Deep learning in diabetic foot ulcers detection: A comprehensive evaluation

An enhanced harmonic densely connected hybrid transformer network architecture for chronic wound segmentation utilising multi-colour space tensor merging

Chronic wounds and associated complications present ever growing burdens for clinics and hospitals world wide. Venous, arterial, diabetic, and pressure wounds are becoming increasingly common globally. These conditions can result in highly debilitating repercussions for those affected, with limb amputations and increased mortality risk resulting from infection becoming more common. New methods to assist clinicians in chronic wound care are therefore vital to maintain high quality care standards. This paper presents an improved HarDNet segmentation architecture which integrates a contrast-eliminating component in the initial layers of the network to enhance feature learning. We also utilise a multi-colour space tensor merging process and adjust the harmonic shape of the convolution blocks to facilitate these additional features. We train our proposed model using wound images from light skinned patients and test the model on two test sets (one set with ground truth, and one without) comprising only darker skinned cases. Subjective ratings are obtained from clinical wound experts with intraclass correlation coefficient used to determine inter-rater reliability. For the dark skin tone test set with ground truth, when comparing the baseline results (DSC=0.6389, IoU=0.5350) with the results for the proposed model (DSC=0.7610, IoU=0.6620) we demonstrate improvements in terms of Dice similarity coefficient (+0.1221) and intersection over union (+0.1270). Measures from the qualitative analysis also indicate improvements in terms of high expert ratings, with improvements of >3% demonstrated when comparing the baseline model with the proposed model. This paper presents the first study to focus on darker skin tones for chronic wound segmentation using models trained only on wound images exhibiting lighter skin. Diabetes is highly prevalent in countries where patients have darker skin tones, highlighting the need for a greater focus on such cases. Additionally, we conduct the largest qualitative study to date for chronic wound segmentation. All source code for this study is available at: https://github.com/mmu-dermatology-research/hardnet-cws.

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.

Deep-Learning-Based Analysis of Electronic Skin Sensing Data

E-skin is an integrated electronic system that can mimic the perceptual ability of human skin. Traditional analysis methods struggle to handle complex e-skin data, which include time series and multiple patterns, especially when dealing with intricate signals and real-time responses. Recently, deep learning techniques, such as the convolutional neural network, recurrent neural network, and transformer methods, provide effective solutions that can automatically extract data features and recognize patterns, significantly improving the analysis of e-skin data. Deep learning is not only capable of handling multimodal data but can also provide real-time response and personalized predictions in dynamic environments. Nevertheless, problems such as insufficient data annotation and high demand for computational resources still limit the application of e-skin. Optimizing deep learning algorithms, improving computational efficiency, and exploring hardware-algorithm co-designing will be the key to future development. This review aims to present the deep learning techniques applied in e-skin and provide inspiration for subsequent researchers. We first summarize the sources and characteristics of e-skin data and review the deep learning models applicable to e-skin data and their applications in data analysis. Additionally, we discuss the use of deep learning in e-skin, particularly in health monitoring and human-machine interactions, and we explore the current challenges and future development directions.

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.

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.

Deep learning-based object detection algorithms in medical imaging: Systematic review

Over the past decade, Deep Learning (DL) techniques have demonstrated remarkable advancements across various domains, driving their widespread adoption. Particularly in medical image analysis, DL received greater attention for tasks like image segmentation, object detection, and classification. This paper provides an overview of DL-based object recognition in medical images, exploring recent methods and emphasizing different imaging techniques and anatomical applications. Utilizing a meticulous quantitative and qualitative analysis following PRISMA guidelines, we examined publications based on citation rates to explore into the utilization of DL-based object detectors across imaging modalities and anatomical domains. Our findings reveal a consistent rise in the utilization of DL-based object detection models, indicating unexploited potential in medical image analysis. Predominantly within Medicine and Computer Science domains, research in this area is most active in the US, China, and Japan. Notably, DL-based object detection methods have gotten significant interest across diverse medical imaging modalities and anatomical domains. These methods have been applied to a range of techniques including CR scans, pathology images, and endoscopic imaging, showcasing their adaptability. Moreover, diverse anatomical applications, particularly in digital pathology and microscopy, have been explored. The analysis underscores the presence of varied datasets, often with significant discrepancies in size, with a notable percentage being labeled as private or internal, and with prospective studies in this field remaining scarce. Our review of existing trends in DL-based object detection in medical images offers insights for future research directions. The continuous evolution of DL algorithms highlighted in the literature underscores the dynamic nature of this field, emphasizing the need for ongoing research and fitted optimization for specific applications.

