Automated features analysis of patients with spinal diseases using medical thermal images

Nowadays, the medical infrared thermal imaging (MITI) techniques can provide good quality images in real-time for monitoring and pre-clinical diagnostic of the diseases caused by inflammatory processes by showing the thermal abnormalities present in the body. MITI allows specify of the functional changes in the normal temperature distribution on the surface of the body, as well as enables refinement the localization of functional changes, the activity of the process, its prevalence and the nature of the changes – inflammation, stagnation, malignancy, etc. Due to its non-contact, non-invasive and non-destructive way of using, this technology has a distinct advantage among other diagnostic methods. Therefore, the main objectives of this research work were automated steps of feature extraction and analysis MTIs, i.e. to develop novel algorithm for quantitative interpretation of thermal images database, to improve the experimental protocol of obtaining thermal images and to perform an extensive field measurement in the selected cohort of patients, in our case, with spinal diseases, in order to provide an immediate high-quality solutions in real time clinical validation of the proposed method.

[1]  Reinhard Windhager,et al.  Thermal Imaging as a Noninvasive Diagnostic Tool for Anterior Knee Pain Following Implantation of Artificial Knee Joints , 2011 .

[2]  P. Videira,et al.  Optimization of an Arterialized Venous Fasciocutaneous Flap in the Abdomen of the Rat , 2017, Plastic and reconstructive surgery. Global open.

[3]  S. Rands,et al.  Reporting of thermography parameters in biology: a systematic review of thermal imaging literature , 2018, Royal Society Open Science.

[4]  Julio Molleda,et al.  Infrared Thermography for Temperature Measurement and Non-Destructive Testing , 2014, Sensors.

[5]  N. Bouzida,et al.  Visualization of body thermoregulation by infrared imaging , 2009 .

[6]  Amira S. Ashour,et al.  Thermal Imaging in Medical Science , 2017 .

[7]  B. Venkatraman,et al.  Automated hand thermal image segmentation and feature extraction in the evaluation of rheumatoid arthritis , 2015, Proceedings of the Institution of Mechanical Engineers. Part H, Journal of engineering in medicine.

[8]  P. Lui,et al.  Thermal symmetry of skin temperature: normative data of normal subjects in Taiwan. , 2001, Zhonghua yi xue za zhi = Chinese medical journal; Free China ed.

[9]  Carl F. Pieper,et al.  Patellar Skin Surface Temperature by Thermography Reflects Knee Osteoarthritis Severity , 2010, Clinical medicine insights. Arthritis and musculoskeletal disorders.

[10]  Waldemar Wójcik,et al.  An efficient method for analyzing measurement results on the example of thyroid ultrasound images , 2016 .

[11]  L. Cherkas,et al.  The use of portable radiometry to assess Raynaud's phenomenon: a practical alternative to thermal imaging. , 2001, Rheumatology.

[12]  Huping Ye,et al.  A simple automated dynamic threshold extraction method for the classification of large water bodies from landsat-8 OLI water index images , 2018 .

[13]  Ana R. Farinho,et al.  Reconstruction of a 10-mm-long median nerve gap in an ischemic environment using autologous conduits with different patterns of blood supply: A comparative study in the rat , 2018, PloS one.

[14]  Tim D Spector,et al.  Use of thermographic criteria to identify Raynaud's phenomenon in a population setting. , 2003, The Journal of rheumatology.