A Deep Learning Approach for Diabetic Foot Ulcer Classification and Recognition

Advancing Diabetic Foot Ulcer Care: AI and Generative AI Approaches for Classification, Prediction, Segmentation, and Detection

Background: Diabetic foot ulcers (DFUs) represent a significant challenge in managing diabetes, leading to higher patient complications and increased healthcare costs. Traditional approaches, such as manual wound assessment and diagnostic tool usage, often require significant resources, including skilled clinicians, specialized equipment, and extensive time. Artificial intelligence (AI) and generative AI offer promising solutions for improving DFU management. This study systematically reviews the role of AI in DFU classification, prediction, segmentation, and detection. Furthermore, it highlights the role of generative AI in overcoming data scarcity and potential of AI-based smartphone applications for remote monitoring and diagnosis. Methods: A systematic literature review was conducted following the PRISMA guidelines. Relevant studies published between 2020 and 2025 were identified from databases including PubMed, IEEE Xplore, Scopus, and Web of Science. The review focused on AI and generative AI applications in DFU and excluded non-DFU-related medical imaging articles. Results: This study indicates that AI-powered models have significantly improved DFU classification accuracy, early detection, and predictive modeling. Generative AI techniques, such as GANs and diffusion models, have demonstrated potential in addressing dataset limitations by generating synthetic DFU images. Additionally, AI-powered smartphone applications provide cost-effective solutions for DFU monitoring, potentially improving diagnosis. Conclusions: AI and generative AI are transforming DFU management by enhancing diagnostic accuracy and predictive capabilities. Future research should prioritize explainable AI frameworks and diverse datasets for AI-driven healthcare solutions to facilitate broader clinical adoption.

Diabetic Foot Ulcers Detection Model Using a Hybrid Convolutional Neural Networks-Vision Transformers

Background: Diabetic foot ulcers (DFUs) are severe and common complications of diabetes. Early and accurate DFUs classification is essential for effective treatment and prevention of severe complications. The existing DFUs classification methods have certain limitations, including limited performance, poor generalization, and lack of interpretability, restricting their use in clinical settings. Objectives: To overcome these limitations, this study proposes an innovative model to achieve robust and interpretable DFUs classification. Methodology: The proposed DFUs classification integrates MobileNet V3-SWIN, LeViT-Peformer, Tensor-based feature fusion, and ensemble splines-based Kolmogorov-Arnold Networks (KANs) with Shapley Additive exPlanations (SHAP) values to classify DFUs severities into ischemia and infection classes. In order to train and generalize the proposed model, the authors utilized the DFUs challenge (DFUC) 2021 and 2020 datasets. Findings: The proposed model achieved state-of-the-art performance, outperforming the existing approaches by obtaining an average accuracy of 98.7%, precision of 97.3%, recall of 97.4%, and F1-score of 97.3% on DFUC 2021. On DFUC 2020, it maintained a robust generalization accuracy of 96.9%, demonstrating superiority over standalone and baseline models. The study findings have significant implications for research and clinical practice. The findings offer an effective platform for scalable and explainable automated DFUs treatment and management, improving patient outcomes and clinical practices.

A feature explainability-based deep learning technique for diabetic foot ulcer identification

Diabetic foot ulcers (DFUs) are a common and serious complication of diabetes, presenting as open sores or wounds on the sole. They result from impaired blood circulation and neuropathy associated with diabetes, increasing the risk of severe infections and even amputations if untreated. Early detection, effective wound care, and diabetes management are crucial to prevent and treat DFUs. Artificial intelligence (AI), particularly through deep learning, has revolutionized DFU diagnosis and treatment. This work introduces the DFU_XAI framework to enhance the interpretability of deep learning models for DFU labeling and localization, ensuring clinical relevance. The framework evaluates six advanced models-Xception, DenseNet121, ResNet50, InceptionV3, MobileNetV2, and Siamese Neural Network (SNN)-using interpretability techniques like SHAP, LIME, and Grad-CAM. Among these, the SNN model excelled with 98.76% accuracy, 99.3% precision, 97.7% recall, 98.5% F1-score, and 98.6% AUC. Grad-CAM heat maps effectively identified ulcer locations, aiding clinicians with precise and visually interpretable insights. The DFU_XAI framework integrates explainability into AI-driven healthcare, enhancing trust and usability in clinical settings. This approach addresses challenges of transparency in AI for DFU management, offering reliable and efficient solutions to this critical healthcare issue. Traditional DFU methods are labor-intensive and costly, highlighting the transformative potential of AI-driven systems.