Reconstruction residual network with a fused spatial-channel attention mechanism for automatically classifying diabetic foot ulcer

Diabetic foot ulcer (DFU) is a common chronic complication of diabetes. This complication is characterized by the formation of ulcers that are difficult to heal on the skin of the foot. Ulcers can negatively affect patients' quality of life, and improperly treated lesions can result in amputation and even death. Traditionally, the severity and type of foot ulcers are determined by doctors through visual observations and on the basis of their clinical experience; however, this subjective evaluation can lead to misjudgments. In addition, quantitative methods have been developed for classifying and scoring are therefore time-consuming and labor-intensive. In this paper, we propose a reconstruction residual network with a fused spatial-channel attention mechanism (FARRNet) for automatically classifying DFUs. The use of pseudo-labeling and Data augmentation as a pre-processing technique can overcome problems caused by data imbalance and small sample size. The developed model's attention was enhanced using a spatial channel attention (SPCA) module that incorporates spatial and channel attention mechanisms. A reconstruction mechanism was incorporated into the developed residual network to improve its feature extraction ability for achieving better classification. The performance of the proposed model was compared with that of state-of-the-art models and those in the DFUC Grand Challenge. When applied to the DFUC Grand Challenge, the proposed method outperforms other state-of-the-art schemes in terms of accuracy, as evaluated using 5-fold cross-validation and the following metrics: macro-average F1-score, AUC, Recall, and Precision. FARRNet achieved the F1-score of 60.81%, AUC of 87.37%, Recall of 61.04%, and Precision of 61.56%. Therefore, the proposed model is more suitable for use in medical diagnosis environments with embedded devices and limited computing resources. The proposed model can assist patients in initial identifications of ulcer wounds, thereby helping them to obtain timely treatment.

An overview of current developments and methods for identifying diabetic foot ulcers: A survey

Diabetic foot ulcers (DFUs) present a substantial health risk across diverse age groups, creating challenges for healthcare professionals in the accurate classification and grading. DFU plays a crucial role in automated health monitoring and diagnosis systems, where the integration of medical imaging, computer vision, statistical analysis, and gait information is essential for comprehensive understanding and effective management. Diagnosing DFU is imperative, as it plays a major role in the processes of diagnosis, treatment planning, and neuropathy research within automated health monitoring and diagnosis systems. To address this, various machine learning and deep learning‐based methodologies have emerged in the literature to support healthcare practitioners in achieving improved diagnostic analyses for DFU. This survey paper investigates various diagnostic methodologies for DFU, spanning traditional statistical approaches to cutting‐edge deep learning techniques. It systematically reviews key stages involved in diabetic foot ulcer classification (DFUC) methods, including preprocessing, feature extraction, and classification, explaining their benefits and drawbacks. The investigation extends to exploring state‐of‐the‐art convolutional neural network models tailored for DFUC, involving extensive experiments with data augmentation and transfer learning methods. The overview also outlines datasets commonly employed for evaluating DFUC methodologies. Recognizing that neuropathy and reduced blood flow in the lower limbs might be caused by atherosclerotic blood vessels, this paper provides recommendations to researchers and practitioners involved in routine medical therapy to prevent substantial complications. Apart from reviewing prior literature, this survey aims to influence the future of DFU diagnostics by outlining prospective research directions, particularly in the domains of personalized and intelligent healthcare. Finally, this overview is to contribute to the continual evolution of DFU diagnosis in order to provide more effective and customized medical care.

This article is categorized under:

Enhancing diabetic foot ulcer prediction with machine learning: A focus on Localized examinations

Background

diabetices foot ulcer (DFU) are serious complications. It is crucial to detect and diagnose DFU early in order to provide timely treatment, improve patient quality of life, and avoid the social and economic consequences. Machine learning techniques can help identify risk factors associated with DFU development.

Objective

The aim of this study was to establish correlations between clinical and biochemical risk factors of DFU through local foot examinations based on the construction of predictive models using automated machine learning techniques.

Methods

The input dataset consisted of 566 diabetes cases and 50 DFU risk factors, including 9 local foot examinations. 340 patients with Class 0 labeling (low-risk DFU), 226 patients with Class 1 labeling (high-risk DFU). To divide the training group (consisting of 453 cases) and the validation group (consisting of 113 cases), as well as preprocess the data and develop a prediction model, a Monte Carlo cross-validation approach was employed. Furthermore, potential high-risk factors were analyzed using various algorithms, including Bayesian BYS, Multi-Gaussian Weighted Classifier (MGWC), Support Vector Machine (SVM), and Random Forest Classifier (RF). A three-layer machine learning training was constructed, and model performance was estimated using a Confusion Matrix. The top 30 ranking feature variables were ultimately determined. To reinforce the robustness and generalizability of the predictive model, an independent dataset comprising 248 cases was employed for external validation. This validation process evaluated the model's applicability and reliability across diverse populations and clinical settings. Importantly, the external dataset required no additional tuning or adjustment of parameters, enabling an unbiased assessment of the model's generalizability and its capacity to predict the risk of DFU.

