Infrared Imaging

Musculoskeletal Radiology using Infrared Imaging

Overview of Research in Arthritis related Inflammation Detection:

Infrared Thermography in Arthritis related Inflammation Detection

Arthritis is a auto-immune diseases that kills normal cells of the joint. Inflammation is an indicator of the diseases progression. High inflammation implies that the diseases is in severe condition therefore physician first attempt to decrease inflammation. Inflammation is an important factor in arthritis. In arthritis a progressive destruction of the joints has occurred and an inflammation also produced because of this destruction. Therefore, the inflammation considered as an effective sign of activity of arthritis. Mild inflammation tells that the disease activity is under control or it indicates the presence of the disease. Severe inflammation referred to urgent medical attention. Clinicians depend upon the subjective measures to determine the inflammation. Tenderness of effected joint, pain, swelling of the joint, restriction of movement of the joint and the surface temperature of the joint. Clinicians usually use their hand to determine the temperature of the joint skin surface. Based on these clinicians confirmed the presence of inflammation and as well as the diseases activity. In this scenario, thermal imaging able to help the clinicians in determining the inflammation as thermal imaging is able to detect the temperature profile of the joints. Joints having inflammation elevate their surface temperature which is detectable by thermal imaging. Therefore, thermal imaging can be used as an additive tool that help the clinicians to detect the inflammation of the joint.

Figure 1: Thermogram of an OA patient

Designing of Pain Thermogram Image Dataset:

Thermal imaging is not only different from visual imaging, the capturing of thermal imaging is also different from the former. Thermal imaging is sensible to the temperature of the object surroundings. Thermal imaging captures the relative temperature of an object. Therefore, object environment able to influence the outcome of the thermal camera. Capturing protocols are already determined by different research works. A setup is established in collaborative hospitals by the Bio-medical Infrared Image Processing Laboratory for proper capturing of thermal images. Patients are first prepared by maintaining protocols and after that images of the patients are captured using thermal imaging.

Figure 2: Samples of dataset. (a) Rheumatoid Arthritis (b) Osteoarthritis Arthritis (c) Reactive Arthritis (d) Healthy Subject

Analysis of Pain thermograms:

In analysis of pain thermograms, the motivation is to automatic early detection of disease, automatic detection of type of disease, automatic gradation of disease. First step is to detect abnormality by asymmetry analysis. In the next phase, segmentation of the inflamed region is conducted for analysis. Accurate segmentation is the prime requirement for analysis of the inflamed region. After extraction of inflamed region, different image processing algorithm is used for determining the disease type and grade the disease etc. Till date, three segmentation methods are devised for thermal images that is followed by the automatic gradation of inflammation.

Figure 3: Segmentation of Hotspot will provide the above shown ROI (Inflamed region/Hotspot). Analysis of this ROI provide different insights of arthritis diseases.

Featured Articles :

1. Shawli Bardhan, Mrinal Kanti Bhowmik, Tathagata Debnath, Debotosh Bhattacharjee, "RASIT: Region shrinking based Accurate Segmentation of Inflammatory areas from Thermograms", Biocybernetics and Biomedical Engineering, published by Elsevier, Volume 38, Issue 4, pp. 903-917 ISSN: 0208-5216, Indexed by Science Citation Index Expanded(SCIE), Impact factor : 2.537, DOI: https://doi.org/10.1016/j.bbe.2018.07.002.


2. Shawli Bardhan and Mrinal Kanti Bhowmik, "2-Stage classification of knee joint thermograms for rheumatoid arthritis prediction in subclinical inflammation" Australasian Physical & Engineering Sciences in Medicine, Published by Springer, Indexed by Science Citation Index Expanded(SCIE), Volume 12, Issue 1, pp 259-277, ISSN: 0158-9938, Impact Factor:1.161, DOI: https://doi.org/10.1007/s13246-019-00726-9.


3. Kakali Das, Mrinal Kanti Bhowmik, Omkar Chowdhuary, Debotosh Bhattacharjee and Barin Kumar De, "Accurate segmentation of inflammatory and abnormal regions using medical thermal imagery" Australasian Physical & Engineering Sciences in Medicine, Published by Springer, Indexed by Science Citation Index Expanded(SCIE), 2019, ISSN 0158-9938, Impact Factor: 1.161, DOI: https://doi.org/10.1007/s13246-019-00753-6


4. Mrinal Kanti Bhowmik, Kakali Das and Debotosh Bhattacharjee, "Temperature Profile Guided Segmentation for Detection of Early Subclinical Inflammation in Arthritis Knee Joints From Thermal Images" Infrared Physics & Technology, Published by Elsevier, Indexed by Science Citation Index Expanded (SCIE), Volume 99, pp 102-112, 2019, Impact Factor: 2.379, DOI: https://doi.org/10.1016/j.infrared.2019.04.011


5. Kakali Das, Mrinal Kanti Bhowmik, and Dipti Prasad Mukherjee, "Segmentation of Knee Thermograms For Detecting Inflammation" Proceedings of 26th IEEE International Conference on Image Processing (ICIP) - Tier 2 Conference, 2019, Taipei, Taiwan.