Towards explainable classifiers using the counterfactual approach -- global explanations for discovering bias in data
This work addresses bias detection in medical imaging for improved classifier reliability, though it is incremental as it builds on existing counterfactual methods.
The paper tackled the problem of detecting bias in data by proposing a global explanation method using counterfactual approaches, and it successfully identified artifacts like black frames in skin lesion images, with 22% of these frames changing predictions from benign to malignant.
The paper proposes summarized attribution-based post-hoc explanations for the detection and identification of bias in data. A global explanation is proposed, and a step-by-step framework on how to detect and test bias is introduced. Since removing unwanted bias is often a complicated and tremendous task, it is automatically inserted, instead. Then, the bias is evaluated with the proposed counterfactual approach. The obtained results are validated on a sample skin lesion dataset. Using the proposed method, a number of possible bias causing artifacts are successfully identified and confirmed in dermoscopy images. In particular, it is confirmed that black frames have a strong influence on Convolutional Neural Network's prediction: 22% of them changed the prediction from benign to malignant.