Artificial Intelligence Methods for Diagnostic and Decision-Making Assistance in Chronic Wounds: A Systematic Review

Chronic wounds, which take over four weeks to heal, are a major global health issue linked to conditions such as diabetes, venous insufficiency, arterial diseases, and pressure ulcers. These wounds cause pain, reduce quality of life, and impose significant economic burdens. This systematic review explores the impact of technological advancements on the diagnosis of chronic wounds, focusing on how computational methods in wound image and data analysis improve diagnostic precision and patient outcomes. A literature search was conducted in databases including ACM, IEEE, PubMed, Scopus, and Web of Science, covering studies from 2013 to 2023. The focus was on articles applying complex computational techniques to analyze chronic wound images and clinical data. Exclusion criteria were non-image samples, review articles, and non-English or non-Spanish texts. From 2,791 articles identified, 93 full-text studies were selected for final analysis. The review identified significant advancements in tissue classification, wound measurement, segmentation, prediction of wound aetiology, risk indicators, and healing potential. The use of image-based and data-driven methods has proven to enhance diagnostic accuracy and treatment efficiency in chronic wound care. The integration of technology into chronic wound diagnosis has shown a transformative effect, improving diagnostic capabilities, patient care, and reducing healthcare costs. Continued research and innovation in computational techniques are essential to unlock their full potential in managing chronic wounds effectively.

An explainable deep learning model for diabetic foot ulcer classification using swin transformer and efficient multi-scale attention-driven network

Diabetic Foot Ulcer (DFU) is a severe complication of diabetes mellitus, resulting in significant health and socio-economic challenges for the diagnosed individual. Severe cases of DFU can lead to lower limb amputation in diabetic patients, making their diagnosis a complex and costly process that poses challenges for medical professionals. Manual identification of DFU is particularly difficult due to their diverse visual characteristics, leading to multiple cases going undiagnosed. To address this challenge, Deep Learning (DL) methods offer an efficient and automated approach to facilitate timely treatment and improve patient outcomes. This research proposes a novel feature fusion-based model that incorporates two parallel tracks for efficient feature extraction. The first track utilizes the Swin transformer, which captures long-range dependencies by employing shifted windows and self-attention mechanisms. The second track involves the Efficient Multi-Scale Attention-Driven Network (EMADN), which leverages Light-weight Multi-scale Deformable Shuffle (LMDS) and Global Dilated Attention (GDA) blocks to extract local features efficiently. These blocks dynamically adjust kernel sizes and leverage attention modules, enabling effective feature extraction. To the best of our knowledge, this is the first work reporting the findings of a dual track architecture for DFU classification, leveraging Swin transformer and EMADN networks. The obtained feature maps from both the networks are concatenated and subjected to shuffle attention for feature refinement at a reduced computational cost. The proposed work also incorporates Grad-CAM-based Explainable Artificial Intelligence (XAI) to visualize and interpret the decision making of the network. The proposed model demonstrated better performance on the DFUC-2021 dataset, surpassing existing works and pre-trained CNN architectures with an accuracy of 78.79% and a macro F1-score of 80%.

Diabetic foot ulcer classification assessment employing an improved machine learning algorithm

BACKGROUND

Diabetic foot ulcers (DFU) are a severe consequence of diabetes that, if left untreated, can lead to amputation, blindness, renal failure, and other serious complications. The high treatment expense and length of treatment for this therapeutic technique are both disadvantages. Despite the effectiveness of this strategy, a distant, cost-effective, and comfortable DFU diagnostic therapy is necessary.

OBJECTIVE

This study proposed the Advanced Machine Learning Practical Method for Diabetic Foot Ulcer Classification.

METHODS

This unique and cost-effective healthcare solution uses Practical Methodologies with the reinforcement learning algorithm for DFU imaging. The categorization was based on constant technological advancements, and the benefits of Machine Learning (ML) for use in DFU treatment are numerous, including enhanced clinical decision-making based on Ulcer classification and healing progress. The ML greatly impacted DFU data analysis, with categorization and risk assessment among the findings.

RESULTS

The machine-learning technique can potentially create a paradigm shift by providing a 92.5% classification accuracy evaluation in the diabetic foot Ulcer problem. According to Clustering Scenario Analysis of Diabetic Foot Ulcer, when compared to Mild To Moderate Localized Cellulitis (Cluster 1 produces classification efficiency from 71% to 88%), Moderate To Severe Cellulitis (Cluster 2 delivers classification efficiency from 85% to 97%), Moderate To Severe Cellulitis With Ischemia (Cluster 3 produces classification efficiency from 90% to 98%), and Life-Or Limb-Threatening Infection (Cluster 4), the results were promising (Cluster 4 makes classification efficiency from 93.5% to 98.2%). The efficiency of this is Cluster 78.45 percent higher than the existing procedure.

