Progressive increase in sacroiliac joint and spinal mri lesions in healthy individuals in relation to age

Year in Review in Axial Spondyloarthritis Clinical Research and Guidelines: SPARTAN 2023 Annual Meeting Proceedings

PURPOSE OF REVIEW

To highlight high impact clinical publications in spondyloarthritis from May 2022 to April 2023 that were summarized and presented at the SPARTAN annual meeting in May 2023.

RECENT FINDINGS

Publications included updated guidelines on management of axial spondyloarthritis (axSpA) by ASAS-EULAR and development of a modified Juvenile Spondyloarthritis Disease Activity Index (JSpADA). Definitions were published for MRI lesions of the spine in axSpA and active and structural sacroiliac (SI) joint lesions in juvenile spondyloarthritis (JSpA). Anatomic variants of the sacroiliac joint were commonly detected using synthetic CT derived from pelvis MRI images. Anti-CD74 antibodies hold promise as a diagnostic biomarker for axSpA; however, the mechanism of such antibody development seems unrelated to gastrointestinal inflammation. High impact clinical publications in spondyloarthritis addressed lab-based and imaging biomarkers, outcome measures, and updated management guidelines.

The sacroiliac joint across ages - what is normal?

The anatomy of the sacroiliac joint (SIJ) is complex with wide variations inter-individually as well as intra-individually (right versus left) and a frequent occurrence of anatomical variants. Besides, the joints are subject to strain, which may elicit non-inflammatory subchondral changes such as bone marrow edema (BME), sclerosis, and fat deposition simulating inflammatory SIJ changes. Furthermore, normal physiological changes during skeletal maturation can make interpretation of SIJ magnetic resonance imaging in children challenging. Knowledge about the wide range of normal findings is therefore important to avoid misinterpretation of findings as pathological. This review describes the current knowledge about normal SIJ findings across all ages.

Deep Learning Algorithm of the SPARCC Scoring System in SI Joint MRI

BACKGROUND

The Spondyloarthritis Research Consortium of Canada (SPARCC) scoring system is a sacroiliitis grading system.

PURPOSE

To develop a deep learning-based pipeline for grading sacroiliitis using the SPARCC scoring system.

STUDY TYPE

Prospective.

POPULATION

The study included 389 participants (42.2-year-old, 44.6% female, 317/35/37 for training/validation/testing). A pretrained algorithm was used to differentiate image with/without sacroiliitis.

FIELD STRENGTH/SEQUENCE

3-T, short tau inversion recovery (STIR) sequence, fast spine echo.

ASSESSMENT

The regions of interest as ground truth for models' training were identified by a rheumatologist (HYC, 10-year-experience) and a radiologist (KHL, 6-year-experience) using the Assessment of Spondyloarthritis International Society definition of MRI sacroiliitis independently. Another radiologist (YYL, 4.5-year-experience) solved the discrepancies. The bone marrow edema (BME) and sacroiliac region models were for segmentation. Frangi-filter detected vessels used as intense reference. Deep learning pipeline scored using SPARCC scoring system evaluating presence and features of BMEs. A rheumatologist (SCWC, 6-year-experience) and a radiologist (VWHL, 14-year-experience) scored using the SPARCC scoring system once. The radiologist (YYL) scored twice with 5-day interval.

STATISTICAL TESTS

Independent samples t-tests and Chi-squared tests were used. Interobserver and intraobserver reliability by intraclass correlation coefficient (ICC) and Pearson coefficient evaluated consistency between readers and the deep learning pipeline. We evaluated the performance using sensitivity, accuracy, positive predictive value, and Dice coefficient. A P-value <0.05 was considered statistically significant.

RESULTS

The ICC and the Pearson coefficient between the SPARCC scores from three readers and the deep learning pipeline were 0.83 and 0.86, respectively. The sensitivity in identifying BME and accuracy of identifying SI joints and blood vessels was 0.83, 0.90, and 0.88, respectively. The dice coefficients were 0.82 (sacrum) and 0.80 (ilium).

