Comparison of machine learning strategies for infrared thermography of skin cancer

Cutaneous Imaging Techniques

Cutaneous imaging is a central tenant to the practice of dermatology. In this article, the authors explore various noninvasive and invasive skin imaging techniques, as well as the latest deployment of these technologies in conjunction with the use artificial intelligence and machine learning. The authors also provide insight into the benefits, limitations, and challenges around integrating these technologies into dermatologic practice.

Artificial intelligence for nonmelanoma skin cancer

Nonmelanoma skin cancers (NMSCs) are among the top five most common cancers globally. NMSC is an area with great potential for novel application of diagnostic tools including artificial intelligence (AI). In this scoping review, we aimed to describe the applications of AI in the diagnosis and treatment of NMSC. Twenty-nine publications described AI applications to dermatopathology including lesion classification and margin assessment. Twenty-five publications discussed AI use in clinical image analysis, showing that algorithms are not superior to dermatologists and may rely on unbalanced, nonrepresentative, and nontransparent training data sets. Sixteen publications described the use of AI in cutaneous surgery for NMSC including use in margin assessment during excisions and Mohs surgery, as well as predicting procedural complexity. Eleven publications discussed spectroscopy, confocal microscopy, thermography, and the AI algorithms that analyze and interpret their data. Ten publications pertained to AI applications for the discovery and use of NMSC biomarkers. Eight publications discussed the use of smartphones and AI, specifically how they enable clinicians and patients to have increased access to instant dermatologic assessments but with varying accuracies. Five publications discussed large language models and NMSC, including how they may facilitate or hinder patient education and medical decision-making. Three publications pertaining to the skin of color and AI for NMSC discussed concerns regarding limited diverse data sets for the training of convolutional neural networks. AI demonstrates tremendous potential to improve diagnosis, patient and clinician education, and management of NMSC. Despite excitement regarding AI, data sets are often not transparently reported, may include low-quality images, and may not include diverse skin types, limiting generalizability. AI may serve as a tool to increase access to dermatology services for patients in rural areas and save health care dollars. These benefits can only be achieved, however, with consideration of potential ethical costs.

Beyond visual inspection: The value of infrared thermography in skin diseases, a scoping review

Although warmth is a key sign of inflammatory skin lesions, an objective assessment and follow-up of the temperature changes are rarely done in dermatology. The recent availability of accurate, sensitive and cost-effective thermography devices has made the implementation of thermography in clinical settings feasible. The aim of this scoping review is to summarize the evidence around the value and pitfalls of infrared thermography (IRT) when used in the dermatology clinic. A systematic literature search was done for original articles using IRT in skin disorders. The results concerning the potential of IRT for diagnosis, severity staging and monitoring of skin diseases were collected. The data on the sensitivity and specificity of IRT were extracted. Numerous studies have investigated IRT in various skin diseases, revealing its significant value in wound management, skin infections (e.g. cellulitis), vascular abnormalities and deep skin inflammation (e.g. hidradenitis suppurativa). For other dermatological applications such as the interpretation of intradermal and patch allergy testing, hyper-/anhidrosis, erythromelalgia, cold urticaria and lymph node metastases more complex calculations, provocation tests or active cooling procedures are required. Dermatologists should be aware of a learning curve of IRT and recognize factors contributing to false positive and false negative results. Nonetheless, enough evidence is available to recommend IRT as a supplement to the clinical evaluation for the diagnosis, severity and follow-up of several skin diseases.

Feasibility Study on the Use of Infrared Cameras for Skin Cancer Detection under a Proposed Data Degradation Model

Infrared thermography is considered a useful technique for diagnosing several skin pathologies but it has not been widely adopted mainly due to its high cost. Here, we investigate the feasibility of using low-cost infrared cameras with microbolometer technology for detecting skin cancer. For this purpose, we collected infrared data from volunteer subjects using a high-cost/high-quality infrared camera. We propose a degradation model to assess the use of lower-cost imagers in such a task. The degradation model was validated by mimicking video acquisition with the low-cost cameras, using data originally captured with a medium-cost camera. The outcome of the proposed model was then compared with the infrared video obtained with actual cameras, achieving an average Pearson correlation coefficient of more than 0.9271. Therefore, the model successfully transfers the behavior of cameras with poorer characteristics to videos acquired with higher-quality cameras. Using the proposed model, we simulated the acquisition of patient data with three different lower-cost cameras, namely, Xenics Gobi-640, Opgal Therm-App, and Seek Thermal CompactPRO. The degraded data were used to evaluate the performance of a skin cancer detection algorithm. The Xenics and Opgal cameras achieved accuracies of 84.33% and 84.20%, respectively, and sensitivities of 83.03% and 83.23%, respectively. These values closely matched those from the non-degraded data, indicating that employing these lower-cost cameras is appropriate for skin cancer detection. The Seek camera achieved an accuracy of 82.13% and a sensitivity of 79.77%. Based on these results, we conclude that this camera is appropriate for less critical applications.

