E-DFu-Net: An efficient deep convolutional neural network models for Diabetic Foot Ulcer classification

Nouf  F. Almufadi; Haifa F. Alhasson; Shuaa S. Alharbi

doi:10.17305/bb.2024.11117

Authors

Nouf F. Almufadi Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi Arabia https://orcid.org/0000-0001-9070-6063
Haifa F. Alhasson Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi Arabia
Shuaa S. Alharbi Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi Arabia https://orcid.org/0000-0003-2121-0296

DOI:

https://doi.org/10.17305/bb.2024.11117

Keywords:

Diabetic foot ulcers, deep learning, image classification, ischemia classification, infection classification, medical imaging processing, medical image, transfer learning

Abstract

The Diabetic Foot Ulcer (DFU) is a severe complication that affects approximately 33% of diabetes patients globally, often leading to limb amputation if not detected early. This study introduces an automated approach for identifying and classifying DFU using transfer learning. DFU is typically categorized into ischemic and infection states, which are challenging to distinguish visually. We evaluate the effectiveness of pre-trained Deep Convolutional Neural Network (DCNN) models for autonomous DFU detection. Seven models are compared: EfficientNetB0, DenseNet121, ResNet101, VGG16, MobileNetV2, InceptionV3, and InceptionResNetV2. Additionally, we propose E-DFu-Net, a novel model derived from existing architectures, designed to mitigate overfitting. Experimental results demonstrate that E-DFu-Net achieves remarkable performance, with 97% accuracy in ischemia classification and 92% in infection classification. This advancement enhances current methodologies and aids practitioners in effectively detecting DFU cases.