Results

The ensemble learning method outperformed individual classifiers in various performance evaluation metrics. Based on the ROC analysis, the AUC of the AutoML model for assessing diabetic foot risk was 88.48 % (74.44-97.83 %). Other results were found to be as follows: 87.23 % (63.33 %-100.00 %) for sensitivity, 87.43 % (70.00 %-100.00 %) for specificity, 87.33 % (76.66 %-95.00 %) for accuracy, 87.69 % (75.00 %-100.00 %) for positive predictive value, and 87.70 % (71.79 %-100.00 %) for negative predictive value. In addition to traditional DFU risk factors such as cardiovascular disorders, peripheral artery disease, and neurological damage, we identified new risk factors such as lower limb varicose veins, history of cerebral infarction, blood urea nitrogen, GFR (Glomerular Filtration Rate), and type of diabetes that may be related to the development of DFU. In the external validation set of 158 samples, originating from an initial 248 with exclusions due to missing labels or features, the model still exhibited strong predictive accuracy. The AUC score of 0.762 indicated a strong discriminatory capability of the model. Furthermore, the Sensitivity and Specificity values provided insights into the model's ability to correctly identify both DFU cases and non-cases, respectively.

Conclusion

The predictive model, developed through AutoML and grounded in local foot examinations, has proven to be a robust and practical instrument for the screening, prediction, and diagnosis of DFU risk. This model not only aids medical practitioners in the identification of potential DFU cases but also plays a pivotal role in mitigating the progression towards adverse outcomes. And the recent successful external validation of our DFU risk prediction model marks a crucial advancement, indicating its readiness for clinical application. This validation reinforces the model's efficacy as an accessible and reliable tool for early DFU risk assessment, thereby facilitating prompt intervention strategies and enhancing overall patient outcomes.

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.

DFUCare: deep learning platform for diabetic foot ulcer detection, analysis, and monitoring

Introduction

Diabetic foot ulcers (DFUs) are a severe complication among diabetic patients, often leading to amputation or even death. Early detection of infection and ischemia is essential for improving healing outcomes, but current diagnostic methods are invasive, time-consuming, and costly. There is a need for non-invasive, efficient, and affordable solutions in diabetic foot care.

Methods

We developed DFUCare, a platform that leverages computer vision and deep learning (DL) algorithms to localize, classify, and analyze DFUs non-invasively. The platform combines CIELAB and YCbCr color space segmentation with a pre-trained YOLOv5s algorithm for wound localization. Additionally, deep-learning models were implemented to classify infection and ischemia in DFUs. The preliminary performance of the platform was tested on wound images acquired using a cell phone.

Results

DFUCare achieved an F1-score of 0.80 and a mean Average Precision (mAP) of 0.861 for wound localization. For infection classification, we obtained a binary accuracy of 79.76%, while ischemic classification reached 94.81% on the validation set. The system successfully measured wound size and performed tissue color and textural analysis for a comparative assessment of macroscopic wound features. In clinical testing, DFUCare localized wounds and predicted infected and ischemic with an error rate of less than 10%, underscoring the strong performance of the platform.

Discussion

DFUCare presents an innovative approach to wound care, offering a cost-effective, remote, and convenient healthcare solution. By enabling non-invasive and accurate analysis of wounds using mobile devices, this platform has the potential to revolutionize diabetic foot care and improve clinical outcomes through early detection of infection and ischemia.

Target-based deep learning network surveillance of non-contrast computed tomography for small infarct core of acute ischemic stroke

Purpose

Rapid diagnosis of acute ischemic stroke (AIS) is critical to achieve positive outcomes and prognosis. This study aimed to construct a model to automatically identify the infarct core based on non-contrast-enhanced CT images, especially for small infarcts.

Methods

The baseline CT scans of AIS patients, who had DWI scans obtained within less than 2 h apart, were included in this retrospective study. A modified Target-based deep learning model of YOLOv5 was developed to detect infarctions on CT. Randomly selected CT images were used for testing and evaluated by neuroradiologists and the model, using the DWI as a reference standard. Intraclass correlation coefficient (ICC) and weighted kappa were calculated to assess the agreement. The paired chi-square test was used to compare the diagnostic efficacy of physician groups and automated models in subregions. p < 0.05 was considered statistically significant.

Results

Five hundred and eighty four AIS patients were enrolled in total, finally 275 cases were eligible. Modified YOLOv5 perform better with increased precision (0.82), recall (0.81) and mean average precision (0.79) than original YOLOv5. Model showed higher consistency to the DWI-ASPECTS scores (ICC = 0.669, κ = 0.447) than neuroradiologists (ICC = 0.452, κ = 0.247). The sensitivity (75.86% vs. 63.79%), specificity (98.87% vs. 95.02%), and accuracy (96.20% vs. 91.40%) were better than neuroradiologists. Automatic model had better diagnostic efficacy than physician diagnosis in the M6 region (p = 0.039).