Is thermography an effective screening tool for differentiating benign and malignant skin lesions in the head and neck? A systematic review

The aim of this study was to assess, through a systematic review, the status of infrared thermography (IRT) as a diagnostic tool for skin neoplasms of the head and neck region and in order to validate its effectiveness in differentiating benign and malignant lesions. A search was carried out in the LILACS, PubMed/MEDLINE, SCOPUS, Web of Science and EMBASE databases including studies published between 2004 and 2024, written in the Latin-Roman alphabet. Accuracy studies with patients aged 18 years or over presenting benign and malignant lesions in the head and neck region that evaluated the performance of IRT in differentiating these lesions were included. Lesions of mesenchymal origin and studies that did not mention histopathological diagnosis were excluded. The systematic review protocol was registered in the PROSPERO database (CRD42023416079). Reviewers independently analyzed titles, abstracts, and full-texts. After extracting data, the risk of bias of the selected studies was assessed using the QUADAS - 2 tool. Results were narratively synthesized and the certainty of evidence was measured using the GRADE approach. The search resulted in 1,587 records and three studies were included. Only one of the assessed studies used static IRT, while the other two studies used cold thermal stress. All studies had an uncertain risk of bias. In general, studies have shown wide variation in the accuracy of IRT for differentiating between malignant and benign lesions, with a low level of certainty in the evidence for both specificity and sensitivity.

Review of the application of the most current sophisticated image processing methods for the skin cancer diagnostics purposes

This paper presents the most current and innovative solutions applying modern digital image processing methods for the purpose of skin cancer diagnostics. Skin cancer is one of the most common types of cancers. It is said that in the USA only, one in five people will develop skin cancer and this trend is constantly increasing. Implementation of new, non-invasive methods plays a crucial role in both identification and prevention of skin cancer occurrence. Early diagnosis and treatment are needed in order to decrease the number of deaths due to this disease. This paper also contains some information regarding the most common skin cancer types, mortality and epidemiological data for Poland, Europe, Canada and the USA. It also covers the most efficient and modern image recognition methods based on the artificial intelligence applied currently for diagnostics purposes. In this work, both professional, sophisticated as well as inexpensive solutions were presented. This paper is a review paper and covers the period of 2017 and 2022 when it comes to solutions and statistics. The authors decided to focus on the latest data, mostly due to the rapid technology development and increased number of new methods, which positively affects diagnosis and prognosis.

Privacy-Aware Collaborative Learning for Skin Cancer Prediction

Cancer, including the highly dangerous melanoma, is marked by uncontrolled cell growth and the possibility of spreading to other parts of the body. However, the conventional approach to machine learning relies on centralized training data, posing challenges for data privacy in healthcare systems driven by artificial intelligence. The collection of data from diverse sensors leads to increased computing costs, while privacy restrictions make it challenging to employ traditional machine learning methods. Researchers are currently confronted with the formidable task of developing a skin cancer prediction technique that takes privacy concerns into account while simultaneously improving accuracy. In this work, we aimed to propose a decentralized privacy-aware learning mechanism to accurately predict melanoma skin cancer. In this research we analyzed federated learning from the skin cancer database. The results from the study showed that 92% accuracy was achieved by the proposed method, which was higher than baseline algorithms.

