Classification and Decision Making of Medical Infrared Thermal Images

Abstract

Medical Infrared Thermal Imaging (MITI) is a technique that allows to record skin surface temperature distribution, in a completely safe and innocuous manner. These images provide underlining physiological in-formation on the blood flow, vasoconstriction/vasodilatation, inflammation, transpiration or other processes that can contribute to the skin temperature. This medical imaging modality has been available for nearly six decades and proved to be useful for vascular, neurological and musculoskeletal conditions. Since the recordings are digital, in a form of a matrix of numbers (image), it can be computationally analyzed, by a specialist mostly performing operations of processing and analysis manually supported by proprietary solutions of software. This limits the number of images that can be processed, making difficult the evolution of knowledge, expertise development and information sharing. This chapter aims to disclose the medical imaging method, along with its particularities, principles, applications, advantages and disadvantages. Introducing all available classification and decision making methods that can be employed in digital information along with a literature review of their operation in the biomedical applications of Infrared Thermal Imaging.

Intelligent Thermal Imaging-Based Diagnostics of Turbojet Engines

“…The environment in the laboratory had a relatively stable humidity (around 50%) and temperature (around 21 • C) during the experiments with no direct sunlight. These parameters can have an impact on the precision of the IRT measurements, but can be quite well-controlled in a laboratory environment [39]. The measured state parameters (n (rpm), T 2 ( • C), T 3 ( • C), T 4 ( • C)) for a single run of the iSTC-21v engine in laboratory conditions are shown in Figure 12.…”

“…However, the most successful methodologies for image classification come from the area of computational intelligence. These include artificial neural networks, which have been widely and successfully applied in image processing, pattern recognition, and diagnostic tasks [38,39]. The most complex neural networks, such as convolutional neural networks, are able to classify any pattern in an image with high precision, as well as detect objects [40].…”

Performance evaluation of two optical architectures for task-specific compressive classification

“…Classification of images is an active area of research for fields such as self-driving cars, 1,2 facial recognition, 3 medical imaging, 4,5 and remote sensing. 6,7 High-resolution data optimized for human observers is commonly passed into a machine learning algorithm that processes the data and returns a classification decision.…”

Discriminating patients with paediatric idiopathic hyperhidrosis from healthy subjects with infrared thermography and machine learning classifiers

“…Dynamic IRT has showed to provide more physiological information about autonomous nervous system than static IRT [5]. The usage of machine learning classifiers also demonstrated to improve the usage of the data provided by this imaging technique [6,7].…”