Loading...
25 results
Search Results
Now showing 1 - 10 of 25
- Comparison of machine learning strategies for infrared thermography of skin cancerPublication . Ricardo Vardasca, PhD, ASIS, FRPSObjective: The aim of this work was to explore the potential of infrared thermal imaging as an aiding tool for the diagnosis of skin cancer lesions, using artificial intelligence methods. Methods: Thermal parameters of skin tumours were retrieved from thermograms and used as input features for two machine learning based strategies: ensemble learning and deep learning. Results: The deep learning strategy outperformed the ensemble learning one, showing good predictive performance for the differentiation of melanoma and nevi (Precision=0.9665, Recall=0.9411, f1-score=0.9536, ROC(AUC)=0.9185) and melanoma and non-melanoma skin cancer (Precision=0.9259, Recall=0.8852, f1-score=0.9051, ROC(AUC)=0.901). Conclusion: IRT imaging combined with deep learning techniques is promising for simplifying and accelerating the diagnosis of skin cancer. Significance: Despite ongoing awareness campaigns for skin cancer’ risk factors, its incidence rate has continuously been growing worldwide, becoming a major public health issue. The standard first detection method – dermoscopy –, is largely experience-dependent and mostly used to assess melanocytic lesions. As infrared thermal imaging is an innocuous imaging technique that maps skin surface temperature, which may be associated to pathological states, e.g., tumorous lesions, it could be a potential aiding tool for all skin cancer conditions. The application of artificial intelligence methods to process the collected temperature data can save time and assist health care professionals with low experience levels in the diagnosis task. To the best of our knowledge, this is the first study where a data set of skin cancer thermograms is expanded and used for skin lesion differentiation with a deep learning approach.
- Towards Dynamic Assessment of Healthy Breast Skin Temperature using Infrared ThermographyPublication . Ricardo Vardasca, PhD, ASIS, FRPSBreast skin temperature assessment has been of interest since of the first application of Infrared Thermography in Medicine in 1956. Since it many investigations attempted to appraise the method as a screening tool, although reference data is still lacking and dynamic thermal imaging has proved its value in other clinical applications. It is aim of this research to apply a thermal stimulus to the breasts of 11 healthy participants through thermal conduction and convection to determine, which can be feasible in clinical setup for further research involving breast cancer patients. It was found that the use of a conduction stimuli on the nipple for a 1 minute to be the most adequate method.
- Dynamics of plantar foot temperature after conductive cold provocation in diabetic patients and healthy controlsPublication . Ricardo Vardasca, PhD, ASIS, FRPSCold provocation tests are largely used in clinical and research settings, but conductive cold provocation tests have not been applied in the feet. This study analyses skin temperature dynamics after a conductive cold provocation test in a sample of 30 diabetic patients and 30 healthy controls. The test was easy and practical to apply and induced significant temperature changes immediately after and 5 minutes after the test. Tsk dynamics were similar in both groups. The cooling of the plantar surface was not homogenous with large differences in TSk drops between some regions of interest.
- Discriminating patients with paediatric idiopathic hyperhidrosis from healthy subjects with infrared thermography and machine learning classifiersPublication . Ricardo Vardasca, PhD, ASIS, FRPSIdiopathic hyperhidrosis (IH) is a medical condition characterised by excessive sweating beyond what is physiologically necessary for thermoregulation affecting mainly the axillae and palms. It affects seriously the quality of life of patients and has an incidence at paediatric age of 1.6%. The diagnosis is subjective relying only the the patient claim and physician perception. It is aim of this research to evaluate if dynamic infrared thermography (IRT) along with machine learning classifier on the thermal data are able to discriminate IH paediatric patients from healthy subjects. Using dynamic IRT, through convective provocation, on the views of axillae and palms, it was possible to discriminate IH paediatric patients from healthy subjects using artificial neural networks (ANN) and random forests (RF) in thermal measurements with high accuracy (>99%), the same was not possible only with the thermal data and statistics.
- Towards an Effective Decision Support System for Diabetic Foot Ulcers Diagnostic and Treatment AssessmentPublication . Ricardo Vardasca, PhD, ASIS, FRPS; Martinho, DomingosDiabetes mellitus (DM) is a fast-growing metabolic condition that threatens human population quality of living in the overcoming decades. One of its severe consequences is diabetic foot ulcers (DFU), which affect up to a quarter of the DM patients in their lifetime. This consequence leads to high health costs and significant decrease of the patients’ quality of life and self-esteem. In order to cope with the rising demands of heath resources and shortage in clinical human assets intelligent computational tools are required to aid in the decision where a patient is in an early stage of a DFU development and on the appraisal of a DFU treatment. It is aim of this research to provide a critical overview of the existing decision support systems (DSS) and publicly available research datasets for diabetic foot ulcers early diagnosis and treatment assessment, and thus proposing a new infrastructure system to deal with it overcoming the past attempts. The existing DFU DSS failed in being introduced in clinical practice due to total discrepancy with current daily clinical practice with DFU and the publicly available DM research datasets are shorter in data for feeding a new DSS. This research presents the actual and promising future data required for effective decisions and discloses a proposed architecture for a DSS applicable to DFU early diagnosis and treatment evaluation. Implementing the proposed system will take time but it will definitely contribute to cope with the patient demands, associated cost reduction and promotion of patients care.
