Human-centered XAI for Burn Depth Characterization
This work addresses burn injury treatment for patients by enhancing ultrasound classification models, but it is incremental as it builds on existing methods like LIME and GLCM features.
The paper tackled the problem of improving burn depth classification in medical AI by proposing a human-in-the-loop explainable framework, resulting in an accuracy increase from ~88% to ~94% on real porcine data.
Approximately 1.25 million people in the United States are treated each year for burn injuries. Precise burn injury classification is an important aspect of the medical AI field. In this work, we propose an explainable human-in-the-loop framework for improving burn ultrasound classification models. Our framework leverages an explanation system based on the LIME classification explainer to corroborate and integrate a burn expert's knowledge -- suggesting new features and ensuring the validity of the model. Using this framework, we discover that B-mode ultrasound classifiers can be enhanced by supplying textural features. More specifically, we confirm that texture features based on the Gray Level Co-occurance Matrix (GLCM) of ultrasound frames can increase the accuracy of transfer learned burn depth classifiers. We test our hypothesis on real data from porcine subjects. We show improvements in the accuracy of burn depth classification -- from ~88% to ~94% -- once modified according to our framework.