Automatic analysis of the trunk thermal images from healthy subjects and patients with faulty posture. (1st July 2015)

• Record Type: Journal Article
• Authors: Koprowski, Robert
• Is Part Of: Computers in biology and medicine. Volume 62(2015)
• Page Start: 110
• Page End: 118
• Publication Date: 2015-07-01
• Subjects: Algorithms -- Classification -- Decision trees -- Image processing -- Measurement automation -- Neural networks -- Spine -- SVM -- Thermovision -- THV; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2015.04.017
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Background: This paper presents an automatic method for assessing temperature distribution on the patient׳s back using thermal imaging. It discusses the advantages and disadvantages of thermal imaging and presents an algorithm for image analysis and processing that runs automatically and reproducibly. Method: The proposed new method of image analysis relates to automatic and reproducible analysis of temperature distribution on the patient׳s back. It includes the following steps: (1) detection of the external contours of the human body, (2) identification and recognition of the position of the arms, hips and shoulders, (3) application of a mesh having a fixed number of fields (which automatically adapts to the size of the patient׳s back), (4) analysis of the paraspinal muscles. These steps are preceded by image pre-processing. Results: Based on a thermal image, this new fully automated algorithm enables to: (1) evaluate temperature distribution in the paraspinal area; (2) pre-assess the degree of lateral spinal curvature in screening, and (3) evaluate anomalies (deviations from the norm) in temperature distribution. The algorithm was practically implemented in Matlab Image Processing Toolbox.