Predicting the development of rheumatoid arthritis (RA) in an early stage through magnetic resonance imaging (MRI) can initiate timely treatment and improve long-term patient outcomes. Although... Show morePredicting the development of rheumatoid arthritis (RA) in an early stage through magnetic resonance imaging (MRI) can initiate timely treatment and improve long-term patient outcomes. Although manual prediction is time-consuming and requires expert knowledge, automatic RA prediction has not been fully investigated. While standard models fail to achieve acceptable performance, we present a consistency-based deep learning framework to classify and predict RA automatically and precisely, including an output-standardized model, customized self-supervised pretraining and a loss function that is based on label consistency between original and augmented inputs. For training and evaluation, we used a database, containing 5945 MRI scans of carpal, metacarpophalangeal (MCP), and metatarsophalangeal (MTP) joints, from 2151 subjects obtained over a period of ten years. Four (three classification- and one prediction-) tasks were defined to distinguish two patient groups (with recent-onset arthritis and clinically suspect arthralgia) from healthy controls and RA from other arthritis patients within the recent-onset arthritis group, and predict RA development in a period of two years within the clinically suspect arthralgia group. The proposed method was evaluated with the area under the receiver operating curve (AUROC) on a separate test set, achieving mean AUROCs of 83.6%, 83.3%, and 69.7% in the three classification tasks, and 67.8% in the prediction task. This proves the existence of early signs of RA in MRI and the potential of a consistency-based deep learning model to detect these early signs and predict RA Show less
Stoel, B.C.; Staring, M.; Reijnierse, M.; Helm-van Mil, A.H.M. van der 2024
Artificial intelligence techniques, specifically deep learning, have already affected daily life in a wide range of areas. Likewise, initial applications have been explored in rheumatology. Deep... Show moreArtificial intelligence techniques, specifically deep learning, have already affected daily life in a wide range of areas. Likewise, initial applications have been explored in rheumatology. Deep learning might not easily surpass the accuracy of classic techniques when performing classification or regression on low-dimensional numerical data. With images as input, however, deep learning has become so successful that it has already outperformed the majority of conventional image-processing techniques developed during the past 50 years. As with any new imaging technology, rheumatologists and radiologists need to consider adapting their arsenal of diagnostic, prognostic and monitoring tools, and even their clinical role and collaborations. This adaptation requires a basic understanding of the technical background of deep learning, to efficiently utilize its benefits but also to recognize its drawbacks and pitfalls, as blindly relying on deep learning might be at odds with its capabilities. To facilitate such an understanding, it is necessary to provide an overview of deep-learning techniques for automatic image analysis in detecting, quantifying, predicting and monitoring rheumatic diseases, and of currently published deep-learning applications in radiological imaging for rheumatology, with critical assessment of possible limitations, errors and confounders, and conceivable consequences for rheumatologists and radiologists in clinical practice.Deep learning is a powerful technique with great potential for the analysis and interpretation of rheumatological images. To successfully use deep learning, rheumatologists should understand the tasks involved in image processing and the potential confounders and limitations that can affect the analysis of clinical data.The number of research studies on deep learning in rheumatological imaging has grown rapidly during the past 5 years, but they mainly consist of pilot studies that require external validation.Confounding factors and errors in deep-learning methods need to be ruled out before deep learning can be applied in clinical practice, for which the intended use should be strictly defined.Deep-learning techniques, together with mapping to explain their reasoning, will enable hypothesis-free image analysis and could identify new imaging biomarkers.Deep learning might assist rheumatologists and radiologists in interpreting rheumatological images, increasing their diagnostic, prognostic and monitoring accuracy, and decreasing workloads and costs. Show less
