Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.11458 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916491768627200 |
|---|---|
| author | Pohjonen, Joona Batouche, Abderrahim-Oussama Rannikko, Antti Sandeman, Kevin Erickson, Andrew Pitkanen, Esa Mirtti, Tuomas |
| author_facet | Pohjonen, Joona Batouche, Abderrahim-Oussama Rannikko, Antti Sandeman, Kevin Erickson, Andrew Pitkanen, Esa Mirtti, Tuomas |
| contents | Foundation models are trained on massive amounts of data to distinguish complex patterns and can be adapted to a wide range of downstream tasks with minimal computational resources. Here, we develop a foundation model for prostate cancer digital pathology called HistoEncoder by pre-training on 48 million prostate tissue tile images. We demonstrate that HistoEncoder features extracted from tile images with similar histological patterns map closely together in the feature space. HistoEncoder outperforms models pre-trained with natural images, even without fine-tuning or with 1000 times less training data. We describe two use cases that leverage the capabilities of HistoEncoder by fine-tuning the model with a limited amount of data and computational resources. First, we show how HistoEncoder can be used to automatically annotate large-scale datasets with high accuracy. Second, we combine histomics with commonly used clinical nomograms, significantly improving prostate cancer-specific death survival models. Foundation models such as HistoEncoder can allow organizations with limited resources to build effective clinical software tools without needing extensive datasets or significant amounts of computing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_11458 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HistoEncoder: a digital pathology foundation model for prostate cancer Pohjonen, Joona Batouche, Abderrahim-Oussama Rannikko, Antti Sandeman, Kevin Erickson, Andrew Pitkanen, Esa Mirtti, Tuomas Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Foundation models are trained on massive amounts of data to distinguish complex patterns and can be adapted to a wide range of downstream tasks with minimal computational resources. Here, we develop a foundation model for prostate cancer digital pathology called HistoEncoder by pre-training on 48 million prostate tissue tile images. We demonstrate that HistoEncoder features extracted from tile images with similar histological patterns map closely together in the feature space. HistoEncoder outperforms models pre-trained with natural images, even without fine-tuning or with 1000 times less training data. We describe two use cases that leverage the capabilities of HistoEncoder by fine-tuning the model with a limited amount of data and computational resources. First, we show how HistoEncoder can be used to automatically annotate large-scale datasets with high accuracy. Second, we combine histomics with commonly used clinical nomograms, significantly improving prostate cancer-specific death survival models. Foundation models such as HistoEncoder can allow organizations with limited resources to build effective clinical software tools without needing extensive datasets or significant amounts of computing. |
| title | HistoEncoder: a digital pathology foundation model for prostate cancer |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.11458 |