Automatic quantification of tenosynovitis on MRI of the wrist in patients with early arthritis: a feasibility study

Artificial intelligence to analyze magnetic resonance imaging in rheumatology

Rheumatic disorders present a global health challenge, marked by inflammation and damage to joints, bones, and connective tissues. Accurate, timely diagnosis and appropriate management are crucial for favorable patient outcomes. Magnetic resonance imaging (MRI) has become indispensable in rheumatology, but interpretation remains laborious and variable. Artificial intelligence (AI), including machine learning (ML) and deep learning (DL), offers a means to improve and advance MRI analysis. This review examines current AI applications in rheumatology MRI analysis, addressing diagnostic support, disease classification, activity assessment, and progression monitoring. AI demonstrates promise, with high sensitivity, specificity, and accuracy, achieving or surpassing expert performance. The review also discusses clinical implementation challenges and future research directions to enhance rheumatic disease diagnosis and management.

Artificial intelligence powered advancements in upper extremity joint MRI: A review

Magnetic resonance imaging (MRI) is an indispensable medical imaging examination technique in musculoskeletal medicine. Modern MRI techniques achieve superior high-quality multiplanar imaging of soft tissue and skeletal pathologies without the harmful effects of ionizing radiation. Some current limitations of MRI include long acquisition times, artifacts, and noise. In addition, it is often challenging to distinguish abutting or closely applied soft tissue structures with similar signal characteristics. In the past decade, Artificial Intelligence (AI) has been widely employed in musculoskeletal MRI to help reduce the image acquisition time and improve image quality. Apart from being able to reduce medical costs, AI can assist clinicians in diagnosing diseases more accurately. This will effectively help formulate appropriate treatment plans and ultimately improve patient care. This review article intends to summarize AI's current research and application in musculoskeletal MRI, particularly the advancement of DL in identifying the structure and lesions of upper extremity joints in MRI images.

Implementation of artificial intelligence models in magnetic resonance imaging with focus on diagnosis of rheumatoid arthritis and axial spondyloarthritis: narrative review

Early diagnosis in rheumatoid arthritis (RA) and axial spondyloarthritis (axSpA) is essential to initiate timely interventions, such as medication and lifestyle changes, preventing irreversible joint damage, reducing symptoms, and improving long-term outcomes for patients. Since magnetic resonance imaging (MRI) of the wrist and hand, in case of RA and MRI of the sacroiliac joints (SIJ) in case of axSpA can identify inflammation before it is clinically discernible, this modality may be crucial for early diagnosis. Artificial intelligence (AI) techniques, together with machine learning (ML) and deep learning (DL) have quickly evolved in the medical field, having an important role in improving diagnosis, prognosis, in evaluating the effectiveness of treatment and monitoring the activity of rheumatic diseases through MRI. The improvements of AI techniques in the last years regarding imaging interpretation have demonstrated that a computer-based analysis can equal and even exceed the human eye. The studies in the field of AI have investigated how specific algorithms could distinguish between tissues, diagnose rheumatic pathology and grade different signs of early inflammation, all of them being crucial for tracking disease activity. The aim of this paper is to highlight the implementation of AI models in MRI with focus on diagnosis of RA and axSpA through a literature review.

Magnetic Resonance Imaging Image Segmentation under Edge Detection Intelligent Algorithm in Diagnosis of Surgical Wrist Joint Injuries

Background

Wrist joint injury refers to the injury of the wrist joint caused by excessive stretching of the ligaments and joint capsules around the joint caused by indirect violence. The tissue structure of the wrist joint is complex, and the clinical diagnosis effect is poor.

Methods

The purpose of this study was to improve the diagnostic accuracy of wrist joint injuries and provide evidence for imaging analysis and automatic diagnosis of lesions in patients with wrist joint injuries. The Canny algorithm was adopted to extract the edge features of the patient's magnetic resonance imaging (MRI) image, and the particle swarm optimization-support vector machine (PSO-SVM) algorithm was applied to segment the lesion. The image processing effect of the algorithm was evaluated by taking peak signal to noise ratio (PSNR), mean square error (MSE), figure of merit (FOM), and structural similarity (SSIM) as indicators. The accuracy, sensitivity, specificity, and Dice similarity coefficient of the algorithm were analyzed to evaluate the diagnostic accuracy in WJI.

