AB0594 IMPROVING OSTEOARTHRITIS CARE BY AUTOMATIC MEASUREMENT OF HIP EFFUSION USING AI

Abstract

Background: Osteoarthritis (OA) is the commonest disease affecting hip joints and has high prevalence across various age groups [1,2]. Effusion is a hallmark of OA and could represent a potential target for therapy [3–5]. Positive correlations of effusion to clinical outcomes are not well established, partly due to variability in manual assessment. Voxel-based volume quantification could reduce this variability [6]. Objectives: We examine the inter-observer agreement of manual assessment of voxel-based effusion volume from coronal STIR MRI sequences at two time points and examine the feasibility of using Artificial Intelligence (AI) for standalone volume assessment. Methods: Our algorithm is based on Mask R-CNN [7] and was trained on labeled effusion regions in MRI slices from 68 patients with hip osteoarthritis. For validation, 2 human readers measured effusion from MRI STIR sequences of 25 patients at baseline and at 8 weeks follow-up. AI was used to measure effusion volume as an independent reader. Agreement between human readers and AI was assessed using absolute difference in volume (DV), Coefficients of Variation (CoV) and intraclass correlation coefficient (ICC). Results: Effusion regions detected by AI closely correlated with manual segmentation ([Figure 1][1]) for all samples. Differences in volumes measured by each pair of readers are summarized in [Table 1][2]. Agreement was excellent between human readers (ICC=0.99) and for each reader vs AI (ICC = 0.85-0.87). ![Figure 1.][3] Figure 1. Mask overlays of regions of joint fluid detected by human readers (green, column 2) and AI (red, column 3) from 3 different patients. Raw MRI images are shown in column 1. View this table: Table 1. Comparison of volumes measured in cubic millimeters and agreement between each pair of readers (with AI as the 3rd reader) Conclusion: Initial results of automatic effusion measurement using AI show high agreement with human experts. This has potential to reduce variability and save expert time in OA MRI assessment, and to lead to improved OA care. References: [1]Sharif B, Garner R, Hennessy D, Sanmartin C, Flanagan WM, Marshall DA. Productivity costs of work loss associated with osteoarthritis in Canada from 2010 to 2031. Osteoarthritis Cartilage. 2017 Feb;25(2):249–58. [2]Sharif B, Kopec J, Bansback N, Rahman MM, Flanagan WM, Wong H, et al. Projecting the direct cost burden of osteoarthritis in Canada using a microsimulation model. Osteoarthritis Cartilage. 2015 Oct;23(10):1654–63. [3]Loeuille D, Chary-Valckenaere I, Champigneulle J, Rat A-C, Toussaint F, Pinzano-Watrin A, et al. Macroscopic and microscopic features of synovial membrane inflammation in the osteoarthritic knee: correlating magnetic resonance imaging findings with disease severity. Arthritis Rheum. 2005 Nov;52(11):3492–501. [4]Fernandez-Madrid F, Karvonen RL, Teitge RA, Miller PR, An T, Negendank WG. Synovial thickening detected by MR imaging in osteoarthritis of the knee confirmed by biopsy as synovitis. Magn Reson Imaging. 1995;13(2):177–83. [5]Atukorala I, Kwoh CK, Guermazi A, Roemer FW, Boudreau RM, Hannon MJ, et al. Synovitis in knee osteoarthritis: a precursor of disease? Ann Rheum Dis. 2016 Feb;75(2):390–5. [6]Quinn-Laurin V, Thejeel B, Chauvin NA, Brandon TG, Weiss PF, Jaremko JL. Normal hip joint fluid volumes in healthy children of different ages, based on MRI volumetric quantitative measurement. Pediatr Radiol. 2020 Oct;50(11):1587–93. [7]He K, Gkioxari G, Dollár P, Girshick R. Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision. openaccess.thecvf.com; 2017. p. 2961–9. Acknowledgements: Jacob Jaremko is supported by the AHS Chair in Diagnostic Imaging at the University of Alberta. Medical Imaging Consultants (MIC) funds musculoskeletal radiology fellowships for Vanessa Quinn-Laurin at the University of Alberta, and provides Jacob Jaremko and Robert Lambert with protected academic time. Banafshe Felfeliyan is supported by an Alberta Innovates Graduate Student Scholarship for Data-Enabled Innovation. Disclosure of Interests: None declared. [1]: #F1 [2]: #T1 [3]: pending:yes