Heat-assisted detection and ranging

Machine perception uses advanced sensors to collect information about the surrounding scene for situational awareness^1-7. State-of-the-art machine perception⁸ using active sonar, radar and LiDAR to enhance camera vision⁹ faces difficulties when the number of intelligent agents scales up^10,11. Exploiting omnipresent heat signal could be a new frontier for scalable perception. However, objects and their environment constantly emit and scatter thermal radiation, leading to textureless images famously known as the 'ghosting effect'¹². Thermal vision thus has no specificity limited by information loss, whereas thermal ranging-crucial for navigation-has been elusive even when combined with artificial intelligence (AI)¹³. Here we propose and experimentally demonstrate heat-assisted detection and ranging (HADAR) overcoming this open challenge of ghosting and benchmark it against AI-enhanced thermal sensing. HADAR not only sees texture and depth through the darkness as if it were day but also perceives decluttered physical attributes beyond RGB or thermal vision, paving the way to fully passive and physics-aware machine perception. We develop HADAR estimation theory and address its photonic shot-noise limits depicting information-theoretic bounds to HADAR-based AI performance. HADAR ranging at night beats thermal ranging and shows an accuracy comparable with RGB stereovision in daylight. Our automated HADAR thermography reaches the Cramér-Rao bound on temperature accuracy, beating existing thermography techniques. Our work leads to a disruptive technology that can accelerate the Fourth Industrial Revolution (Industry 4.0)¹⁴ with HADAR-based autonomous navigation and human-robot social interactions.

Real-time monitoring of focused ultrasound therapy using intelligence-based thermography: A feasibility study

Focused ultrasound (FUS) therapy has been widely studied for breast cancer treatment due to its potential as a fully non-invasive method to improve cosmetic and oncologic results. However, real-time imaging and monitoring of the therapeutic ultrasound delivered to the target area remain challenges for precision breast cancer therapy. The main objective of this study is to propose and evaluate a novel intelligence-based thermography (IT) method that can monitor and control FUS treatment using thermal imaging with the fusion of artificial intelligence (AI) and advanced heat transfer modeling. In the proposed method, a thermal camera is integrated into FUS system for thermal imaging of the breast surface, and an AI model is employed for the inverse analysis of the surface thermal monitoring, thereby estimating the features of the focal region. This paper presents experimental and computational studies conducted to assess the feasibility and efficiency of IT-guided FUS (ITgFUS). Tissue phantoms, designed to mimic the properties of breast tissue, were used in the experiments to investigate detectability and the impact of temperature rise at the focal region on the tissue surface. Additionally, an AI computational analysis employing an artificial neural network (ANN) and FUS simulation was carried out to provide a quantitative estimation of the temperature rise at the focal region. This estimation was based on the observed temperature profile on the breast model's surface. The results proved that the effects of temperature rise at the focused area could be detected by the thermal images acquired with thermography. Moreover, it was demonstrated that the AI analysis of the surface temperature measurement could result in near real-time monitoring of FUS by quantitative estimation of the temporal and spatial temperature rise profiles at the focal region.

The risk assessment of arsenic contamination in the urbanized coastal aquifer of Rayong groundwater basin, Thailand using the machine learning approach

The rapid expansion of urbanization has resulted in an insufficient of groundwater resource. In order to use groundwater more efficiently, a risk assessment of groundwater pollution should be proposed. The present study used machine learning with three algorithms consisting of Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN) to locate risk areas of arsenic contamination in Rayong coastal aquifers, Thailand and selected the suitable model based on model performance and uncertainty for risk assessment. The parameters of 653 groundwater wells (Deep=236, Shallow=417) were selected based on the correlation of each hydrochemical parameters with arsenic concentration in deep and shallow aquifer environments. The models were validated with arsenic concentration collected from 27 well data in the field. The model's performance indicated that the RF algorithm has the highest performance as compared to those of SVM and ANN in both deep and shallow aquifers (Deep: AUC=0.72, Recall=0.61, F1 =0.69; Shallow: AUC=0.81, Recall=0.79, F1 =0.68). In addition, the uncertainty from the quantile regression of each model confirmed that the RF algorithm has the lowest uncertainty (Deep: PICP=0.20; Shallow: PICP=0.34). The result of the risk map obtained from the RF reveals that the deep aquifer, in the northern part of the Rayong basin has a higher risk for people to expose to As. In contrast, the shallow aquifer revealed that the southern part of the basin has a higher risk, which is also supported by the location of the landfill and industrial estates in the area. Therefore, health surveillance is important in monitoring the toxic effects on the residents who use groundwater from these contaminated wells. The outcome of this study can help policymakers in regions to manage the quality of groundwater resources and enhance the sustainable use of groundwater resources. The novelty process of this research can be used to further study other groundwater aquifers contaminated and increase the effectiveness of groundwater quality management.