- A Review of Carpal Tunnel Syndrome and Its Association with Age, Body Mass Index, Cardiovascular Risk Factors, Hand Dominance, and SexPublication . Ricardo Vardasca, PhD, ASIS, FRPSCarpal tunnel syndrome (CTS) is one of the most common compressive, canalicular neuropathies of the upper extremities, causing hand pain and impaired function. CTS results from compression or injury of the median nerve at the wrist within the confines of the carpal tunnel. Parameters such as age, sex, and body mass index (BMI) could be risk factors for CTS. This research work aimed to review the existing literature regarding the relationship between CTS and possible risk factors, such as age, sex, BMI, dominant hand, abdominal circumference, respiratory rate, blood pressure, and cardiac rate to determine which ones are the most influential, and therefore, take them into account in subsequent applied research in the manufacturing industry. We performed a literature search in the PubMed, EBSCO, and ScienceDirect databases using the following keywords: carpal tunnel syndrome AND (age OR sex OR BMI OR handedness OR abdominal circumference OR respiratory rate OR blood pressure OR cardiac rate). We chose 72 articles by analyzing the literature found based on selection criteria. We concluded that CTS is associated with age, female sex, and high BMI. Trends and future challenges have been proposed to delve into the relationship between risk factors and CTS, such as correlation studies on pain reduction, analysis of weight changes to predict the severity of this pathology, and its influence on clinical treatments.
- Bilateral comparison of forearm skin temperature during handgrip force exercisePublication . Ricardo Vardasca, PhD, ASIS, FRPSHandgrip force (HGF) test has been used to provide important occupational health information about subject’s nutritional and physiological condition. Handgrip force (average and maximum) and exercise accumulated work can be measured using a dynamometer connected to a computer, other physiological energy spent in the HGF test can be obtained with infrared thermal (IRT) imaging at the anterior forearm region. A protocol has been developed combining both measurements, showing correlations between the measured values and the degrees of similarity between bilateral limbs was assessed, varying at maximum of 1.6 ºC in the considered thermal regions of interest of the forearm. The obtained results on 13 subjects at three different endurance HGF tests showed that the procedure is reproducible and can be applied in both limbs for physiological assessments in occupational, rehabilitation or geriatric contexts.
- Infrared Thermal Imaging: A dataset definition towards decision making and intelligencePublication . Ricardo Vardasca, PhD, ASIS, FRPS; Bento, Fernando; TERESO, MARCO; Martinho, DomingosInfrared imaging is being used every day for monitoring and diagnostic purposes, although it is poorly documented, which can be a major barrier for intelligence creation from the data collected. This research looked deeper into reference recent literature to find the different sources of data related to an IR examination. It was found that exam, image, object of interest, environmental and equipment data are required for a comprehensive dataset. This dataset will enforce quality assurance and drive decision making through being the basis for intelligence generation.
- COMPARISON OF MACHINE LEARNING TECHNIQUES FOR INDIRECT ASSESSMENT METHODS OF BODY CORE TEMPERATUREPublication . Ricardo Vardasca, PhD, ASIS, FRPSPandemic conditions are once again in great prominence with the recent situation caused by COVID-19, some of these conditions present feverish states that can be de tected by means of mass screening at places of great influx of people. There are available different indirect methods to estimate human body core temperature. Being a febrile state considered of a body core temperature higher than 37.5 ºC. This value may differ according to the indirect method used, which can make it difficult to identify febrile cases close to the threshold value, for assisting in this task advanced Artificial Intelligence tools such as Machine Learning (ML) algorithms may be an important aid. The aim of this research is to evaluate which ML technique has the best performance with a certain indirect method of as sessing body temperature, considering the reference pro vided by another method.
- Meta-Analysis and Systematic Review of the Application of Machine Learning Classifiers in Biomedical Applications of Infrared ThermographyPublication . Ricardo Vardasca, PhD, ASIS, FRPSAtypical body temperature values can be an indication of abnormal physiological processes associated with several health conditions. Infrared thermal (IRT) imaging is an innocuous imaging modality capable of capturing the natural thermal radiation emitted by the skin surface, which is connected to physiology-related pathological states. The implementation of artificial intelligence (AI) methods for interpretation of thermal data can be an interesting solution to supply a second opinion to physicians in a diagnostic/therapeutic assessment scenario. The aim of this work was to perform a systematic review and meta-analysis concerning different biomedical thermal applications in conjunction with machine learning strategies. The bibliographic search yielded 68 records for a qualitative synthesis and 34 for quantitative analysis. The results show potential for the implementation of IRT imaging with AI, but more work is needed to retrieve significant features and improve classification metrics.
- «
- 1 (current)
- 2
- 3
- »