalable stain color augmentation for domain generalization without domain labels in digital pathology Nguyen, Tan H. Juyal, Dinkar Li, Jin Prakash, Aaditya Nofallah, Shima Shah, Chintan Gullapally, Sai Chowdary Yu, Limin Griffin, Michael Sampat, Anand Abel, John Lee, Justin Taylor-Weiner, Amaro Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Differences in staining and imaging procedures can cause significant color variations in histopathology images, leading to poor generalization when deploying deep-learning models trained from a different data source. Various color augmentation methods have been proposed to generate synthetic images during training to make models more robust, eliminating the need for stain normalization during test time. Many color augmentation methods leverage domain labels to generate synthetic images. This approach causes three significant challenges to scaling such a model. Firstly, incorporating data from a new domain into deep-learning models trained on existing domain labels is not straightforward. Secondly, dependency on domain labels prevents the use of pathology images without domain labels to improve model performance. Finally, implementation of these methods becomes complicated when multiple domain labels (e.g., patient identification, medical center, etc) are associated with a single image. We introduce ContriMix, a novel domain label free stain color augmentation method based on DRIT++, a style-transfer method. Contrimix leverages sample stain color variation within a training minibatch and random mixing to extract content and attribute information from pathology images. This information can be used by a trained ContriMix model to create synthetic images to improve the performance of existing classifiers. ContriMix outperforms competing methods on the Camelyon17-WILDS dataset. Its performance is consistent across different slides in the test set while being robust to the color variation from rare substances in pathology images. We make our code and trained ContriMix models available for research use. The code for ContriMix can be found at https://gitlab.com/huutan86/contrimix |
| title | ContriMix: Scalable stain color augmentation for domain generalization without domain labels in digital pathology |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2306.04527 |