Few-shot learning and explainable AI for colon cancer histopathology: A prototypical network with multi-technique interpretability.
[BACKGROUND] Colon cancer diagnosis from histopathology is challenging due to limited annotated data and the lack of interpretability in deep models.
APA
Merabet A, Saighi A, et al. (2026). Few-shot learning and explainable AI for colon cancer histopathology: A prototypical network with multi-technique interpretability.. International journal of medical informatics, 206, 106167. https://doi.org/10.1016/j.ijmedinf.2025.106167
MLA
Merabet A, et al.. "Few-shot learning and explainable AI for colon cancer histopathology: A prototypical network with multi-technique interpretability.." International journal of medical informatics, vol. 206, 2026, pp. 106167.
PMID
41232395
Abstract
[BACKGROUND] Colon cancer diagnosis from histopathology is challenging due to limited annotated data and the lack of interpretability in deep models.
[OBJECTIVE] We present a data-efficient framework combining few-shot learning and explainable AI for accurate and transparent diagnosis.
[METHODS] A Prototypical Network with a ConvNeXt-Tiny backbone was trained on small colon-tissue image sets. Explanations from Grad-CAM and LIME were validated by a pathologist, and generalization was tested on an external dataset.
[RESULTS] The model achieved 98.5 % accuracy in-domain and 90 % on the EBHI dataset, showing strong generalization.
[CONCLUSIONS] This few-shot and explainable model performs well with minimal data and generates clinically interpretable visual outputs, supporting its potential for reliable colon cancer diagnosis.
[OBJECTIVE] We present a data-efficient framework combining few-shot learning and explainable AI for accurate and transparent diagnosis.
[METHODS] A Prototypical Network with a ConvNeXt-Tiny backbone was trained on small colon-tissue image sets. Explanations from Grad-CAM and LIME were validated by a pathologist, and generalization was tested on an external dataset.
[RESULTS] The model achieved 98.5 % accuracy in-domain and 90 % on the EBHI dataset, showing strong generalization.
[CONCLUSIONS] This few-shot and explainable model performs well with minimal data and generates clinically interpretable visual outputs, supporting its potential for reliable colon cancer diagnosis.
MeSH Terms
Colonic Neoplasms; Humans; Artificial Intelligence; Computer Simulation; Image Interpretation, Computer-Assisted; Deep Learning