A Deep Learning Approach for Diabetic Foot Ulcer Classification and Recognition

Diabetic foot ulcer (DFU) is one of the major complications diabetes and results in amputation lower limb if not treated timely properly. Despite traditional clinical approaches used DFU classification, automatic methods based on a deep learning framework show promising results. In this paper, we present several end-to-end CNN-based architectures, i.e., AlexNet, VGG16/19, GoogLeNet, ResNet50.101, MobileNet, SqueezeNet, DenseNet, for infection ischemia categorization using benchmark dataset DFU2020. We fine-tune weight to overcome lack data reduce computational cost. Affine transform techniques are augmentation input data. The indicate that ResNet50 achieves highest accuracy 99.49% 84.76% Ischaemia infection, respectively.