Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.20833 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918367095422976 |
|---|---|
| author | Agrawal, Vidit Peters, John Thompson, Tyler N. Sanian, Mohammad Vali Pham, Chau Moshkov, Nikita Kazi, Arshad Pillai, Aditya Freeman, Jack Kang, Byunguk Farhi, Samouil L. Fraenkel, Ernest Stewart, Ron Paavolainen, Lassi Plummer, Bryan A. Caicedo, Juan C. |
| author_facet | Agrawal, Vidit Peters, John Thompson, Tyler N. Sanian, Mohammad Vali Pham, Chau Moshkov, Nikita Kazi, Arshad Pillai, Aditya Freeman, Jack Kang, Byunguk Farhi, Samouil L. Fraenkel, Ernest Stewart, Ron Paavolainen, Lassi Plummer, Bryan A. Caicedo, Juan C. |
| contents | Quantifying cell morphology using images and machine learning has proven to be a powerful tool to study the response of cells to treatments. However, models used to quantify cellular morphology are typically trained with a single microscopy imaging type. This results in specialized models that cannot be reused across biological studies because the technical specifications do not match (e.g., different number of channels). Here, we present CHAMMI-75, an open access dataset of heterogeneous, multi-channel microscopy images from 75 diverse biological studies. We curated this resource from publicly available sources to investigate cellular morphology models that are channel-adaptive and can process any microscopy image type. Our experiments show that training with CHAMMI-75 can improve performance in multi-channel bioimaging tasks primarily because of its high diversity in microscopy modalities. This work paves the way to create the next generation of cellular morphology models for biological studies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_20833 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CHAMMI-75: Pre-training multi-channel models with heterogeneous microscopy images Agrawal, Vidit Peters, John Thompson, Tyler N. Sanian, Mohammad Vali Pham, Chau Moshkov, Nikita Kazi, Arshad Pillai, Aditya Freeman, Jack Kang, Byunguk Farhi, Samouil L. Fraenkel, Ernest Stewart, Ron Paavolainen, Lassi Plummer, Bryan A. Caicedo, Juan C. Computer Vision and Pattern Recognition Machine Learning Quantifying cell morphology using images and machine learning has proven to be a powerful tool to study the response of cells to treatments. However, models used to quantify cellular morphology are typically trained with a single microscopy imaging type. This results in specialized models that cannot be reused across biological studies because the technical specifications do not match (e.g., different number of channels). Here, we present CHAMMI-75, an open access dataset of heterogeneous, multi-channel microscopy images from 75 diverse biological studies. We curated this resource from publicly available sources to investigate cellular morphology models that are channel-adaptive and can process any microscopy image type. Our experiments show that training with CHAMMI-75 can improve performance in multi-channel bioimaging tasks primarily because of its high diversity in microscopy modalities. This work paves the way to create the next generation of cellular morphology models for biological studies. |
| title | CHAMMI-75: Pre-training multi-channel models with heterogeneous microscopy images |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2512.20833 |