CONCLUSIONS

The proposed Advanced Machine Learning Practical Method demonstrates significant improvements in DFU classification accuracy and efficiency, presenting a cost-effective and effective alternative to traditional diagnostic approaches.

Artificial Intelligence to Diagnose Complications of Diabetes

Artificial intelligence (AI) is increasingly being used to diagnose complications of diabetes. Artificial intelligence is technology that enables computers and machines to simulate human intelligence and solve complicated problems. In this article, we address current and likely future applications for AI to be applied to diabetes and its complications, including pharmacoadherence to therapy, diagnosis of hypoglycemia, diabetic eye disease, diabetic kidney diseases, diabetic neuropathy, diabetic foot ulcers, and heart failure in diabetes.Artificial intelligence is advantageous because it can handle large and complex datasets from a variety of sources. With each additional type of data incorporated into a clinical picture of a patient, the calculation becomes increasingly complex and specific. Artificial intelligence is the foundation of emerging medical technologies; it will power the future of diagnosing diabetes complications.

SwinDFU-Net: Deep learning transformer network for infection identification in diabetic foot ulcer

BACKGROUND

The identification of infection in diabetic foot ulcers (DFUs) is challenging due to variability within classes, visual similarity between classes, reduced contrast with healthy skin, and presence of artifacts. Existing studies focus on visual characteristics and tissue classification rather than infection detection, critical for assessing DFUs and predicting amputation risk.

OBJECTIVE

To address these challenges, this study proposes a deep learning model using a hybrid CNN and Swin Transformer architecture for infection classification in DFU images. The aim is to leverage end-to-end mapping without prior knowledge, integrating local and global feature extraction to improve detection accuracy.

METHODS

The proposed model utilizes a hybrid CNN and Swin Transformer architecture. It employs the Grad CAM technique to visualize the decision-making process of the CNN and Transformer blocks. The DFUC Challenge dataset is used for training and evaluation, emphasizing the model's ability to accurately classify DFU images into infected and non-infected categories.

RESULTS

The model achieves high performance metrics: sensitivity (95.98%), specificity (97.08%), accuracy (96.52%), and Matthews Correlation Coefficient (0.93). These results indicate the model's effectiveness in quickly diagnosing DFU infections, highlighting its potential as a valuable tool for medical professionals.

CONCLUSION

The hybrid CNN and Swin Transformer architecture effectively combines strengths from both models, enabling accurate classification of DFU images as infected or non-infected, even in complex scenarios. The use of Grad CAM provides insights into the model's decision process, aiding in identifying infected regions within DFU images. This approach shows promise for enhancing clinical assessment and management of DFU infections.

A few-shot diabetes foot ulcer image classification method based on deep ResNet and transfer learning

Diabetes foot ulcer (DFU) is one of the common complications of diabetes patients, which may lead to infection, necrosis and even amputation. Therefore, early diagnosis, classification of severity and related treatment are crucial for the patients. Current DFU classification methods often require experienced doctors to manually classify the severity, which is time-consuming and low accuracy. The objective of the study is to propose a few-shot DFU image classification method based on deep residual neural network and transfer learning. Considering the difficulty in obtaining clinical DFU images, it is a few-shot problem. Therefore, the methods include: (1) Data augmentation of the original DFU images by using geometric transformations and random noise; (2) Deep ResNet models selection based on different convolutional layers comparative experiments; (3) DFU classification model training with transfer learning by using the selected pre-trained ResNet model and fine tuning. To verify the proposed classification method, the experiments were performed with the original and augmented datasets by separating three classifications: zero grade, mild grade, severe grade. (1) The datasets were augmented from the original 146 to 3000 image datasets and the corresponding DFU classification's average accuracy from 0.9167 to 0.9867; (2) Comparative experiments were conducted with ResNet18, ResNet34, ResNet50, ResNet101, ResNet152 by using 3000 image datasets, and the average accuracy/loss is 0.9325/0.2927, 0.9276/0.3234, 0.9901/0.1356, 0.9865/0.1427, 0.9790/0.1583 respectively; (3) Based on the augmented 3000 image datasets, it was achieved 0.9867 average accuracy with the DFU classification model, which was trained by the pre-trained ResNet50 and hyper-parameters. The experimental results indicated that the proposed few-shot DFU image classification method based on deep ResNet and transfer learning got very high accuracy, and it is expected to be suitable for low-cost and low-computational terminal equipment, aiming at helping clinical DFU classification efficiently and auxiliary diagnosis.

