Artificial Intelligence In Ir Thermal Imaging And Sensing For Medical

Bonisiwe Shabane

-Dec 28, 2025, 1:42 AM

Nowakowski, A.Z.; Kaczmarek, M. Artificial Intelligence in IR Thermal Imaging and Sensing for Medical Applications. Sensors 2025, 25, 891. https://doi.org/10.3390/s25030891 Nowakowski AZ, Kaczmarek M. Artificial Intelligence in IR Thermal Imaging and Sensing for Medical Applications.

Sensors. 2025; 25(3):891. https://doi.org/10.3390/s25030891 Nowakowski, Antoni Z., and Mariusz Kaczmarek. 2025. "Artificial Intelligence in IR Thermal Imaging and Sensing for Medical Applications" Sensors 25, no.

3: 891. https://doi.org/10.3390/s25030891 Nowakowski, A. Z., & Kaczmarek, M. (2025). Artificial Intelligence in IR Thermal Imaging and Sensing for Medical Applications.

Sensors, 25(3), 891. https://doi.org/10.3390/s25030891 A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions. This report analyzes recent advancements in infrared (IR) thermal imaging, focusing on the integration of artificial intelligence (AI) and machine learning (ML) for enhanced medical diagnostics. We explore the evolution of thermal imaging technology, its applications in disease detection (e.g., breast cancer, diabetic foot ulcers), and the transformative impact of AI on image quality, data analysis, and diagnostic accuracy.

Key challenges and future directions for enterprise adoption are also discussed. AI-powered thermal imaging offers non-invasive, cost-effective diagnostics with significant potential to improve early detection and patient outcomes. Implementing these advanced solutions requires strategic foresight in data management, regulatory compliance, and workforce integration. Select a topic to dive deeper, then explore the specific findings from the research, rebuilt as interactive, enterprise-focused modules. This section summarizes the historical and technological advancements in infrared (IR) thermal imaging for medical applications from 1960 to 2020. Key innovations include the transition from single-element scanning cameras to real-time focal plane arrays (FPAs), significant improvements in detector technologies (InSb, HgCdTe, microbolometers), and the integration of digital processing and software.

The evolution led to smaller, lighter, more sensitive, and cost-effective cameras, paving the way for wider adoption in diagnostics. Recent advancements include multimodality and multispectral systems, with AI tools now integrated for enhanced image quality and diagnostic analysis. The adoption of Artificial Intelligence (AI) and Machine Learning (ML) has revolutionized thermal diagnostics, addressing limitations like low signal-to-noise ratio and blurred edges. Deep Learning (DL), particularly Convolutional Neural Networks (CNNs), excels in feature extraction, pattern recognition, and image segmentation for medical thermograms. Specific applications include breast cancer detection (with CNNs like ResNet, DenseNet achieving >90% sensitivity), diabetic foot screening, and fever detection (COVID-19). AI enhances image quality through denoising, super-resolution, and artifact removal.

Challenges include data scarcity, lack of standardization, and regulatory hurdles, but federated learning offers a privacy-preserving solution for collaborative model training across institutions. Infrared thermography (IRT), also known as thermal imaging, is a measurement and imaging technique in which a thermal camera detects infrared radiation originating from the surface of objects. This radiation has two main components: thermal emission from the object's surface, which depends on its temperature and emissivity, and reflected radiation from surrounding sources. When the object is not (fully) opaque, i.e. exhibits nonzero transmissivity at the cameras operating wavelengths, transmitted radiation also contributes to the observed signal. The result is a visible image called a thermogram.

Thermal cameras most commonly operate in the long-wave infrared (LWIR) range (7–14 μm); less frequently, systems designed for the mid-wave infrared (MWIR) range (3–5 μm) are used. Since infrared radiation is emitted by all objects with a temperature above absolute zero according to the black body radiation law, thermography makes it possible to see one's environment with or without visible illumination. The amount of radiation emitted by an object increases with temperature, and thermography allows one to see variations in temperature. When viewed through a thermal imaging camera, warm objects stand out well against cooler backgrounds. For example, humans and other warm-blooded animals become easily visible against their environment in day or night. As a result, thermography is particularly useful to the military and other users of surveillance cameras.

Some physiological changes in human beings and other warm-blooded animals can also be monitored with thermal imaging during clinical diagnostics. Thermography is used in allergy detection and veterinary medicine. Some alternative medicine practitioners promote its use for breast screening, despite the FDA warning that "those who opt for this method instead of mammography may miss the chance to detect cancer at its earliest... Thermography has a long history, although its use has increased dramatically with the commercial and industrial applications of the past 50 years. Firefighters use thermography to see through smoke, to find persons, and to locate the base of a fire. Maintenance technicians use thermography to locate overheating joints and sections of power lines, which are a sign of impending failure.

Building construction technicians can see thermal signatures that indicate heat leaks in faulty thermal insulation, improving the efficiency of heating and air-conditioning units. The appearance and operation of a modern thermographic camera is often similar to a camcorder. Often the live thermogram reveals temperature variations so clearly that a photograph is not necessary for analysis. A recording module is therefore not always built-in. This special issue belongs to the section “AI in Imaging“. Infrared (IR) imaging has become an indispensable tool in a wide range of domains, including surveillance, remote sensing, medical diagnostics, autonomous driving, industrial inspection, and environmental monitoring.

Unlike visible-spectrum imaging, infrared captures thermal radiation, offering unique advantages in low-light and obscured environments. However, IR image processing poses distinct challenges, such as low contrast, limited texture, noise, and variability in environmental conditions. Recent advances in artificial intelligence (AI)—particularly deep learning—have led to significant breakthroughs in addressing these challenges. AI-powered methods now play a crucial role in tasks such as image enhancement, object detection and tracking, semantic segmentation, anomaly detection, and multimodal fusion involving IR data. Despite these advances, the field continues to face various obstacles, including limited labeled data, high domain variability, a lack of generalization, and the need for interpretable and energy-efficient models. This Special Issue aims to compile state-of-the-art research at the intersection of AI and infrared image processing.

We welcome the submission of original contributions that explore novel algorithms, datasets, applications, and theoretical frameworks. Both supervised and unsupervised learning paradigms, multimodal approaches, and cross-domain adaptation methods are welcome. The scope of this Special Issue includes, but is not limited to, the following topics:

People Also Search

Nowakowski, A.Z.; Kaczmarek, M. Artificial Intelligence In IR Thermal Imaging

Sensors. 2025; 25(3):891. Https://doi.org/10.3390/s25030891 Nowakowski, Antoni Z., And Mariusz Kaczmarek.

3: 891. Https://doi.org/10.3390/s25030891 Nowakowski, A. Z., & Kaczmarek, M. (2025).