Validation of histopathology foundation models through whole slide image retrieval
Abstract We evaluated several foundation models in histopathology for image retrieval using a zero-shot approach. These models generated embeddings that were directly employed for retrieval without additional fine-tuning. Our experiments were conducted on diagnostic slides from The Cancer Genome Atl...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-88545-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571706113261568 |
|---|---|
| author | Saghir Alfasly Ghazal Alabtah Sobhan Hemati Krishna Rani Kalari Joaquin J. Garcia H. R. Tizhoosh |
| author_facet | Saghir Alfasly Ghazal Alabtah Sobhan Hemati Krishna Rani Kalari Joaquin J. Garcia H. R. Tizhoosh |
| author_sort | Saghir Alfasly |
| collection | DOAJ |
| description | Abstract We evaluated several foundation models in histopathology for image retrieval using a zero-shot approach. These models generated embeddings that were directly employed for retrieval without additional fine-tuning. Our experiments were conducted on diagnostic slides from The Cancer Genome Atlas (TCGA), which covers 23 organs and 117 cancer subtypes. We used Yottixel as the framework for whole-slide image (WSI) retrieval via patch-based embeddings. Retrieval performance was evaluated using macro-averaged F1 scores for top-1, top-3, and top-5 retrievals. The top-5 retrieval F1 scores indicated varying levels of performance: Yottixel-DenseNet (27% ± 13%), Yottixel-UNI (42% ± 14%), Yottixel-Virchow (40% ± 13%), Yottixel-GigaPath (41% ± 13%), and GigaPath WSI (40% ± 14%). These results demonstrate the potential and limitations of foundation models for histopathology image retrieval, underscoring the need for further advancements in embedding and retrieval techniques. |
| format | Article |
| id | doaj-art-1bf12a7cbf8c417e87d1dbfd2d27b5d9 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-1bf12a7cbf8c417e87d1dbfd2d27b5d92025-02-02T12:20:55ZengNature PortfolioScientific Reports2045-23222025-02-011511810.1038/s41598-025-88545-9Validation of histopathology foundation models through whole slide image retrievalSaghir Alfasly0Ghazal Alabtah1Sobhan Hemati2Krishna Rani Kalari3Joaquin J. Garcia4H. R. Tizhoosh5KIMIA Lab, Department of Artificial Intelligence & Informatics, Mayo ClinicKIMIA Lab, Department of Artificial Intelligence & Informatics, Mayo ClinicKIMIA Lab, Department of Artificial Intelligence & Informatics, Mayo ClinicDivision of Computational Biology, Department of Quantitative Health Sciences, Mayo ClinicDepartment of Laboratory Medicine and Pathology, Mayo ClinicKIMIA Lab, Department of Artificial Intelligence & Informatics, Mayo ClinicAbstract We evaluated several foundation models in histopathology for image retrieval using a zero-shot approach. These models generated embeddings that were directly employed for retrieval without additional fine-tuning. Our experiments were conducted on diagnostic slides from The Cancer Genome Atlas (TCGA), which covers 23 organs and 117 cancer subtypes. We used Yottixel as the framework for whole-slide image (WSI) retrieval via patch-based embeddings. Retrieval performance was evaluated using macro-averaged F1 scores for top-1, top-3, and top-5 retrievals. The top-5 retrieval F1 scores indicated varying levels of performance: Yottixel-DenseNet (27% ± 13%), Yottixel-UNI (42% ± 14%), Yottixel-Virchow (40% ± 13%), Yottixel-GigaPath (41% ± 13%), and GigaPath WSI (40% ± 14%). These results demonstrate the potential and limitations of foundation models for histopathology image retrieval, underscoring the need for further advancements in embedding and retrieval techniques.https://doi.org/10.1038/s41598-025-88545-9 |
| spellingShingle | Saghir Alfasly Ghazal Alabtah Sobhan Hemati Krishna Rani Kalari Joaquin J. Garcia H. R. Tizhoosh Validation of histopathology foundation models through whole slide image retrieval Scientific Reports |
| title | Validation of histopathology foundation models through whole slide image retrieval |
| title_full | Validation of histopathology foundation models through whole slide image retrieval |
| title_fullStr | Validation of histopathology foundation models through whole slide image retrieval |
| title_full_unstemmed | Validation of histopathology foundation models through whole slide image retrieval |
| title_short | Validation of histopathology foundation models through whole slide image retrieval |
| title_sort | validation of histopathology foundation models through whole slide image retrieval |
| url | https://doi.org/10.1038/s41598-025-88545-9 |
| work_keys_str_mv | AT saghiralfasly validationofhistopathologyfoundationmodelsthroughwholeslideimageretrieval AT ghazalalabtah validationofhistopathologyfoundationmodelsthroughwholeslideimageretrieval AT sobhanhemati validationofhistopathologyfoundationmodelsthroughwholeslideimageretrieval AT krishnaranikalari validationofhistopathologyfoundationmodelsthroughwholeslideimageretrieval AT joaquinjgarcia validationofhistopathologyfoundationmodelsthroughwholeslideimageretrieval AT hrtizhoosh validationofhistopathologyfoundationmodelsthroughwholeslideimageretrieval |