Dijk, B.T. van; Reijnierse, M.; Helm-van Mil, A.H.M. van der 2023
ObjectiveInflammation around the tendons of the hand interosseous muscles (interosseous tendon inflammation [ITI]) was recently identified on magnetic resonance imaging (MRI) in a set of patients... Show moreObjectiveInflammation around the tendons of the hand interosseous muscles (interosseous tendon inflammation [ITI]) was recently identified on magnetic resonance imaging (MRI) in a set of patients with rheumatoid arthritis (RA) and arthralgia. We conducted a large MRI study to assess the prevalence of ITI at diagnosis of RA and of other arthritides, as well as its relationship with clinical signs.MethodsA total of 1,205 patients presenting with various types of early arthritis between 2010 and 2020 underwent contrast-enhanced hand MRI as part of the prospective Leiden Early Arthritis Cohort. MRI was evaluated with blinding for clinical data, for ITI lateral of metacarpophalangeal (MCP) joints 2–5, and for synovitis/tenosynovitis/osteitis. We assessed ITI presence at baseline per diagnosis and its relationship with clinical characteristics (ie, presence of hand arthritis, increased acute phase reactants, and local joint swelling and tenderness). Logistic regression and generalized estimating equations were used with adjustment for age and established local inflammation features (synovitis/tenosynovitis/osteitis).ResultsA total of 36% of patients with early RA (n = 532) had ITI; this was similar in patients with anti–citrullinated protein antibody (ACPA)-negative RA (37%) and those with ACPA-positive RA (34%; P = 0.53). ITI occurred regularly in remitting seronegative symmetrical synovitis with pitting edema (60%) and connective tissue diseases (44%) and less frequently in undifferentiated arthritis (14%), psoriatic arthritis (14%), inflammatory osteoarthritis (8%), reactive arthritis (7%), crystal arthritis (7%), and peripheral spondylarthritis (4%). ITI occurred more often in diagnoses with frequent arthritis of the hands (P < 0.001) and increased acute-phase reactants (P < 0.001). Within RA, ITI occurred together with local MCP joint synovitis (odds ratio [OR] 2.4, 95% confidence interval [95% CI] 1.7–3.4), tenosynovitis (OR 2.4, 95% CI 1.8–3.3), and osteitis (OR 2.2, 95% CI 1.6–3.1) on MRI. Moreover, ITI presence was associated with local MCP joint tenderness (OR 1.6, 95% CI 1.2–2.1) and swelling (OR 1.8, 95% CI 1.3–2.6), independent of age and MRI-detected synovitis/tenosynovitis/osteitis.ConclusionITI occurs regularly in RA and other arthritides with preferential involvement of hand joints and increased acute-phase reactants. At the MCP joint level, ITI associates independently with joint tenderness and swelling. Hence, ITI is a newly identified inflamed tissue mainly found in arthritides with particularly extensive and symptomatic inflammation. Show less
Dijk, B.T. van; Reijnierse, M.; Helm-van Mil, A.H.M. van der 2023
ObjectiveInflammation around the tendons of the hand interosseous muscles (interosseous tendon inflammation [ITI]) was recently identified on magnetic resonance imaging (MRI) in a set of patients... Show moreObjectiveInflammation around the tendons of the hand interosseous muscles (interosseous tendon inflammation [ITI]) was recently identified on magnetic resonance imaging (MRI) in a set of patients with rheumatoid arthritis (RA) and arthralgia. We conducted a large MRI study to assess the prevalence of ITI at diagnosis of RA and of other arthritides, as well as its relationship with clinical signs.MethodsA total of 1,205 patients presenting with various types of early arthritis between 2010 and 2020 underwent contrast-enhanced hand MRI as part of the prospective Leiden Early Arthritis Cohort. MRI was evaluated with blinding for clinical data, for ITI lateral of metacarpophalangeal (MCP) joints 2–5, and for synovitis/tenosynovitis/osteitis. We assessed ITI presence at baseline per diagnosis and its relationship with clinical characteristics (ie, presence of hand arthritis, increased acute phase reactants, and local joint swelling and tenderness). Logistic regression and generalized estimating equations were used with adjustment for age and established local inflammation features (synovitis/tenosynovitis/osteitis).ResultsA total of 36% of patients with early RA (n = 532) had ITI; this was similar in patients with anti–citrullinated protein antibody (ACPA)-negative RA (37%) and those with ACPA-positive RA (34%; P = 0.53). ITI occurred regularly in remitting seronegative symmetrical synovitis with pitting edema (60%) and connective tissue diseases (44%) and less frequently in undifferentiated arthritis (14%), psoriatic arthritis (14%), inflammatory