Detecting Knee Cartilage Structural Changes Using Magnetic Resonance Computed Vision Analysis in Patients with Osteoarthritis: Preliminary Results
-
Published:2021-02-01
Issue:1
Volume:75
Page:47-51
-
ISSN:1407-009X
-
Container-title:Proceedings of the Latvian Academy of Sciences. Section B. Natural, Exact, and Applied Sciences.
-
language:en
-
Short-container-title:
Author:
Supe Ingus1, Supoņenkovs Artjoms2, Platkājis Ardis1, Kadiša Anda3, Lejnieks Aivars3
Affiliation:
1. Department of Radiology , Rīga Stradiņš University , 2 Hipokrāta Str., Rīga, LV-1038 , Latvia 2. Faculty of Computed Science and Information Technology , Rīga Technical University , 1 Sētas Str., Rīga, LV-1048 , Latvia 3. Department of Internal Medicine , Rīga Stradiņš University , 4 Hipokrāta Str., Rīga, LV-1038 , Latvia
Abstract
Abstract
Based on epidemiological data, osteoarthritis (OA) is the most common joint disease of populations of industrialised countries. The increasing prevalence of OA is closely related to an ageing population and a sedentary lifestyle. Load-bearing joints, such as hip, knee, and intervertebral joints, are the primary ones that are being subjected to the degenerative changes. The patho-physiology of the disease is based on progressive damage and gradual deterioration of the micro and macrostructure of hyaline cartilage. In today’s radiological practice, the first-line method for assessing the condition of articular cartilage is magnetic resonance imaging (MRI). However, the sensitivity of standard clinical MRI in articular cartilage assessment is limited. For this reason, for the last five years there has been a rapidly growing interest in developing advanced MRI techniques for cartilage structure evaluation. The purpose of this pilot study was to highlight the possibilities of Artificial Intelligence Computed Vision Analysis (MEDH 3.0 algorithm) in the evaluation of cartilage changes of the knee joint. The study was carried out at Rīga East Clinical University Hospital (RAKUS) and included 25 patients. After assessment by a rheumatologist, the participants were divided into two groups: 15 (60%) participants with OA and 10 (40%) healthy individuals. All patients underwent MRI examinations according to a unified RAKUS Gaiïezers Radiology clinic protocol. MRI data were analysed using the Computed Vision Analysis MEDH 3.0 algorithm. The results showed substantial differences in intensity variance (p < 0.01) parameters, as well as in pixel entropy and homogeneity values (p < 0.01). The results of the pilot study confirmed the potential use of Artificial Intelligence Computed Vision Analysis in further development and integration in the assessment of cartilage changes in the knee joint.
Publisher
Walter de Gruyter GmbH
Subject
Multidisciplinary
Reference28 articles.
1. Amira, B., R., Faouzi, B., Hamid, A. (2016). Segmentation of brain MRI using active contour model. Int. J. Imaging Syst. Technol.,27 (1), 3–11. 2. Apprich, S., Mamisch, T. C., Welsch, G. H., Stelzeneder, D., Albers, C., Totzke, J., Trattnig, S. (2012). Quantitative T2 mapping of the patella at 3.0 T is sensitive to early cartilage degeneration, but also to loading of the knee. Eur. J. Radiol.,81 (4), 438–443. 3. Armi, L., Fekri-Ershad, S. (2019). Texture image analysis and texture classification methods: A review. Int. Online J. Image Process. Pattern Recogn.,2 (1), 1–29. 4. Barr, C., Bauer, J. S., Malfair, D., Ma, B., Henning, T. D., Steinbach, L., Link, T. M. (2007). MR imaging of the ankle at 3 Tesla and 1.5 Tesla: Protocol optimization and application to cartilage, ligament and tendon pathology in cadaver specimens. Euro Radiol.,17 (6), 1518–1528. 5. Binks, D. A., Hodgson, R. J., Ries, M. E., Foster, R. J., Smye, S. W., Gonagle, D. Mc., Radjenovic, A. (2013). Quantitative parametric MRI of articular cartilage: A review of progress and open challenges. BRJ Radiology,86 (1023), 120–163.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|