Diabetic Foot Ulcer Ischemia and Infection Classification Using EfficientNet Deep Learning Models
Ziyang Liu, Josvin John, Emmanuel Agu
Abstract
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Motivation:</i> Infection (bacteria in the wound) and ischemia (insufficient blood supply) in Diabetic Foot Ulcers (DFUs) increase the risk of limb amputation. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Goal:</i> To develop an image-based DFU infection and ischemia detection system that uses deep learning. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Methods:</i> The DFU dataset was augmented using geometric and color image operations, after which binary infection and ischemia classification was done using the EfficientNet deep learning model and a comprehensive set of baselines. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Results:</i> The EfficientNets model achieved 99% accuracy in ischemia classification and 98% in infection classification, outperforming ResNet and Inception (87% accuracy) and Ensemble CNN, the prior state of the art (Classification accuracy of 90% for ischemia 73% for infection). EfficientNets also classified test images in a fraction (10% to 50%) of the time taken by baseline models. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Conclusions</i> : This work demonstrates that EfficientNets is a viable deep learning model for infection and ischemia classification.