Conclusion

The deep learning model was able to detect small infarct core on CT images more accurately. It provided the infarct portion and extent, which is valuable in assessing the severity of disease and guiding treatment procedures.

CFI-Net: A Choquet Fuzzy Integral Based Ensemble Network With PSO-Optimized Fuzzy Measures for Diagnosing Multiple Skin Diseases Including Mpox

In the domain of medical diagnostics, precise identification of various skin and oral diseases is vital for effective patient care. In particular, Mpox is a potentially dangerous viral disease with zoonotic origins, capable of human-to-human transmission, underscoring the urgency of precise diagnostic methods for timely intervention. This paper introduces a novel approach named the Choquet Fuzzy Integral-based Ensemble (CFI-Net) for accurate classification of skin diseases, with a specific emphasis on detecting Mpox, foot ulcers, and various mouth and oral diseases. Our methodology begins with Transfer Learning, enhancing the classification capabilities of base classifiers (DenseNet169, MobileNetV1 and DenseNet201) by incorporating additional layers. Subsequently, we aggregate the prediction scores from each base classifier using the Choquet fuzzy integral (CFI) to derive the final predicted labels, thus ensuring dynamic and robust predictions. Fuzzy measures, a crucial component of this fuzzy integral-based ensemble method, are typically determined through manual experimentation in previous approaches. However, in our study, we have tackled the challenge of manual tuning by employing meta-heuristic optimization algorithm to precisely configure the fuzzy measures for optimal performance. A rigorous evaluation is conducted on four publicly available datasets, encompassing two Mpox datasets, a foot ulcer dataset, and a mouth and oral disease dataset. The experiments reveal the remarkable effectiveness of CFI-Net in significantly improving disease classification accuracy. Additionally, we employ Grad-CAM analysis to provide insights into the decision-making processes of our models. Our findings underscore the exceptional performance of CFI-Net, achieving accuracy rates of 98.06% and 94.81% for Mpox detection, 99.06% for foot ulcer detection, and an impressive 99.61% for mouth and oral disease classification. This research not only contributes to the advancement of disease diagnosis but also demonstrates the effectiveness of ensemble learning techniques coupled with fuzzy integral-based fusion in enhancing diagnostic accuracy.

Smart diabetic foot ulcer scoring system

Current assessment methods for diabetic foot ulcers (DFUs) lack objectivity and consistency, posing a significant risk to diabetes patients, including the potential for amputations, highlighting the urgent need for improved diagnostic tools and care standards in the field. To address this issue, the objective of this study was to develop and evaluate the Smart Diabetic Foot Ulcer Scoring System, ScoreDFUNet, which incorporates artificial intelligence (AI) and image analysis techniques, aiming to enhance the precision and consistency of diabetic foot ulcer assessment. ScoreDFUNet demonstrates precise categorization of DFU images into "ulcer," "infection," "normal," and "gangrene" areas, achieving a noteworthy accuracy rate of 95.34% on the test set, with elevated levels of precision, recall, and F1 scores. Comparative evaluations with dermatologists affirm that our algorithm consistently surpasses the performance of junior and mid-level dermatologists, closely matching the assessments of senior dermatologists, and rigorous analyses including Bland-Altman plots and significance testing validate the robustness and reliability of our algorithm. This innovative AI system presents a valuable tool for healthcare professionals and can significantly improve the care standards in the field of diabetic foot ulcer assessment.

Diabetic Foot Ulcer Detection: Combining Deep Learning Models for Improved Localization

Diabetes mellitus (DM) can cause chronic foot issues and severe infections, including Diabetic Foot Ulcers (DFUs) that heal slowly due to insufficient blood flow. A recurrence of these ulcers can lead to 84% of lower limb amputations and even cause death. High-risk diabetes patients require expensive medications, regular check-ups, and proper personal hygiene to prevent DFUs, which affect 15–25% of diabetics. Accurate diagnosis, appropriate care, and prompt response can prevent amputations and fatalities through early and reliable DFU detection from image analysis. We propose a comprehensive deep learning-based system for detecting DFUs from patients’ feet images by reliably localizing ulcer points. Our method utilizes innovative model ensemble techniques—non-maximum suppression (NMS), Soft-NMS, and weighted bounding box fusion (WBF)—to combine predictions from state-of-the-art object detection models. The performances of diverse cutting-edge model architectures used in this study complement each other, leading to more generalized and improved results when combined in an ensemble. Our WBF-based approach combining YOLOv8m and FRCNN-ResNet101 achieves a mean average precision (mAP) score of 86.4% at the IoU threshold of 0.5 on the DFUC2020 dataset, significantly outperforming the former benchmark by 12.4%. We also perform external validation on the IEEE DataPort Diabetic Foot dataset which has demonstrated robust and reliable model performance on the qualitative analysis. In conclusion, our study effectively developed an innovative diabetic foot ulcer (DFU) detection system using an ensemble model of deep neural networks (DNNs). This AI-driven tool serves as an initial screening aid for medical professionals, augmenting the diagnostic process by enhancing sensitivity to potential DFU cases. While recognizing the presence of false positives, our research contributes to improving patient care through the integration of human medical expertise with AI-based solutions in DFU management.

