%Aigaion2 BibTeX export from HES SO Valais Publications
%Saturday 02 May 2026 11:52:06 AM

@INPROCEEDINGS{,
     author = {Graziani, Mara and Palatnik de Sousa, Iam and Vellasco BR, Marley M and Costa da Silva, Eduardo and M{\"{u}}ller, Henning and Andrearczyk, Vincent},
   keywords = {Deep Learning, explainable AI (XAI), interpretability, machine learning},
      month = oct,
      title = {Sharpening Local Interpretable Model-agnostic Explanations for Histopathology: Improved Understandability and Reliability},
  booktitle = {MICCAI 2021},
     series = {LNCS},
       year = {2021},
  publisher = {Springer},
   abstract = {Being accountable for the signed reports, pathologists may be wary of high-quality deep learning outcomes if the decision-making is not understandable. Applying off-the-shelf methods with default configurations such as Local Interpretable Model-Agnostic Explanations (LIME) is not sufficient to generate stable and understandable explanations. This work improves the application of LIME to histopathology images by leveraging nuclei annotations, creating a reliable way for pathologists to audit black-box tumor classifiers. The obtained visualizations reveal the sharp, neat and high attention of the deep classifier to the neoplas-tic nuclei in the dataset, an observation in line with clinical decision making. Compared to standard LIME, our explanations show improved understandability for domain-experts, report higher stability and pass the sanity checks of consistency to data or initialization changes and sensitivity to network parameters. This represents a promising step in giving pathologists tools to obtain additional information on image classification models. The code and trained models are available on GitHub.}
}