Differential Diagnosis of Diabetic Foot Osteomyelitis and Charcot Neuropathic Osteoarthropathy with Deep Learning Methods

Our study aims to evaluate the potential of a deep learning (DL) algorithm for differentiating the signal intensity of bone marrow between osteomyelitis (OM), Charcot neuropathic osteoarthropathy (CNO), and trauma (TR). The local ethics committee approved this retrospective study. From 148 patients, segmentation resulted in 679 labeled regions for T1-weighted images (comprising 151 CNO, 257 OM, and 271 TR) and 714 labeled regions for T2-weighted images (consisting of 160 CNO, 272 OM, and 282 TR). We employed both multi-class classification (MCC) and binary-class classification (BCC) approaches to compare the classification outcomes of CNO, TR, and OM. The ResNet-50 and the EfficientNet-b0 accuracy values were computed at 96.2% and 97.1%, respectively, for T1-weighted images. Additionally, accuracy values for ResNet-50 and the EfficientNet-b0 were determined at 95.6% and 96.8%, respectively, for T2-weighted images. Also, according to BCC for CNO, OM, and TR, the sensitivity of ResNet-50 is 91.1%, 92.4%, and 96.6% and the sensitivity of EfficientNet-b0 is 93.2%, 97.6%, and 98.1% for T1, respectively. For CNO, OM, and TR, the sensitivity of ResNet-50 is 94.9%, 83.6%, and 97.9% and the sensitivity of EfficientNet-b0 is 95.6%, 85.2%, and 98.6% for T2, respectively. The specificity values of ResNet-50 for CNO, OM, and TR in T1-weighted images are 98.1%, 97.9%, and 94.7% and 98.6%, 97.5%, and 96.7% in T2-weighted images respectively. Similarly, for EfficientNet-b0, the specificity values are 98.9%, 98.7%, and 98.4% and 99.1%, 98.5%, and 98.7% for T1-weighted and T2-weighted images respectively. In the diabetic foot, deep learning methods serve as a non-invasive tool to differentiate CNO, OM, and TR with high accuracy.

Integrated image and location analysis for wound classification: a deep learning approach

The global burden of acute and chronic wounds presents a compelling case for enhancing wound classification methods, a vital step in diagnosing and determining optimal treatments. Recognizing this need, we introduce an innovative multi-modal network based on a deep convolutional neural network for categorizing wounds into four categories: diabetic, pressure, surgical, and venous ulcers. Our multi-modal network uses wound images and their corresponding body locations for more precise classification. A unique aspect of our methodology is incorporating a body map system that facilitates accurate wound location tagging, improving upon traditional wound image classification techniques. A distinctive feature of our approach is the integration of models such as VGG16, ResNet152, and EfficientNet within a novel architecture. This architecture includes elements like spatial and channel-wise Squeeze-and-Excitation modules, Axial Attention, and an Adaptive Gated Multi-Layer Perceptron, providing a robust foundation for classification. Our multi-modal network was trained and evaluated on two distinct datasets comprising relevant images and corresponding location information. Notably, our proposed network outperformed traditional methods, reaching an accuracy range of 74.79-100% for Region of Interest (ROI) without location classifications, 73.98-100% for ROI with location classifications, and 78.10-100% for whole image classifications. This marks a significant enhancement over previously reported performance metrics in the literature. Our results indicate the potential of our multi-modal network as an effective decision-support tool for wound image classification, paving the way for its application in various clinical contexts.

CADFU for Dermatologists: A Novel Chronic Wounds & Ulcers Diagnosis System with DHuNeT (Dual-Phase Hyperactive UNet) and YOLOv8 Algorithm

In recent times, there has been considerable focus on harnessing artificial intelligence (AI) for medical image analysis and healthcare purposes. In this study, we introduce CADFU (Computer-Aided Diagnosis System for Foot Ulcers), a pioneering diabetic foot ulcer diagnosis system. The primary objective of CADFU is to detect and segment ulcers and similar chronic wounds in medical images. To achieve this, we employ two distinct algorithms. Firstly, DHuNeT, an innovative Dual-Phase Hyperactive UNet, is utilized for the segmentation task. Second, we used YOLOv8 for the task of detecting wounds. The DHuNeT autoencoder, employed for the wound segmentation task, is the paper's primary and most significant contribution. DHuNeT is the combination of sequentially stacking two UNet autoencoders. The hyperactive information transmission from the first UNet to the second UNet is the key idea of DHuNeT. The first UNet feeds the second UNet the features it has learned, and the two UNets combine their learned features to create new, more accurate, and effective features. We achieve good performance measures, especially in terms of the Dice co-efficient and precision, with segmentation scores of 85% and 92.6%, respectively. We obtain a mean average precision (mAP) of 86% in the detection task. Future hospitals could quickly monitor patients' health using the proposed CADFU system, which would be beneficial for both patients and doctors.