Diabetic foot ulcers segmentation challenge report: Benchmark and analysis

Monitoring the healing progress of diabetic foot ulcers is a challenging process. Accurate segmentation of foot ulcers can help podiatrists to quantitatively measure the size of wound regions to assist prediction of healing status. The main challenge in this field is the lack of publicly available manual delineation, which can be time consuming and laborious. Recently, methods based on deep learning have shown excellent results in automatic segmentation of medical images, however, they require large-scale datasets for training, and there is limited consensus on which methods perform the best. The 2022 Diabetic Foot Ulcers segmentation challenge was held in conjunction with the 2022 International Conference on Medical Image Computing and Computer Assisted Intervention, which sought to address these issues and stimulate progress in this research domain. A training set of 2000 images exhibiting diabetic foot ulcers was released with corresponding segmentation ground truth masks. Of the 72 (approved) requests from 47 countries, 26 teams used this data to develop fully automated systems to predict the true segmentation masks on a test set of 2000 images, with the corresponding ground truth segmentation masks kept private. Predictions from participating teams were scored and ranked according to their average Dice similarity coefficient of the ground truth masks and prediction masks. The winning team achieved a Dice of 0.7287 for diabetic foot ulcer segmentation. This challenge has now entered a live leaderboard stage where it serves as a challenging benchmark for diabetic foot ulcer segmentation.

Artificial intelligence in wound care: diagnosis, assessment and treatment of hard-to-heal wounds: a narrative review

OBJECTIVE

The effective assessment of wounds, both acute and hard-to-heal, is an important component in the delivery by wound care practitioners of efficacious wound care for patients. Improved wound diagnosis, optimising wound treatment regimens, and enhanced prevention of wounds aid in providing patients with a better quality of life (QoL). There is significant potential for the use of artificial intelligence (AI) in health-related areas such as wound care. However, AI-based systems remain to be developed to a point where they can be used clinically to deliver high-quality wound care. We have carried out a narrative review of the development and use of AI in the diagnosis, assessment and treatment of hard-to-heal wounds. We retrieved 145 articles from several online databases and other online resources, and 81 of them were included in this narrative review. Our review shows that AI application in wound care offers benefits in the assessment/diagnosis, monitoring and treatment of acute and hard-to-heal wounds. As well as offering patients the potential of improved QoL, AI may also enable better use of healthcare resources.

Protocol for metadata and image collection at diabetic foot ulcer clinics: enabling research in wound analytics and deep learning

BACKGROUND

The escalating impact of diabetes and its complications, including diabetic foot ulcers (DFUs), presents global challenges in quality of life, economics, and resources, affecting around half a billion people. DFU healing is hindered by hyperglycemia-related issues and diverse diabetes-related physiological changes, necessitating ongoing personalized care. Artificial intelligence and clinical research strive to address these challenges by facilitating early detection and efficient treatments despite resource constraints. This study establishes a standardized framework for DFU data collection, introducing a dedicated case report form, a comprehensive dataset named Zivot with patient population clinical feature breakdowns and a baseline for DFU detection using this dataset and a UNet architecture.

RESULTS

Following this protocol, we created the Zivot dataset consisting of 269 patients with active DFUs, and about 3700 RGB images and corresponding thermal and depth maps for the DFUs. The effectiveness of collecting a consistent and clean dataset was demonstrated using a bounding box prediction deep learning network that was constructed with EfficientNet as the feature extractor and UNet architecture. The network was trained on the Zivot dataset, and the evaluation metrics showed promising values of 0.79 and 0.86 for F1-score and mAP segmentation metrics.

CONCLUSIONS

This work and the Zivot database offer a foundation for further exploration of holistic and multimodal approaches to DFU research.