Evaluation of artificial intelligence techniques in disease diagnosis and prediction

A broad range of medical diagnoses is based on analyzing disease images obtained through high-tech digital devices. The application of artificial intelligence (AI) in the assessment of medical images has led to accurate evaluations being performed automatically, which in turn has reduced the workload of physicians, decreased errors and times in diagnosis, and improved performance in the prediction and detection of various diseases. AI techniques based on medical image processing are an essential area of research that uses advanced computer algorithms for prediction, diagnosis, and treatment planning, leading to a remarkable impact on decision-making procedures. Machine Learning (ML) and Deep Learning (DL) as advanced AI techniques are two main subfields applied in the healthcare system to diagnose diseases, discover medication, and identify patient risk factors. The advancement of electronic medical records and big data technologies in recent years has accompanied the success of ML and DL algorithms. ML includes neural networks and fuzzy logic algorithms with various applications in automating forecasting and diagnosis processes. DL algorithm is an ML technique that does not rely on expert feature extraction, unlike classical neural network algorithms. DL algorithms with high-performance calculations give promising results in medical image analysis, such as fusion, segmentation, recording, and classification. Support Vector Machine (SVM) as an ML method and Convolutional Neural Network (CNN) as a DL method is usually the most widely used techniques for analyzing and diagnosing diseases. This review study aims to cover recent AI techniques in diagnosing and predicting numerous diseases such as cancers, heart, lung, skin, genetic, and neural disorders, which perform more precisely compared to specialists without human error. Also, AI's existing challenges and limitations in the medical area are discussed and highlighted.

A Highly Discriminative Hybrid Feature Selection Algorithm for Cancer Diagnosis

Cancer is a deadly disease that occurs due to rapid and uncontrolled cell growth. In this article, a machine learning (ML) algorithm is proposed to diagnose different cancer diseases from big data. The algorithm comprises a two-stage hybrid feature selection. In the first stage, an overall ranker is initiated to combine the results of three filter-based feature evaluation methods, namely, chi-squared, F-statistic, and mutual information (MI). The features are then ordered according to this combination. In the second stage, the modified wrapper-based sequential forward selection is utilized to discover the optimal feature subset, using ML models such as support vector machine (SVM), decision tree (DT), random forest (RF), and K-nearest neighbor (KNN) classifiers. To examine the proposed algorithm, many tests have been carried out on four cancerous microarray datasets, employing in the process 10-fold cross-validation and hyperparameter tuning. The performance of the algorithm is evaluated by calculating the diagnostic accuracy. The results indicate that for the leukemia dataset, both SVM and KNN models register the highest accuracy at 100% using only 5 features. For the ovarian cancer dataset, the SVM model achieves the highest accuracy at 100% using only 6 features. For the small round blue cell tumor (SRBCT) dataset, the SVM model also achieves the highest accuracy at 100% using only 8 features. For the lung cancer dataset, the SVM model also achieves the highest accuracy at 99.57% using 19 features. By comparing with other algorithms, the results obtained from the proposed algorithm are superior in terms of the number of selected features and diagnostic accuracy.

Melanoma Detection Using XGB Classifier Combined with Feature Extraction and K-Means SMOTE Techniques

Melanoma, a very severe form of skin cancer, spreads quickly and has a high mortality rate if not treated early. Recently, machine learning, deep learning, and other related technologies have been successfully applied to computer-aided diagnostic tasks of skin lesions. However, some issues in terms of image feature extraction and imbalanced data need to be addressed. Based on a method for manually annotating image features by dermatologists, we developed a melanoma detection model with four improvement strategies, including applying the transfer learning technique to automatically extract image features, adding gender and age metadata, using an oversampling technique for imbalanced data, and comparing machine learning algorithms. According to the experimental results, the improved strategies proposed in this study have statistically significant performance improvement effects. In particular, our proposed ensemble model can outperform previous related models.

Skin Cancer Detection Using Infrared Thermography: Measurement Setup, Procedure and Equipment

Infrared thermography technology has improved dramatically in recent years and is gaining renewed interest in the medical community for applications in skin tissue identification applications. However, there is still a need for an optimized measurement setup and protocol to obtain the most appropriate images for decision making and further processing. Nowadays, various cooling methods, measurement setups and cameras are used, but a general optimized cooling and measurement protocol has not been defined yet. In this literature review, an overview of different measurement setups, thermal excitation techniques and infrared camera equipment is given. It is possible to improve thermal images of skin lesions by choosing an appropriate cooling method, infrared camera and optimized measurement setup.