Results

Compared with the Gradient Vector Flo (GVF) algorithm and the Elastic Automatic Region Growing (ERG) algorithm, the edge stability of the PSO-SVM algorithm was stable above 0.9. After the quality of images processed using different algorithms was analyzed, it was found that the PSNR of the PSO-SVM algorithm was 26.891 ± 5.331 dB, the MSE was 0.0014 ± 0.0003, the FOM was 0.8832 ± 0.0957, and the SSIM was 0.9032 ± 0.0807. The four indicators were all much better than those of the GVF algorithm and the EARG algorithm, showing statistically obvious differences (P < 0.05). Analysis on diagnostic accuracy of different algorithms for WJI suggested that the diagnostic accuracy of the PSO-SVM algorithm was 0.9413, the sensitivity was 0.9129, the specificity was 0.9088, and the Dice similarity coefficient was 0.8715. The four indicators all showed statistically great difference compared with those of the GVF algorithm and the EARG algorithm (P < 0.05).

Conclusions

The PSO-SVM algorithm showed excellent edge detection performance and higher accuracy in the diagnosis of WJI, which can assist clinicians in the clinical auxiliary diagnosis of WJI.

Artificial intelligence in detecting early RA

To prevent chronicity of Rheumatoid Arthritis (RA) by early treatment, detecting inflammatory signs in an early phase is essential. Since Magnetic Resonance Imaging (MRI) of the wrist, hand and foot can detect inflammation before it is clinically detectable, this modality may play an important role in achieving very early diagnoses. By collecting large amounts of MRI data from healthy controls and patients with arthralgia suspicious for progression to RA, patterns can be studied that are most specific for early development of RA. Furthermore, MRI can be used as outcome parameter for randomized placebo-controlled trials on early RA treatment, by detecting subtle changes in image intensities originating from natural progression or treatment effects. Very large amounts of MRI data, however, make manual quantification impractical and the coarse scale used in visual scoring systems (i.e. whole values between 0 and 3) limits its sensitivity to detect changes that are likely to be very subtle in such an early phase. In recent years, advances in artificial intelligence and especially 'deep learning' in interpreting medical images have shown that -in specific areas- a computerized analysis can outperform human observers. Therefore, research has been initiated into applying these artificial intelligence techniques to the quantification of early RA from MRI data. In this paper, an overview is given on the background and history of artificial intelligence, with a special focus on recent developments in 'deep learning', and how these techniques could be applied to detect subtle inflammatory changes in MRI data.

Use of artificial intelligence in imaging in rheumatology - current status and future perspectives

After decades of basic research with many setbacks, artificial intelligence (AI) has recently obtained significant breakthroughs, enabling computer programs to outperform human interpretation of medical images in very specific areas. After this shock wave that probably exceeds the impact of the first AI victory of defeating the world chess champion in 1997, some reflection may be appropriate on the consequences for clinical imaging in rheumatology. In this narrative review, a short explanation is given about the various AI techniques, including 'deep learning', and how these have been applied to rheumatological imaging, focussing on rheumatoid arthritis and systemic sclerosis as examples. By discussing the principle limitations of AI and deep learning, this review aims to give insight into possible future perspectives of AI applications in rheumatology.

The value of MRI examination on bilateral hands including proximal interphalangeal joints for disease assessment in patients with early rheumatoid arthritis: a cross-sectional cohort study

Background

Bilateral hands including proximal interphalangeal joints (PIPJs) are recommended on physical, X-ray radiographic, or ultrasonographic examination by clinical guidelines of rheumatoid arthritis (RA), but MRI still tends to examine unilateral wrists and/or MCPJs. We aimed to demonstrate the advantages of MRI examination on bilateral hands including PIPJs for disease assessment in early RA patients.

Methods

Active early RA patients received 3.0T whole-body MRI examination with contrast-enhanced imaging on bilateral wrists, MCPJs, and PIPJs. MRI features were scored referring to the updated RAMRIS. Clinical assessments were conducted on the day of MRI examination.