DATA CONCLUSION

The high consistency with human readers indicated that deep learning pipeline may provide a SPARCC-informed deep learning approach for scoring of STIR images in spondyloarthritis.

EVIDENCE LEVEL

1 TECHNICAL EFFICACY: Stage 2.

Predominant ligament-centric soft-tissue involvement differentiates axial psoriatic arthritis from ankylosing spondylitis

Since the original description of spondyloarthritis 50 years ago, results have demonstrated similarities and differences between ankylosing spondylitis (AS) and axial psoriatic arthritis (PsA). HLA-B27 gene carriage in axial inflammation is linked to peri-fibrocartilaginous sacroiliac joint osteitis, as well as to spinal peri-entheseal osteitis, which is often extensive and which provides a crucial anatomical and immunological differentiation between the AS and PsA phenotypes. Specifically, HLA-B27-related diffuse bone marrow oedema (histologically an osteitis) and bone marrow fatty corners detected via magnetic resonance imaging, as well as radiographic changes such as sacroiliitis, vertebral squaring, corner erosions and Romanus lesions, all indicate initial bone phenotypes in HLA-B27+ axial disease. However, in much of PsA with axial involvement, enthesitis primarily manifests in ligamentous soft tissue as 'ligamentitis', with characteristic lesions that include para-syndesmophytes and sacroiliac joint bony sparing. Like axial PsA, diffuse idiopathic skeletal hyperostosis phenotypes, which can be indistinguishable from PsA, exhibit a thoracic and cervical spinal ligamentous soft-tissue tropism, clinically manifesting as syndesmophytosis that is soft-tissue-centric, including paravertebral soft-tissue ossification and sacroiliac soft-ligamentous ossification instead of joint-cavity fusion. The enthesis bone and soft tissues have radically different immune cell and stromal compositions, which probably underpins differential responses to immunomodulatory therapy, especially IL-23 inhibition.

Machine Learning Pipeline for Predicting Bone Marrow Edema Along the Sacroiliac Joints on Magnetic Resonance Imaging

OBJECTIVE

We aimed to develop and validate a fully automated machine learning (ML) algorithm that predicts bone marrow edema (BME) on a quadrant level in sacroiliac (SI) joint magnetic resonance imaging (MRI).

METHODS

A computer vision workflow automatically locates the SI joints, segments regions of interest (ilium and sacrum), performs objective quadrant extraction, and predicts presence of BME, suggestive of inflammatory lesions, on a quadrant level in semicoronal slices of T1/T2-weighted MRI scans. Ground truth was determined by consensus among human readers. The inflammation classifier was trained using a ResNet18 backbone and five-fold cross-validated on scans of patients with spondyloarthritis (SpA) (n = 279), postpartum individuals (n = 71), and healthy subjects (n = 114). Independent SpA patient MRI scans (n = 243) served as test data set. Patient-level predictions were derived from aggregating quadrant-level predictions, ie, at least one positive quadrant.

RESULTS

The algorithm automatically detects the SI joints with a precision of 98.4% and segments ilium/sacrum with an intersection over union of 85.6% and 67.9%, respectively. The inflammation classifier performed well in cross-validation: area under the curve (AUC) 94.5%, balanced accuracy (B-ACC) 80.5%, and F1 score 64.1%. In the test data set, AUC was 88.2%, B-ACC 72.1%, and F1 score 50.8%. On a patient level, the model achieved a B-ACC of 81.6% and 81.4% in the cross-validation and test data set, respectively.

CONCLUSION

We propose a fully automated ML pipeline that enables objective and standardized evaluation of BME along the SI joints on MRI. This method has the potential to screen large numbers of patients with (suspected) SpA and is a step closer towards artificial intelligence-assisted diagnosis and follow-up.

