Grading of Metacarpophalangeal Rheumatoid Arthritis on Ultrasound Images Using Machine Learning Algorithms

Abstract

The grading evaluation of metacarpophalangeal rheumatoid arthritis (RA) ultrasonic images is a diagnostic challenge that heavily relies on the expertise of trained sonographers. This study presents a grading method for detecting and estimating the geometric and texture features of synovium thickening and bone erosion. Unlike previous studies in this area, this work uses the metrics and texture features of region of interest (ROI). The highlighted feature of metacarpophalangeal bone and the dark feature of the synovial thickening are extracted simultaneously by the segmented method based on the Gaussian scale space. The segmented results are analyzed to extract three quantitative geometric parameters, which are combined with gray-level co-occurrence matrix (GLCM) statistic texture features to describe the ultrasonic image of metacarpophalangeal RA. To obtain the preferable ability of classification, we applied a support vector machine (SVM) and various feature descriptors, including GLCM, local binary patterns (LBP), and GLCM + LBP, to grade the ultrasonic image of metacarpophalangeal RA. Results show that the SVM, based on our feature descriptor, provides the highest accuracy of up to 92.50%, of the four descriptors. The SVM based on GLCM+LBP descriptor shows better accuracy (86.55%) than either SVM + LBP (85.43%) or SVM+GLCM (82.51%) for discriminating among four grade RA ultrasonic images. Overall, this methodology points to a significant grading of metacarpophalangeal RA ultrasound images without medical expert analysis or blood sample analysis, such as detecting C-reactive protein, measuring erythrocyte sedimentation rate, and testing rheumatoid factor. INDEX TERMS Computer aided diagnosis, metacarpophalangeal rheumatoid arthritis, machine learning, Ultrasonic imaging.

Fruit fly optimization algorithm based modified least squares twin SVM for grading of metacarpophalangeal rheumatoid arthritis

“…A grading technique for the detection and estimation of the geometric and textural aspects of synovium thickening and bone injury was provided in [18]. SVMs and various feature descriptors, including as GLCMs, LBPs (local binary patterns), and GLCMs + LBPs, were utilised to grade the ultrasonic image of MRAs in order to harness the desirable capability of classifications.…”

“…The First Teaching Hospital of Tianjin University of Traditional Chinese Medicine provided complete RA imaging samples. In clinical medicine, MRAs are one of four main categories based on synovium thickening [18]. The synovium does not thicken in grade 0.…”

Classification of Foot Pressure Images Using Machine Learning Algorithm

“…This liquid maintains the smoothness of the joint movements and performs joint actions. There is no permanent solution to generate the synovial liquid [1].…”

COVID-19 discrimination framework for X-ray images by considering radiomics, selective information, feature ranking, and a novel hybrid classifier

“…At this point, the combination of these features and their in-depth analysis constitute the selective information to be processed among the model. First-order statistics (FOS), gray level co-occurrence matrix (GLCM), gray level run length matrix (GLRLM), and gray level size zone matrix (GLSZM) are efficient radiomics frequently used in tasks such as adrenal tumor classification, esophageal cancer categorization, and brain tumor grading [19] , [20] , [21] , [22] , [23] , [24] . These radiomics have also been used in various imaging modalities such as X-ray, magnetic resonance (MR), computed tomography (CT) imaging [19] , [20] , [21] , [22] , [23] , [24] .…”

“…Yang et al. [23] graded rheumatoid arthritis in ultrasound images by using a problem-specific model that was developed on the basis of tests with GLCM features and SVM derivatives.…”