Results

The mean time of MRI examination was 24 ± 3 min. MRI bone erosion in MCPJs would be missed-diagnosed in 23% of patients if non-dominant MCPJs were scanned unilaterally, while osteitis in MCPJs would be missed-diagnosed in 16% of patients if dominant MCPJs were scanned unilaterally. MRI synovitis severity was also asymmetric: 21% of patients showing severe synovitis unilaterally in non-dominant MCPJs/PIPJs and other 20% showing severe synovitis unilaterally in dominant MCPJs/PIPJs. Among these early RA patients, MRI tenosynovitis occurred the most frequently in wrist extensor compartment I, while MRI examination on bilateral hands demonstrated no overuse influence present. However, overuse should be considered in dominant PIPJ2, PIPJ4, and IPJ of thumb of which MRI tenosynovitis prevalence was respectively 18%, 17%, or 16% higher than the non-dominant counterparts. Early MRI abnormality of nervus medianus secondary to severe tenosynovitis occurred either in dominant or non-dominant wrists; MRI of unilateral hands would take a risk of missed-diagnosis. Common MRI findings in PIPJs were synovitis and tenosynovitis, respectively in 87% and 69% of patients. MRI tenosynovitis prevalence in IPJ of thumb or PIPJ5 was much higher than the continued wrist flexor compartments. MRI synovitis or tenosynovitis in PIPJs independently increased more than twice probability of joint tenderness (OR = 2.09 or 2.83, both p < 0.001).

Conclusions

In consideration of asymmetric MRI features in early RA, potential overuse influence for certain tenosynovitis in dominant hands, and high prevalence of MRI findings in PIPJs, MRI examination on bilateral hands including PIPJs is deserved for disease assessment in early RA patients.

ERAMRS: a new MR scoring system for early rheumatoid arthritis of the wrist

PURPOSE

To (i) devise a new semi-quantitative scoring system known as Early Rheumatoid Arthritis Magnetic Resonance Score (ERAMRS) to assess inflammation of the wrist on magnetic resonance imaging in early rheumatoid arthritis and to (ii) test ERAMRS and other MR scoring systems against everyday used clinical scorings.

MATERIALS AND METHODS

One hundred six treatment-naïve patients (81 females, 25 males, mean age 53 ± 12 years) with early rheumatoid arthritis (ERA) underwent clinical/serological testing as well as 3-T MRI examination of the most symptomatic wrist. Clinical assessment included Disease Activity Score-28 and Health Assessment Questionnaire; erythrocyte sedimentation rate and C-reactive protein were measured. MR imaging data was scored in all patients using three devised MR semi-quantitative scoring systems, namely, the (a) ERAMRS system, (b) Rheumatoid Arthritis Magnetic Resonance Imaging Score (RAMRIS) system, and the (c) McQueen Score system.

RESULTS

Synovitis was present in 106 (100%), tenosynovitis in 98 (92%), and bone marrow edema in 84 (79%) of 106 ERA wrists. ERAMRS had the highest correlation with clinical disease activity scores (r = 0.476, p < 0.001) and serological parameters (r = 0.562, p < 0.001). RAMRIS system had the lowest correlation (r = 0.369, p < 0.001 for clinical disease activity; r = 0.436, p < 0.001 for serological parameters). RAMRIS synovitis subscore had a lower correlation than ERAMRS for clinical disease activity (r = 0.410, p < 0.001) and for serological parameters (r = 0.456, p < 0.001).

CONCLUSION

The ERAMRS system, designed to grade inflammation on wrist MRI in ERA, provided the best correlation with all clinical scoring systems and serological parameters, indicating its improved clinical relevance over other MR scoring systems.

KEY POINTS

• We devised a clinically relevant, easy-to-use semi-quantitative scoring system for scoring inflammation on MRI of the wrist in patients with early rheumatoid arthritis. • ERAMRS system showed better correlation with all clinical and serological assessment of inflammation in patients with early rheumatoid arthritis indicating its improved clinical relevance over other MR scoring systems.