MindfulLIME: a stable solution for explanations of machine learning models with enhanced localization precision—a medical image case study

Date

2025-01-01

Author

Rahimiaghdam, Shakiba
Alemdar, Hande

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

229
views

0
downloads

Cite This

Ensuring transparency in machine learning decisions is critically important, especially in sensitive sectors such as healthcare, finance, and justice. Despite this, some popular explainable algorithms, such as Local Interpretable Model-agnostic Explanations (LIME), often produce unstable explanations due to the random generation of perturbed samples. Random perturbation introduces small changes or noise to modified instances of the original data, leading to inconsistent explanations. Even slight variations in the generated samples significantly affect the explanations provided by such models, undermining trust and hindering the adoption of interpretable models. To address this challenge, we propose MindfulLIME, a novel algorithm that intelligently generates purposive samples using a graph-based pruning algorithm and uncertainty sampling. MindfulLIME substantially improves the consistency of visual explanations compared to random sampling approaches. Our experimental evaluation, conducted on a widely recognized chest X-ray dataset, confirms MindfulLIME’s stability with a 100% success rate in delivering reliable explanations under identical conditions. Additionally, MindfulLIME improves the localization precision of visual explanations by reducing the distance between the generated explanations and the actual local annotations compared to LIME. We also performed comprehensive experiments considering various segmentation algorithms and sample numbers, focusing on stability, quality, and efficiency. The results demonstrate the outstanding performance of MindfulLIME across different segmentation settings, generating fewer high-quality samples within a reasonable processing time. By addressing the stability limitations of LIME in the context of image data, MindfulLIME notably contributes to enhancing the trustworthiness and interpretability of machine learning models applied to specific medical images, which is a critical application.

Subject Keywords

Classification, Deep learning, Explainable Artificial Intelligence (XAI), Neural networks

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=105015372253&origin=inward
https://hdl.handle.net/11511/115709

Collections

Department of Computer Engineering, Article