MuCoSA: Multi-contextual similarity assessment for histopathology image search
Year: 2025
Type: article
Abstract: < 0.0001). Furthermore, confusion matrices and visual inspection confirmed that search results were closely aligned with the morphological perceptions of pathologists. In conclusion, our study demonstrates that using a simple and efficient framework like MuCoSA with multi-magnification PRISM without fine-tuning can significantly improve image search in histopathology. We anticipate that MuCoSA can assist pathologists in making more accurate and consistent diagnoses, thereby reducing observer variability in histopathological interpretation.
Source: Journal of Pathology Informatics
Authors: Gyu Yeong Kim, Yongjun Jeon, Hoyeon Jeong, Seungkyun Lee, Hyungbin Kim, Boram Lee, Kyu-Hwan Jung, David Joon Ho, Yoon-La Choi
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,070
Awards: G6799406404, G8460786046
OpenAlex ID: W4416998658