Assessment of axial spondyloarthritis activity using a magnetic resonance imaging-based multi-region-of-interest fusion model

BACKGROUND

Identifying axial spondyloarthritis (axSpA) activity early and accurately is essential for treating physicians to adjust treatment plans and guide clinical decisions promptly. The current literature is mostly focused on axSpA diagnosis, and there has been thus far, no study that reported the use of a radiomics approach for differentiating axSpA disease activity. In this study, the aim was to develop a radiomics model for differentiating active from non-active axSpA based on fat-suppressed (FS) T2-weighted (T2w) magnetic resonance imaging (MRI) of sacroiliac joints.

METHODS

This retrospective study included 109 patients diagnosed with non-active axSpA (n = 68) and active axSpA (n = 41); patients were divided into training and testing cohorts at a ratio of 8:2. Radiomics features were extracted from 3.0 T sacroiliac MRI using two different heterogeneous regions of interest (ROIs, Circle and Facet). Various methods were used to select relevant and robust features, and different classifiers were used to build Circle-based, Facet-based, and a fusion prediction model. Their performance was compared using various statistical parameters. p < 0.05 is considered statistically significant.

RESULTS

For both Circle- and Facet-based models, 2284 radiomics features were extracted. The combined fusion ROI model accurately differentiated between active and non-active axSpA, with high accuracy (0.90 vs.0.81), sensitivity (0.90 vs. 0.75), and specificity (0.90 vs. 0.85) in both training and testing cohorts.

CONCLUSION

The multi-ROI fusion radiomics model developed in this study differentiated between active and non-active axSpA using sacroiliac FS T2w-MRI. The results suggest MRI-based radiomics of the SIJ can distinguish axSpA activity, which can improve the therapeutic result and patient prognosis. To our knowledge, this is the only study in the literature that used a radiomics approach to determine axSpA activity.

Axial Spondyloarthritis: Evolving concepts regarding the disease's diagnosis and treatment

Spondyloarthritis (SpA) is a chronic inflammatory disease that affects the axial skeleton (axSpA) and/or the peripheral joints (p-SpA) and entheses. The natural history of SpA in the decades of the 80 and 90 s involved a progressive disease with pain, spinal stiffness, ankylosis of the axial skeleton, structural damage of peripheral joints, and a poor prognosis. In the last 20 years, enormous advances in understanding and managing SpA have occurred. With the introduction of the ASAS classification criteria and MRI, early disease recognition is now possible. The ASAS criteria widened the spectrum of SpA to include all the disease phenotypes, such as radiographic (r-axSpA), non-radiographic (nr-axSpA), and p-SpA and extraskeletal manifestations. Nowadays, the treatment of SpA is based on a shared decision between patients and rheumatologists and includes non-pharmacological and pharmacological therapies. Moreover, the discovery of TNFα, IL-17, which play a pivotal role in disease pathophysiology, has revolutionized disease management. Thus, new targeted therapies and many biological agents are now available and used in SpA patients. TNFα inhibitors (TNFi), IL-17, and JAK inhibitors were proven to be efficacious, with an acceptable toxicity profile. Overall, their efficacy and safety are comparable with some differences. Sustained clinical disease remission, low disease activity, improvement of patient's quality of life, and prevention of progression of structural damage, are the results of the above interventions. The concept of SpA has changed in the last 20 years. The disease burden can be ameliorated by early and accurate diagnosis and targeting therapies.

Sex-specific diagnostic efficacy of MRI in axial spondyloarthritis: challenging the 'One Size Fits All' notion

OBJECTIVES

Sex-specific differences in the presentation of axial spondyloarthritis (axSpA) may contribute to a diagnostic delay in women. The aim of this study was to investigate the diagnostic performance of MRI findings comparing men and women.

METHODS

Patients with back pain from six different prospective cohorts (n=1194) were screened for inclusion in this post hoc analysis. Two blinded readers scored the MRI data sets independently for the presence of ankylosis, erosion, sclerosis, fat metaplasia and bone marrow oedema. Χ2 tests were performed to compare lesion frequencies. Contingency tables were used to calculate markers for diagnostic performance, with clinical diagnosis as the standard of reference. The positive and negative likelihood ratios (LR+/LR-) were used to calculate the diagnostic OR (DOR) to assess the diagnostic performance.