Determining the Presence and Size of Shoulder Lesions in Sows Using Computer Vision

Shoulder sores predominantly arise in breeding sows and often result in untimely culling. Reported prevalence rates vary significantly, spanning between 5% and 50% depending upon the type of crate flooring inside a farm, the animal's body condition, or an existing injury that causes lameness. These lesions represent not only a welfare concern but also have an economic impact due to the labor needed for treatment and medication. The objective of this study was to evaluate the use of computer vision techniques in detecting and determining the size of shoulder lesions. A Microsoft Kinect V2 camera captured the top-down depth and RGB images of sows in farrowing crates. The RGB images were collected at a resolution of 1920 × 1080. To ensure the best view of the lesions, images were selected with sows lying on their right and left sides with all legs extended. A total of 824 RGB images from 70 sows with lesions at various stages of development were identified and annotated. Three deep learning-based object detection models, YOLOv5, YOLOv8, and Faster-RCNN, pre-trained with the COCO and ImageNet datasets, were implemented to localize the lesion area. YOLOv5 was the best predictor as it was able to detect lesions with an mAP@0.5 of 0.92. To estimate the lesion area, lesion pixel segmentation was carried out on the localized region using traditional image processing techniques like Otsu's binarization and adaptive thresholding alongside DL-based segmentation models based on U-Net architecture. In conclusion, this study demonstrates the potential of computer vision techniques in effectively detecting and assessing the size of shoulder lesions in breeding sows, providing a promising avenue for improving sow welfare and reducing economic losses.

Automatic detection and segmentation of chorda tympani under microscopic vision in otosclerosis patients via convolutional neural networks

BACKGROUND

Artificial intelligence (AI) techniques, especially deep learning (DL) techniques, have shown promising results for various computer vision tasks in the field of surgery. However, AI-guided navigation during microscopic surgery for real-time surgical guidance and decision support is much more complex, and its efficacy has yet to be demonstrated. We propose a model dedicated to the evaluation of DL-based semantic segmentation of chorda tympani (CT) during microscopic surgery.

METHODS

Various convolutional neural networks were constructed, trained, and validated for semantic segmentation of CT. Our dataset has 5817 images annotated from 36 patients, which were further randomly split into the training set (90%, 5236 images) and validation set (10%, 581 images). In addition, 1500 raw images from 3 patients (500 images randomly selected per patient) were used to evaluate the network performance.

RESULTS

When evaluated on a validation set (581 images), our proposed CT detection networks achieved great performance, and the modified U-net performed best (mIOU = 0.892, mPA = 0.9427). Moreover, when applying U-net to predict the test set (1500 raw images from 3 patients), our methods also showed great overall performance (Accuracy = 0.976, Precision = 0.996, Sensitivity = 0.979, Specificity = 0.902).

CONCLUSIONS

This study suggests that DL can be used for the automated detection and segmentation of CT in patients with otosclerosis during microscopic surgery with a high degree of performance. Our research validated the potential feasibility for future vision-based navigation surgical assistance and autonomous surgery using AI.

Multi-Class Wound Classification via High and Low-Frequency Guidance Network

Wound image classification is a crucial preprocessing step to many intelligent medical systems, e.g., online diagnosis and smart medical. Recently, Convolutional Neural Network (CNN) has been widely applied to the classification of wound images and obtained promising performance to some extent. Unfortunately, it is still challenging to classify multiple wound types due to the complexity and variety of wound images. Existing CNNs usually extract high- and low-frequency features at the same convolutional layer, which inevitably causes information loss and further affects the accuracy of classification. To this end, we propose a novel High and Low-frequency Guidance Network (HLG-Net) for multi-class wound classification. To be specific, HLG-Net contains two branches: High-Frequency Network (HF-Net) and Low-Frequency Network (LF-Net). We employ pre-trained models ResNet and Res2Net as the feature backbone of the HF-Net, which makes the network capture the high-frequency details and texture information of wound images. To extract much low-frequency information, we utilize a Multi-Stream Dilation Convolution Residual Block (MSDCRB) as the backbone of the LF-Net. Moreover, a fusion module is proposed to fully explore informative features at the end of these two separate feature extraction branches, and obtain the final classification result. Extensive experiments demonstrate that HLG-Net can achieve maximum accuracy of 98.00%, 92.11%, and 82.61% in two-class, three-class, and four-class wound image classifications, respectively, which outperforms the previous state-of-the-art methods.

Deep Learning Perspectives for Prediction of Diabetic Foot Ulcers

A significant complication of diabetes mellitus, diabetic foot ulcers (DFUs), can have devastating repercussions if they are not identified and treated right away. Machine learning algorithms have gained more attention recently for their potential to anticipate DFUs before they manifest, enabling early management and preventing consequences. In this chapter, the authors examine how convolutional neural networks (CNNs) can be used to forecast DFUs. The performance of DenseNet, EfficientNet, and a regular CNN are specifically compared. With labels identifying the presence or absence of a DFU, the authors use a dataset of medical photographs of diabetic feet to train each model. The objective is to assess the effectiveness of these models and look at how each layer affects the precision of the predictions. The authors also hope to provide some light on how the algorithms are able to pinpoint foot regions that are most likely to get DFUs. They also look into how each CNN model's different layers affect prediction accuracy.

