Diabetic Foot Ulcer Identification: A Review.

Area of Science:

• Medical Informatics
• Artificial Intelligence
• Computer Vision

Background:

• Diabetes mellitus is a chronic condition characterized by uncontrolled blood sugar levels.
• Diabetic foot ulcers (DFUs) are severe complications that can lead to limb amputation.
• Current DFU diagnosis involves complex, time-consuming, and costly clinical procedures.

Purpose of the Study:

• To review the current status of automatic Diabetic Foot Ulcer identification techniques.
• To provide researchers with an overview of machine learning and deep learning applications in DFU diagnosis.
• To highlight the potential of computer vision approaches for improving DFU detection.

Main Methods:

• Review of existing literature on machine learning (ML) and deep learning (DL) for DFU identification.
• Analysis of traditional ML approaches utilizing image features.
• Evaluation of advanced DL techniques, particularly Convolutional Neural Networks (CNNs).

Main Results:

• Traditional ML approaches leverage image features for accurate DFU identification.
• Advanced DL methods, especially CNNs, demonstrate superior performance compared to traditional ML.
• Automatic DFU identification using AI shows potential for faster and more reliable clinical decisions.

Conclusions:

• Both traditional ML and advanced DL techniques are crucial for enhancing DFU diagnosis.
• CNN-based solutions are dominating the field of automatic DFU identification.
• This review assists researchers in understanding the current landscape and defining future research directions in DFU detection.