Interpretable Vertebral Fracture Diagnosis
This work addresses the need for reliable and explainable AI-assisted diagnosis for radiologists, though it appears incremental in applying existing interpretability methods to a specific medical domain.
The paper tackled the problem of understanding whether black-box neural networks learn clinically relevant features for vertebral fracture diagnosis in CT images, by identifying concepts associated with neurons correlated with specific diagnoses and evaluating which concepts lead to correct or false diagnoses.
Do black-box neural network models learn clinically relevant features for fracture diagnosis? The answer not only establishes reliability quenches scientific curiosity but also leads to explainable and verbose findings that can assist the radiologists in the final and increase trust. This work identifies the concepts networks use for vertebral fracture diagnosis in CT images. This is achieved by associating concepts to neurons highly correlated with a specific diagnosis in the dataset. The concepts are either associated with neurons by radiologists pre-hoc or are visualized during a specific prediction and left for the user's interpretation. We evaluate which concepts lead to correct diagnosis and which concepts lead to false positives. The proposed frameworks and analysis pave the way for reliable and explainable vertebral fracture diagnosis.