Deep Learning Based Fire Risk Detection on Construction Sites

The recent large-scale fire incidents on construction sites in South Korea have highlighted the need for computer vision technology to detect fire risks before an actual occurrence of fire. This study developed a proactive fire risk detection system by detecting the coexistence of an ignition source (sparks) and a combustible material (urethane foam or Styrofoam) using object detection on images from a surveillance camera. Statistical analysis was carried out on fire incidences on construction sites in South Korea to provide insight into the cause of the large-scale fire incidents. Labeling approaches were discussed to improve the performance of the object detectors for sparks and urethane foams. Detecting ignition sources and combustible materials at a distance was discussed in order to improve the performance for long-distance objects. Two candidate deep learning models, Yolov5 and EfficientDet, were compared in their performance. It was found that Yolov5 showed slightly higher mAP performances: Yolov5 models showed mAPs from 87% to 90% and EfficientDet models showed mAPs from 82% to 87%, depending on the complexity of the model. However, Yolov5 showed distinctive advantages over EfficientDet in terms of easiness and speed of learning.

Healing profiles in patients with a chronic diabetic foot ulcer: An exploratory study with machine learning

Diabetic foot ulcers (DFU) are one of the most frequent and debilitating complications of diabetes. DFU wound healing is a highly complex process, resulting in significant medical, economic and social challenges. Therefore, early identification of patients with a high-risk profile would be important to adequate treatment and more successful health outcomes. This study explores risk assessment profiles for DFU healing and healing prognosis, using machine learning predictive approaches and decision tree algorithms. Patients were evaluated at baseline (T0; N = 158) and 2 months later (T1; N = 108) on sociodemographic, clinical, biochemical and psychological variables. The performance evaluation of the models comprised F1-score, accuracy, precision and recall. Only profiles with F1-score >0.7 were selected for analysis. According to the two profiles generated for DFU healing, the most important predictive factors were illness representations on T1 IPQ-B (IPQ-B ≤ 9.5 and < 10.5) and the DFU duration (≤ 13 weeks). The two predictive models for DFU healing prognosis suggest that biochemical factors are the best predictors of a favorable healing prognosis, namely IL-6, microRNA-146a-5p and PECAM-1 at T0 and angiopoietin-2 at T1. Illness perception at T0 (IPQ-B ≤ 39.5) also emerged as a relevant predictor for healing prognosis. The results emphasize the importance of DFU duration, illness perception and biochemical markers as predictors of  healing in chronic DFUs. Future research is needed to confirm and test the obtained predictive models.

Diabetic Plantar Foot Segmentation in Active Thermography Using a Two-Stage Adaptive Gamma Transform and a Deep Neural Network

Pathological conditions in diabetic feet cause surface temperature variations, which can be captured quantitatively using infrared thermography. Thermal images captured during recovery of diabetic feet after active cooling may reveal richer information than those from passive thermography, but diseased foot regions may exhibit very small temperature differences compared with the surrounding area, complicating plantar foot segmentation in such cold-stressed active thermography. In this study, we investigate new plantar foot segmentation methods for thermal images obtained via cold-stressed active thermography without the complementary information from color or depth channels. To better deal with the temporal variations in thermal image contrast when planar feet are recovering from cold immersion, we propose an image pre-processing method using a two-stage adaptive gamma transform to alleviate the impact of such contrast variations. To improve upon existing deep neural networks for segmenting planar feet from cold-stressed infrared thermograms, a new deep neural network, the Plantar Foot Segmentation Network (PFSNet), is proposed to better extract foot contours. It combines the fundamental U-shaped network structure, a multi-scale feature extraction module, and a convolutional block attention module with a feature fusion network. The PFSNet, in combination with the two-stage adaptive gamma transform, outperforms multiple existing deep neural networks in plantar foot segmentation for single-channel infrared images from cold-stressed infrared thermography, achieving an accuracy of 97.3% and 95.4% as measured by Intersection over Union (IOU) and Dice Similarity Coefficient (DSC) respectively.

