Explainable artificial intelligence for breast cancer: A visual case-based reasoning approach

Early XAI studies often had implicit limitations where evaluations prioritized technical feasibility or proof-of-concept over robust behavioral assessment.

“This critique builds on limitations that were often implicit in early XAI studies [38,45,46,66,68], where evaluations prioritized technical feasibility or proof-of-concept over robust behavioral assessment.”

Most studies used visualization as a key aspect to enhance explainability, either with SHAP plots, regional abnormality maps, rainbow boxes, or the attention mechanism that highlighted important words leading to a prediction.

“Most studies used visualization as a key aspect to enhance explainability, either with SHAP plots [118,120], regional abnormality maps [119], rainbow boxes [123,126], or the attention mechanism that highlighted the important words that lead to a prediction [122].”

Lamy et al. presented their interface to 11 medical experts for usability and acceptability validation, demonstrating that XAI could provide the user with a good indication of the confidence level of their choice.

“They presented their interface to 11 medical experts for usability and acceptability validation, demonstrating that XAI could provide the user with a good indication of the confidence level of their choice [126].”

Case-Based Reasoning is an intrinsically explainable method that was used by Lamy et al. for their CDSS for breast cancer, supported by visual explanations in the form of rainbow boxes and a polar multidimensional scaling scatter plot.

“Case-Based Reasoning is an intrinsically explainable method that was used by Lamy et al. [126] for their CDSS for breast cancer, which was also supported by visual explanations in the form of rainbow boxes and a polar multidimensional scaling scatter plot.”

Lamy et al. raised the need to confirm their results on a larger user study, in addition to the lack of user studies for some XAI-based approaches.

“As to testing the systems, Lamy et al. [126] raised the need to confirm their results on a larger user study, in addition to the lack of user studies for some XAI-based approaches as discussed in Section 4.3 (RQ3).”

Most reviewed studies implemented a model-specific ante-hoc technique that provided local explanations.

“Most studies implemented a model-specific ante-hoc technique that provided local explanations [122,124-126,128].”

Lamy et al. [126] used a visual case-based reasoning approach (using rainbow-boxes and a polar multidimensional scaling scatter plot); the method was specific, ante-hoc, and local.

“Lamy et al. [126] Visual (using rainbow-boxes [131] and a polar multidimensional scaling scatter plot) case-based reasoning approach specific ante-hoc local”