RESULTS

After application of exclusion criteria, 526 patients (379 axSpA (136 women and 243 men) and 147 controls with chronic low back pain) were included. No major sex-specific differences in the diagnostic performance were shown for bone marrow oedema (DOR m: 3.0; f: 3.9). Fat metaplasia showed a better diagnostic performance in men (DOR 37.9) than in women (DOR 5.0). Lower specificity was seen in women for erosions (77% vs 87%), sclerosis (44% vs 66%), fat metaplasia (87% vs 96%).

CONCLUSION

The diagnostic performance of structural MRI markers is substantially lower in female patients with axSpA; active inflammatory lesions show comparable performance in both sexes, while still overall inferior to structural markers. This leads to a comparably higher risk of false positive findings in women.

HLA-B27 status and inflammatory MRI lesions of the sacroiliac joints: a post hoc analysis in patients without axial spondyloarthritis

OBJECTIVE

The assessment of inflammatory and structural lesions in the sacroiliac joint (SIJ) is crucial in axial spondyloarthritis (axSpA). HLA-B27 status plays an important role in axSpA diagnosis and has been linked to MRI lesion burden in the general population. We aimed to investigate the sex-specific influence of HLA-B27 status on inflammatory and structural MRI findings in patients with low back pain of non-inflammatory origin.

METHODS

This post hoc analysis included 139 non-axSpA patients (90 women) with chronic low back pain. Two readers scored MRIs of the SIJ for the presence of sclerosis, erosion, fat metaplasia, bone marrow oedema (BMO) and ankylosis. Frequencies and extent of lesions were compared regarding the HLA-B27 status using χ2 tests and t-tests. Regression models to assess the sex-dependent influence of HLA-B27 on lesion burden were computed.

RESULTS

HLA-B27 was positive in 33 women (36.7%) and 23 men (46.9%). The overall occurrence of all SIJ lesions did not differ in HLA-B27 negative and positive individuals. There were no significant differences in the extent of lesions considering the HLA-B27 positivity, for erosion (mean sum score (MSS) of 0.91 vs 0.48; p=0.144), sclerosis (MSS 1.65 vs 1.88; p=0.576), fat metaplasia (MSS 0.56 vs 0.27; p=0.425), BMO (MSS 0.75 vs 0.59; p=0.460) and ankylosis (MSS 0.06 vs 0.04; p=0.659).

CONCLUSION

HLA-B27 status has no significant influence on the occurrence and extent of SIJ lesions in patients with low back pain of non-inflammatory origin in either men or women.

Magnetic resonance imaging in spondyloarthritis: Friend or Foe?

Magnetic resonance imaging (MRI) has emerged as a valuable tool for early detection and of axial spondyloarthritis (axSpA). A standardized imaging acquisition protocol, aligned with the current state-of-the-art, is crucial to obtain MRI scans that meet the diagnostic quality requirements. It is important to note that certain lesions, particularly bone marrow edema (BME), can be induced by mechanical stress or be a manifestation of another non-inflammatory disorder and may mimic the characteristic findings of axSpA on MRI. Therefore, a thorough assessment of MRI lesions, considering their localization and presence of highly specific features such as erosions and backfill, becomes imperative. Additionally, the application of additional imaging modalities, when necessary, can contribute to the differentiation of axSpA from other conditions that may exhibit similar MRI findings. This review provides recommendations on how to perform MRI in daily clinical practice and how to interpret finding from the differential diagnostic point of view.

Axial Spondyloarthritis and Diagnostic Challenges: Over-diagnosis, Misdiagnosis, and Under-diagnosis

PURPOSE OF REVIEW

This article aims to review the challenges in axial spondyloarthritis diagnosis and identify the possible contributing factors.

