Problems of Active Dynamic Thermography Measurement Standardization in Medicine

Reliability of thermographic diagnostics in medicine is an important practical problem. In the field of static thermography, a great deal of effort has been made to define the conditions for thermographic measurements, which is now the golden standard for such research. In recent years, there are more and more reports on dynamic tests with external stimulation, such as Active Dynamic Thermography, Thermographic Signal Reconstruction or Thermal Tomography. The subject of this report is a discussion of the problems of standardization of dynamic tests, the choice of the method of thermal stimulation and the conditions determining the credibility of such tests in medical diagnostics. Typical methods of thermal stimulation are discussed, problems concerning accuracy and control of resulting distributions of temperature are commented. The best practices to get reliable conditions of measurements are summarized.

SPAER: Sparse Deep Convolutional Autoencoder Model to Extract Low Dimensional Imaging Biomarkers for Early Detection of Breast Cancer Using Dynamic Thermography

Early diagnosis of breast cancer unequivocally improves the survival rate of patients and is crucial for disease treatment. With the current developments in infrared imaging, breast screening using dynamic thermography seems to be a great complementary method for clinical breast examination (CBE) prior to mammography. In this study, we propose a sparse deep convolutional autoencoder model named SPAER to extract low-dimensional deep thermomics to aid breast cancer diagnosis. The model receives multichannel, low-rank, approximated thermal bases as input images. SPAER provides a solution for high-dimensional deep learning features and selects the predominant basis matrix using matrix factorization techniques. The model has been evaluated using five state-of-the-art matrix factorization methods and 208 thermal breast cancer screening cases. The best accuracy was for non-negative matrix factorization (NMF)-SPAER + Clinical and NMF-SPAER for maintaining thermal heterogeneity, leading to finding symptomatic cases with accuracies of 78.2% (74.3–82.5%) and 77.7% (70.9–82.1%), respectively. SPAER showed significant robustness when tested for additive Gaussian noise cases (3–20% noise), evaluated by the signal-to-noise ratio (SNR). The results suggest high performance of SPAER for preserveing thermal heterogeneity, and it can be used as a noninvasive in vivo tool aiding CBE in the early detection of breast cancer.

Thermography in the diagnosis of carpal tunnel syndrome

Introduction Carpal tunnel syndrome (CTS) is a condition caused by chronic compression of the median nerve. The diagnosis is made mainly on the basis of clinical image and confirmed with electrodiagnostic testing (electromyography and nerve conduction study); however, these methods do not always aid in reaching the diagnosis of CTS. Moreover, they are invasive examinations, unpleasant for the patient and have to be performed by a qualified physician. Aim An evaluation of the usefulness of dynamic thermography in the diagnosis of CTS. Material and methods Forty patients were included in the study group. CTS was diagnosed based on clinical examination and electromyography. Forty healthy volunteers were included in the control group. Each of the participants was examined thrice with dynamic thermography. The patient’s hands were first cooled down and then a thermal camera measured their return to normal temperature. The measurement was repeated on the dorsal and volar aspects of each hand. Results The results obtained in the study show that a relief of symptoms after carpal tunnel release does not correlate with thermal image. Moreover, the return to normal hand temperature was faster in the control group. In patients with unilateral CTS, no difference was observed in thermographic images of the affected and healthy hands. Conclusions Dynamic thermography can be useful in confirming CTS diagnosis. Dynamic thermography does not allow for objective assessment of patient’s complaints in the postoperative period. This method has currently limited clinical application. Due to complexity, it presently serves mainly scientific purposes.

Связь механических свойств анизотропных материалов с их теплофизическими характеристиками на примере древесины сосны

The paper discusses experimentally found relation between mechanical an thermal physical properties of anisotropic materials observed at the pine wood (Pínus sylvéstris L). Hardness and main components of temperature diffusivity tensor measured at the normal to the fibers, tangential and radial faces of the pine wood sample having various moisture content can be linked with linear relations. It renders possible to make express estimation of anisotropic materials mechanical properties typically requiring labor and material extensive destructive testing by means of measurement of its thermal properties using dynamic thermography.

A Computational Method to Assist the Diagnosis of Breast Disease Using Dynamic Thermography

Breast cancer has been the second leading cause of cancer death among women. New techniques to enhance early diagnosis are very important to improve cure rates. This paper proposes and evaluates an image analysis method to automatically detect patients with breast benign and malignant changes (tumors). Such method explores the difference of Dynamic Infrared Thermography (DIT) patterns observed in patients’ skin. After obtaining the sequential DIT images of each patient, their temperature arrays are computed and new images in gray scale are generated. Then the regions of interest (ROIs) of those images are segmented and, from them, arrays of the ROI temperature are computed. Features are extracted from the arrays, such as the ones based on statistical, clustering, histogram comparison, fractal geometry, diversity indices and spatial statistics. Time series that are broken down into subsets of different cardinalities are generated from such features. Automatic feature selection methods are applied and used in the Support Vector Machine (SVM) classifier. In our tests, using a dataset of 68 images, 100% accuracy was achieved.