The Current State of Optical Sensors in Medical Wearables

Optical sensors play an increasingly important role in the development of medical diagnostic devices. They can be very widely used to measure the physiology of the human body. Optical methods include PPG, radiation, biochemical, and optical fiber sensors. Optical sensors offer excellent metrological properties, immunity to electromagnetic interference, electrical safety, simple miniaturization, the ability to capture volumes of nanometers, and non-invasive examination. In addition, they are cheap and resistant to water and corrosion. The use of optical sensors can bring better methods of continuous diagnostics in the comfort of the home and the development of telemedicine in the 21st century. This article offers a large overview of optical wearable methods and their modern use with an insight into the future years of technology in this field.

Use of infrared thermography in medical diagnostics: a scoping review protocol

INTRODUCTION

Thermography offers a non-invasive radiation-free methodology for diagnostic imaging and temperature measurement, but the extent of the current application is unclear, as is the level of evidence for each use case. Moreover, population-based thermographic reference values for diagnostic purposes are nearly unknown. The aim of this scoping review is to identify patient populations and diseases in which thermography is applied, cataloguing of technical and environmental modalities, investigation of the existence of specific reference data and finally exploration of gaps and future tasks.

METHODS AND ANALYSIS

PubMed, Cochrane Database of Systematic Reviews and CENTRAL, Embase, Web of Science and OpenGrey are to be searched using pretested suitable search strategies, with no language restriction, but abstracts should be available in English or German and articles should not have been published before 2000. This limited time frame is due to the rapid technological progress, which makes it necessary to exclude reports based on outdated technology. The literature found will be selected on the basis of previously defined inclusion and exclusion criteria. Subsequently, relevant data will be extracted from the included references into a predesigned table. The selection and extraction process will be conducted by two researchers independently. The report of the results will be according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews checklist. The entire review process will follow the Joanna Briggs Institute approach. The scoping review protocol is registered at the Open Science Framework.

ETHICS AND DISSEMINATION

Ethical approval is not required for this work, but ethical medicine also obliges us to carefully consider diagnostic alternatives and compare them with current standards. The dissemination of the results will take place in a variety of ways. First and foremost through publication in an open access journal, but also through conference proceedings. In addition, this scoping review will serve to open up new research foci with regard to thermography.

Machine-Learning-Based Disease Diagnosis: A Comprehensive Review

Globally, there is a substantial unmet need to diagnose various diseases effectively. The complexity of the different disease mechanisms and underlying symptoms of the patient population presents massive challenges in developing the early diagnosis tool and effective treatment. Machine learning (ML), an area of artificial intelligence (AI), enables researchers, physicians, and patients to solve some of these issues. Based on relevant research, this review explains how machine learning (ML) is being used to help in the early identification of numerous diseases. Initially, a bibliometric analysis of the publication is carried out using data from the Scopus and Web of Science (WOS) databases. The bibliometric study of 1216 publications was undertaken to determine the most prolific authors, nations, organizations, and most cited articles. The review then summarizes the most recent trends and approaches in machine-learning-based disease diagnosis (MLBDD), considering the following factors: algorithm, disease types, data type, application, and evaluation metrics. Finally, in this paper, we highlight key results and provides insight into future trends and opportunities in the MLBDD area.

Dermatology disease prediction based on firefly optimization of ANFIS classifier

<abstract> <p>The rate of increase in skin cancer incidences has become worrying in recent decades. This is because of constraints like eventual draining of ozone levels, air's defensive channel capacity and progressive arrival of Sun-oriented UV radiation to the Earth's surface. The failure to diagnose skin cancer early is one of the leading causes of death from the disease. Manual detection processes consume more time well as not accurate, so the researchers focus on developing an automated disease classification method. In this paper, an automated skin cancer classification is achieved using an adaptive neuro-fuzzy inference system (ANFIS). A hybrid feature selection technique was developed to choose relevant feature subspace from the dermatology dataset. ANFIS analyses the dataset to give an effective outcome. ANFIS acts as both fuzzy and neural network operations. The input is converted into a fuzzy value using the Gaussian membership function. The optimal set of variables for the Membership Function (MF) is generated with the help of the firefly optimization algorithm (FA). FA is a new and strong meta-heuristic algorithm for solving nonlinear problems. The proposed method is designed and validated in the Python tool. The proposed method gives 99% accuracy and a 0.1% false-positive rate. In addition, the proposed method outcome is compared to other existing methods like improved fuzzy model (IFM), fuzzy model (FM), random forest (RF), and Naive Byes (NB).</p> </abstract>