Thermography

Women's breasts are susceptible to developing cancer; this is supported by a recent study from 2016 showing that 2.8 million women worldwide had already been diagnosed with breast cancer that year. The medical care of a patient with breast cancer is costly and, given the cost and value of the preservation of the health of the citizen, the prevention of breast cancer has become a priority in public health. Over the past 20 years several techniques have been proposed for this purpose, such as mammography, which is frequently used for breast cancer diagnosis. However, false positives of mammography can occur in which the patient is diagnosed positive by another technique. Additionally, the potential side effects of using mammography may encourage patients and physicians to look for other diagnostic techniques. Our review of the literature first explored infrared digital imaging, which assumes that a basic thermal comparison between a healthy breast and a breast with cancer always shows an increase in thermal activity in the precancerous tissues and the areas surrounding developing breast cancer. Furthermore, through our research, we realized that a Computer-Aided Diagnostic (CAD) undertaken through infrared image processing could not be achieved without a model such as the well-known hemispheric model. The novel contribution of this paper is the production of a comparative study of several breast cancer detection techniques using powerful computer vision techniques and deep learning models.

According to the World Health Organization (WHO), Diabetes Mellitus (DM) is one of the most prevalent diseases in the world. It is also associated with a high mortality index. Diabetic foot is one of its main complications, and it comprises the development of plantar ulcers that could result in an amputation. Several works report that thermography is useful to detect changes in the plantar temperature, which could give rise to a higher risk of ulceration. However, the plantar temperature distribution does not follow a particular pattern in diabetic patients, thereby making it difficult to measure the changes. Thus, there is an interest in improving the success of the analysis and classification methods that help to detect abnormal changes in the plantar temperature. All this leads to the use of computer-aided systems, such as those involved in artificial intelligence (AI), which operate with highly complex data structures. This paper compares machine learning-based techniques with Deep Learning (DL) structures. We tested common structures in the mode of transfer learning, including AlexNet and GoogleNet. Moreover, we designed a new DL-structure, which is trained from scratch and is able to reach higher values in terms of accuracy and other quality measures. The main goal of this work is to analyze the use of AI and DL for the classification of diabetic foot thermograms, highlighting their advantages and limitations. To the best of our knowledge, this is the first proposal of DL networks applied to the classification of diabetic foot thermograms. The experiments are conducted over thermograms of DM and control groups. After that, a multi-level classification is performed based on a previously reported thermal change index. The high accuracy obtained shows the usefulness of AI and DL as auxiliary tools to aid during the medical diagnosis.

BackgroundThe measurement of body temperature has become commonplace in the current COVID-19 pandemic. Body temperature can be measured using thermal infrared imaging, a safe, non-contact method that relies on the emissivity of the skin being known to provide accurate readings. Skin pigmentation affects the absorption of visible light and enables us to see variations in skin colour. Pigmentation may also affect the absorption of infrared radiation and thus affect thermal imaging. Human skin has an accepted emissivity of 0.98 but the effect of different skin pigmentation on this value is not known. In this study, we investigated the influence of different skin pigmentation on thermal emissivity in 65 adult volunteers.MethodsA reference object of known emissivity (electrical tape) was applied to participant's skin on the inner upper arm. Tape and arm were imaged simultaneously using a thermal infrared camera. The emissivity was set on the camera to the known value for electrical tape. The emissivity was altered manually until the skin temperature using thermal imaging software was equal to the initial tape temperature. This provided the calculated emissivity value of the skin. Participants were grouped according to skin pigmentation, quantified using the Fitzpatrick skin phototyping scale and reflectance spectrophotometry. Differences in emissivity values between skin pigmentation groups were assessed by one-way ANOVA.ResultsThe mean calculated emissivity for the 65 participants was 0.972 (range 0.96-0.99). No significant differences in emissivity were observed between participants when grouped by skin pigmentation according to the Fitzpatrick scale (p = 0.859) or reflectance spectrophotometry (p = 0.346).ConclusionThese data suggest that skin pigmentation does not affect thermal emissivity measurement of skin temperature using thermal infrared imaging. This study will aid further research into the application of thermal infrared imaging as a screening or bedside diagnostic tool in clinical practice.

Monitoring the activity of the autonomic nervous system, including the sympathetic and parasympathetic divisions, plays a crucial role in studying emotional processing. However, few methods allow the dynamic tracking of parasympathetic activity. Here, we propose a testable hypothesis that ear thermography may serve as a dynamic index of sympathetic and parasympathetic activity, with a time resolution of seconds. Anatomical and physiological evidence suggests that the vascular structures of the ear may be innervated in a region-specific manner by the autonomic nervous system, with the posterior regions (e.g., the helix) predominantly influenced by sympathetic activity and the anterior regions (e.g., the tragus) potentially affected by parasympathetic mechanisms. Recent thermographic studies during emotional film viewing have demonstrated distinct spatial and functional patterns: posterior regions showed a linear negative association between temperature and emotional arousal, consistent with sympathetic vasoconstriction, whereas anterior regions exhibited a non-linear (inverted-U-shaped) relationship, resembling the known non-monotonic characteristics of parasympathetic activity. These findings suggest that ear thermography may be used to assess sympathetic- and parasympathetic-related dynamic processes, although direct evidence remains to be established.