Spatial attention-based residual network for human burn identification and classification

Diagnosing burns in humans has become critical, as early identification can save lives. The manual process of burn diagnosis is time-consuming and complex, even for experienced doctors. Machine learning (ML) and deep convolutional neural network (CNN) models have emerged as the standard for medical image diagnosis. The ML-based approach typically requires handcrafted features for training, which may result in suboptimal performance. Conversely, DL-based methods automatically extract features, but designing a robust model is challenging. Additionally, shallow DL methods lack long-range feature dependency, decreasing efficiency in various applications. We implemented several deep CNN models, ResNeXt, VGG16, and AlexNet, for human burn diagnosis. The results obtained from these models were found to be less reliable since shallow deep CNN models need improved attention modules to preserve the feature dependencies. Therefore, in the proposed study, the feature map is divided into several categories, and the channel dependencies between any two channel mappings within a given class are highlighted. A spatial attention map is built by considering the links between features and their locations. Our attention-based model BuRnGANeXt50 kernel and convolutional layers are also optimized for human burn diagnosis. The earlier study classified the burn based on depth of graft and non-graft. We first classified the burn based on the degree. Subsequently, it is classified into graft and non-graft. Furthermore, the proposed model performance is evaluated on Burns_BIP_US_database. The sensitivity of the BuRnGANeXt50 is 97.22% and 99.14%, respectively, for classifying burns based on degree and depth. This model may be used for quick screening of burn patients and can be executed in the cloud or on a local machine. The code of the proposed method can be accessed at https://github.com/dhirujis02/Journal.git for the sake of reproducibility.

Deep Learning-Based Classification and Feature Extraction for Predicting Pathogenesis of Foot Ulcers in Patients with Diabetes

The World Health Organization (WHO) has identified that diabetes mellitus (DM) is one of the most prevalent disease worldwide. Individuals with DM have a higher risk of mortality, and it is crucial to prioritize the treatment of foot ulcers, which is a significant complication associated with the disease, as they lead to the development of plantar ulcers, which results in the need to amputate part of the foot or leg. People with diabetes are at risk of experiencing various complications, such as heart disease, eye problems, kidney dysfunction, nerve damage, skin issues, foot ulcers, and dental diseases. Unawareness of the risk associated with diabetic foot ulcers (DFU) is a significant contributing factor to the mortality of diabetic patients. Evolving technological advancements such as deep learning techniques can be used to predict the symptoms of diabetic foot ulcers as early as possible, which helps to provide effective treatment to DM patients. This research introduces a methodology for analyzing images of foot ulcers in diabetic patients, focusing on feature extraction and classification. The dataset used in this study was collected from historical medical records and foot images of patients with diabetes, who commonly experience foot ulcers as a major complication. The dataset was pre-processed and segmented, and features were extracted using a deep recurrent neural network (DRNN). Image and numerical/text data were extracted separately, and the normal and abnormal diabetes ranges were identified. Foot images of patients with abnormal diabetes ranges were separated and classified using a pre-trained fast convolutional neural network (PFCNN) with U++net. The classification procedure involves the analysis of foot ulcers to predict their pathogenesis. To assess the effectiveness of the proposed technique, the study presented simulation results, including a confusion matrix and receiver operating characteristic curve. These results specifically focused on predicting two classes: normal and abnormal diabetes foot ulcerations. The analysis yielded various parameters, including accuracy, precision, recall curve, and area under the curve. The main goal of the study was to introduce an novel technique for assessing the risk of foot ulceration development in patients with diabetes, leveraging the analysis of foot ulcer images. The researchers collected a dataset of foot images and medical data from historical records of patients with diabetes and pre-processed and segmented the data. They then used a deep recurrent neural network to extract features from the segmented data and identified normal and abnormal diabetes ranges based on numerical and text data. Foot images of patients with abnormal diabetes ranges were classified using a pre-trained fast convolutional neural network with U++net to examine foot ulcers and forecast the development of the risk of diabetic foot ulcers (DFU). The study assessed the accuracy of the proposed technique as 99.32% by simulating results for feature extraction and the classification of diabetic foot ulcers. A comparison was made between this proposed technique and existing approaches.