osteoarthritis (8%), reactive arthritis (7%), crystal arthritis (7%), and peripheral spondylarthritis (4%). ITI occurred more often in diagnoses with frequent arthritis of the hands (P < 0.001) and increased acute-phase reactants (P < 0.001). Within RA, ITI occurred together with local MCP joint synovitis (odds ratio [OR] 2.4, 95% confidence interval [95% CI] 1.7–3.4), tenosynovitis (OR 2.4, 95% CI 1.8–3.3), and osteitis (OR 2.2, 95% CI 1.6–3.1) on MRI. Moreover, ITI presence was associated with local MCP joint tenderness (OR 1.6, 95% CI 1.2–2.1) and swelling (OR 1.8, 95% CI 1.3–2.6), independent of age and MRI-detected synovitis/tenosynovitis/osteitis.ConclusionITI occurs regularly in RA and other arthritides with preferential involvement of hand joints and increased acute-phase reactants. At the MCP joint level, ITI associates independently with joint tenderness and swelling. Hence, ITI is a newly identified inflamed tissue mainly found in arthritides with particularly extensive and symptomatic inflammation. Show less
This opinion article by the European Society of Musculoskeletal Radiology Arthritis and Pediatric Subcommittees discusses the current use of conventional radiography (CR) of the sacroiliac joints... Show moreThis opinion article by the European Society of Musculoskeletal Radiology Arthritis and Pediatric Subcommittees discusses the current use of conventional radiography (CR) of the sacroiliac joints in adults and juveniles with suspected axial spondyloarthritis (axSpA). The strengths and limitations of CR compared with magnetic resonance imaging (MRI) and computed tomography (CT) are presented.Based on the current literature and expert opinions, the subcommittees recognize the superior sensitivity of MRI to detect early sacroiliitis. In adults, supplementary pelvic radiography, low-dose CT, or synthetic CT may be needed to evaluate differential diagnoses. CR remains the method of choice to detect structural changes in patients with suspected late-stage axSpA or established disease and in patients with suspected concomitant hip or pubic symphysis involvement. In children, MRI is the imaging modality of choice because it can detect active as well as structural changes and is radiation free. Show less
Background Inflammation around the tendons of interosseous muscles of the hand (interosseous tendon inflammation) was recently observed with MRI for the first time in patients with rheumatoid... Show moreBackground Inflammation around the tendons of interosseous muscles of the hand (interosseous tendon inflammation) was recently observed with MRI for the first time in patients with rheumatoid arthritis and in at-risk individuals with detectable anti-citrullinated protein antibodies, generating the hypothesis that interosseous tendon inflammation precedes clinical arthritis. To better understand the role of interosseous tendon inflammation during the development of rheumatoid arthritis, we studied the frequency of interosseous tendon inflammation in healthy individuals and in those with arthralgia that was suspected of progressing to rheumatoid arthritis (ie, clinically suspect arthralgia) and the association of interosseous tendon inflammation with other symptoms of inflamed joint tissues and with clinical arthritis development.Methods Adult (age >= 18 years) patients who presented with clinically suspect arthralgia and symptom-free (control) individuals underwent contrast-enhanced hand MRI. MRIs were evaluated for interosseous tendon inflammation on the radial and ulnar sides of the second to fifth metacarpophalangeal joints, and for synovitis, tenosynovitis, and osteitis using the rheumatoid arthritis MRI scoring system. Patients with clinically suspect arthralgia were followed up for clinical arthritis development. The presence of local tenosynovium was examined using immunohistochemistry for anti-CD55 and anti-CD68 on tissue from the hands of three embalmed bodies donated for scientific research. The primary outcome for the cross-sectional part of the study was the presence of interosseous tendon inflammation on MRI. The primary outcome for the longitudinal part of the study was development of clinical arthritis.Findings Between April 3, 2012, and May 20, 2020, 667 patients with clinically suspect arthralgia (mean age 44 years [SD 13], 504 [76%] were women and 163 [24%] were men) underwent contrast-enhanced hand MRI. Between Nov 1, 2013, and Nov 30, 2014, 193 symptom-free controls were recruited (mean age 50 years [SD 16], 136 [70%] were women and 57 [30%] were men). Two (1%) of 193 symptom-free controls had interosseous tendon inflammation. Immunohistochemistry of cadaveric hand tissues showed no tenosynovium surrounding interosseous tendons. At inclusion, 67 (10%) of 667 patients with clinically suspect arthralgia had interosseous tendon inflammation (p<00001 vs symptom-free controls). Interosseous tendon inflammation occurred more frequently if synovitis (odds ratio [OR] 22 [95% CI 12-42]), or tenosynovitis (OR 97 [55-170]), was present at metacarpophalangeal joints. A three-dimensional MRI reconstruction suggested confluency of interosseous tendon inflammation with metacarpophalangeal-flexor-tenosynovitis. 