Deep Learning-Based Classification of Abrasion and Ischemic Diabetic Foot Sores Using Camera-Captured Images

Diabetic foot sores (DFS) are serious diabetic complications. The patient’s weakened neurological system damages the tissues of the foot’s skin, which results in amputation. This study aims to validate and deploy a deep learning-based system for the automatic classification of abrasion foot sores (AFS) and ischemic diabetic foot sores (DFS). We proposed a novel model combining convolutional neural network (CNN) capabilities with Vgg-19. The proposed method utilized two benchmark datasets to classify AFS and DFS from the patient’s foot. A data augmentation technique was used to enhance the accuracy of the training. Moreover, image segmentation was performed using UNet++. We tested and evaluated the proposed model’s classification performance against two well-known pre-trained classifiers, Inceptionv3 and MobileNet. The proposed model classified AFS and ischemia DFS images with an accuracy of 99.05%, precision of 98.99%, recall of 99.01%, MCC of 0.9801, and f1 score of 99.04%. Furthermore, the results of statistical evaluations using ANOVA and Friedman tests revealed that the proposed model exhibited a remarkable performance. The proposed model achieved an excellent performance that assist medical professionals in identifying foot ulcers.

Old and Novel Predictors for Cardiovascular Risk in Diabetic Foot Syndrome—A Narrative Review

Diabetic foot syndrome (DFS) is a complication associated with diabetes that has a strong negative impact, both medically and socio-economically. Recent epidemiological data show that one in six patients with diabetes will develop an ulcer in their lifetime. Vascular complications associated with diabetic foot have multiple prognostic implications in addition to limiting functional status and leading to decreased quality of life for these patients. We searched the electronic databases of PubMed, MEDLINE and EMBASE for studies that evaluated the role of DFS as a cardiovascular risk factor through the pathophysiological mechanisms involved, in particular the inflammatory ones and the associated metabolic changes. In the era of evidence-based medicine, the management of these cases in multidisciplinary teams of “cardio-diabetologists” prevents the occurrence of long-term disabling complications and has prognostic value for cardiovascular morbidity and mortality among diabetic patients. Identifying artificial-intelligence-based cardiovascular risk prediction models or conducting extensive clinical trials on gene therapy or potential therapeutic targets promoted by in vitro studies represent future research directions with a modulating role on the risk of morbidity and mortality in patients with DFS.

Graded stiffness offloading insoles better redistribute heel plantar pressure to protect the diabetic neuropathic foot

BACKGROUND

Diabetic heel ulceration is a common, detrimental, and costly complication of diabetes. This study investigates a novel "graded-stiffness" offloading method, which consists of a heel support with increasing levels of stiffness materials to better redistribute plantar pressure for heel ulcer prevention and treatment.

RESEARCH QUESTION

Is the novel "graded-stiffness" solution better able to redistribute heel pressure and reduce focal stress concentration areas of the heel?

METHODS

Twenty healthy young men walked with four, 3D-printed, insole configurations. The configurations included the "graded-stiffness" insoles with and without an offloading hole under the heel tissue at risk for ulcerations and two conventional offloading supports of flat insoles with no offloading and simple holed offloading insoles. In-shoe plantar pressure was measured using the Pedar-X system. Peak pressure and pressure dose were measured at three heel regions: offloaded region, perimeter of offloaded region, and periphery region.

RESULTS

The simple offloading configuration reduced pressure at the offloaded region; however, pressure at the perimeter of the offloading region significantly increased. With respect to ANOVA, the "graded-stiffness" offloading configurations were more effective than existing tested solutions in reducing and redistributing heel peak pressure and pressure dose, considering all heel regions.

SIGNIFICANCE

The "graded-stiffness" offloading solution demonstrated a novel flexible and customized solution that can be manufactured on-demand through a precise selection of the graded-stiffness offloading location and material properties to fit the shape and size of the ulcer. This study is a follow-up in-vivo pilot study, in a healthy population group, to our previous computation modeling work that reported the efficiency of the "graded-stiffness" configuration, and which emphasizes its potential for streamlining and optimizing the prevention and treatment of diabetic heel ulcers.

One-stage and lightweight CNN detection approach with attention: Application to WBC detection of microscopic images

White blood cell (WBC) detection in microscopic images is indispensable in medical diagnostics; however, this work, based on manual checking, is time-consuming, labor-intensive, and easily results in errors. Using object detectors for WBCs with deep convolutional neural networks can be regarded as a feasible solution. In this paper, to improve the examination precision and efficiency, a one-stage and lightweight CNN detector with an attention mechanism for detecting microscopic WBC images, and a white blood cell detection vision system are proposed. The method integrates different optimizing strategies to strengthen the feature extraction capability through the combination of an improved residual convolution module, hybrid spatial pyramid pooling module, improved coordinate attention mechanism, efficient intersection over union (EIOU) loss and Mish activation function. Extensive ablation and contrast experiments on the latest public Raabin-WBC dataset verify the effectiveness and robustness of the proposed detector for achieving a better overall detection performance. It is also more efficient than other existing studies for blood cell detection on two additional classic public BCCD and LISC datasets. The novel detection approach is significant and flexible for medical technicians to use for blood cell microscopic examination in clinical practice.