Case Study: Explaining Diabetic Retinopathy Detection Deep CNNs via Integrated Gradients
This work addresses interpretability for medical AI in diabetic retinopathy detection, but it is incremental as it applies an existing method to a specific domain.
The study applied integrated gradients to explain a diabetic retinopathy detection deep CNN, exploring techniques like explaining intermediate layers and generating contrary samples, with visualization results extending the model's use from prediction to assisting in lesion identification.
In this report, we applied integrated gradients to explaining a neural network for diabetic retinopathy detection. The integrated gradient is an attribution method which measures the contributions of input to the quantity of interest. We explored some new ways for applying this method such as explaining intermediate layers, filtering out unimportant units by their attribution value and generating contrary samples. Moreover, the visualization results extend the use of diabetic retinopathy detection model from merely predicting to assisting finding potential lesions.