91 (16%) of 558 patients with clinically suspect arthralgia developed clinical arthritis during follow-up (median total follow-up 253 months [95% CI 251-255]). Patients with clinically suspect arthralgia with interosseous tendon inflammation had a higher risk of developing clinical arthritis (hazard ratio [HR] 45 [28-72]), which was attenuated but still significant after adjusting for concomitant synovitis, tenosynovitis, or osteitis (HR 17 [102-28]).Interpretation Interosseous tendon inflammation is almost absent in symptom-free individuals but occurs in people with clinically suspect arthralgia, in whom it correlates with symptoms and is associated with the development of clinical arthritis. The absence of local tenosynovium suggests that interosseous tendon inflammation arises from expanding local subclinical inflammation in the pre-arthritis phase of rheumatoid arthritis. Show less
Magnetic resonance imaging (MRI) of the axial skeleton, spine, and sacroiliac (SI) joints is critical for the early detection and follow-up of inflammatory rheumatologic disorders such as axial... Show moreMagnetic resonance imaging (MRI) of the axial skeleton, spine, and sacroiliac (SI) joints is critical for the early detection and follow-up of inflammatory rheumatologic disorders such as axial spondyloarthritis, rheumatoid arthritis, and SAPHO/CRMO (synovitis, acne, pustulosis, hyperostosis, and osteitis/chronic recurrent multifocal osteomyelitis). To offer a valuable report to the referring physician, disease-specific knowledge is essential. Certain MRI parameters can help the radiologist provide an early diagnosis and lead to effective treatment. Awareness of these hallmarks may help avoid misdiagnosis and unnecessary biopsies. A bone marrow edema-like signal plays an important role in reports but is not disease specific. Age, sex, and history should be considered in interpreting MRI to prevent overdiagnosis of rheumatologic disease. Differential diagnoses-degenerative disk disease, infection, and crystal arthropathy-are addressed here. Whole-body MRI may be helpful in diagnosing SAPHO/CRMO. Show less
ObjectiveInflammatory hand arthritis (IHA) results in impaired function. Local gene therapy with ART-I02, a recombinant adeno-associated virus (AAV) serotype 5 vector expressing interferon (IFN)-β,... Show moreObjectiveInflammatory hand arthritis (IHA) results in impaired function. Local gene therapy with ART-I02, a recombinant adeno-associated virus (AAV) serotype 5 vector expressing interferon (IFN)-β, under the transcriptional control of nuclear factor κ-B responsive promoter, was preclinically shown to have favorable effects. This study aimed to investigate the safety and tolerability of local gene therapy with ART-I02 in patients with IHA.MethodsIn this first-in-human, dose-escalating, cohort study, 12 IHA patients were to receive a single intra-articular (IA) injection of ART-I02 ranging 0.3 × 1012-1.2 × 1013 genome copies in an affected hand joint. Adverse events (AEs), routine safety laboratory and the clinical course of disease were periodically evaluated. Baseline- and follow-up contrast enhanced magnetic resonance images (MRIs), shedding of viral vectors in bodily fluids, and AAV5 and IFN-β immune responses were evaluated. A data review committee provided safety recommendations.ResultsFour patients were enrolled. Long-lasting local AEs were observed in 3 patients upon IA injection of ART-I02. The AEs were moderate in severity and could be treated conservative. Given the duration of the AEs and their possible or probable relation to ART-I02, no additional patients were enrolled. No systemic treatment emergent AEs were observed. The MRIs reflected the AEs by (peri)arthritis. No T-cell response against AAV5 or IFN-β, nor IFN-β antibodies could be detected. Neutralizing antibody titers against AAV5 raised post-dose.ConclusionSingle IA doses of 0.6 × 1012 or 1.2 × 1012 ART-I02 vector genomes were administered without systemic side effects or serious AEs. However, local tolerability was insufficient for continuation. Show less
Dakkak, Y.J.; Heijde, D.M. van der; Reijnierse, M.; Helm-van Mil, A.H.M. van der 2018