RECENT FINDINGS

The inability to reach an accurate diagnosis in a timely fashion can lead to treatment delays and worse disease outcomes. The lack of validated diagnostic criteria and the misuse of the currently available classification criteria could be contributing. There is also significant inter-reader variability in interpreting images, and the radiologic definitions of axial spondyloarthritis continue to be re-defined to improve their positive predictive value. The role of inflammatory back pain features, serologic biomarkers, genetics, and their diagnostic contribution to axial spondyloarthritis continues to be investigated. There is still a significant amount of delay in the diagnosis of axial spondyloarthritis. Appreciating the factors that contribute to this delay is of utmost importance to close the gap. It is similarly important to recognize other conditions that may present with symptoms that mimic axial spondyloarthritis so that misdiagnosis and wrong treatment can be avoided.

Diagnostics of Sacroiliac Joint Differentials to Axial Spondyloarthritis Changes by Magnetic Resonance Imaging

The diagnosis of axial spondyloarthritis (axSpA) is usually based on a pattern of imaging and clinical findings due to the lack of diagnostic criteria. The increasing use of magnetic resonance imaging (MRI) of the sacroiliac joints (SIJ) to establish the diagnosis early in the pre-radiographic phase has resulted in a shift in the paradigm with an increasing frequency of axSpA diagnoses and a changed sex distribution. Non-radiographic axSpA affects males and females nearly equally, whereas ankylosing spondylitis predominantly occurs in males. The MRI-based increasing frequency of axSpA in women is mainly due to the presence of subchondral bone marrow edema (BME) on fluid-sensitive MR sequences, which may be a non-specific finding in both women and men. Due to the somewhat different pelvic tilt and SIJ anatomy, women are more prone than men to develop strain-related MRI changes and may have pregnancy-related changes. Awareness of non-specific subchondral BME at the SIJ is important as it can imply a risk for an incorrect SpA diagnosis, especially as the clinical manifestations of axSpA may also be non-specific. Knowledge of relevant MRI and clinical features of differential diagnoses is needed in the diagnostic workout of patients with suspected axSpA considering that non-SpA-related SIJ conditions are more common in patients with low back or buttock pain than axSpA sacroiliitis. The purpose of this review was to present current knowledge of the most frequent differential diagnoses to axSpA sacroiliitis by MRI taking the clinical characteristics into account.

The influence of age on the prevalence of inflammatory and structural MRI lesions in the SIJ of patients with and without axSpA

OBJECTIVE

To compare the influence of age on inflammatory (bone marrow oedema. BME) and structural (fat lesions (FL), erosions and ankylosis) MRI lesions in the SIJ of patients with and without axial spondyloarthritis (axSpA).

METHODS

In a retrospective study, SIJ MRI (STIR/T1 sequences) of consecutive patients with chronic back pain diagnosed with axSpA or non-SpA were evaluated based on SIJ quadrants (SIJ-Q). Two blinded readers evaluated BME and structural lesions. Reader agreement was evaluated for prevalence of MRI lesions related to age.

RESULTS

MRIs of 309 (175 axSpA, 134 non-SpA) patients were evaluated. Their mean age was 38.5 ± 11.4 vs 43.4 ± 13.8 years (y), 67% and 36% were male, CRP 1.6 ± 2.4 vs 1.1 ± 2.1 mg/dl, median symptom duration 48 and 60 months, respectively. SIJ-Q with BME and erosions were significantly more frequent in axSpA vs non-SpA patients independent of age, while this difference was seen for FL only in patients ≥50 y. The proportion of patients with ≥1 or ≥ 3 BME or chronic lesions except for FL increased with age in both groups, and was constantly higher in axSpA vs non-SpA. In univariate analyses, only female sex was significantly associated with more FL.

CONCLUSIONS

The proportion of patients with MRI lesions was high in both, axSpA and non-SpA patients. However, the prevalence of BME and erosions was significantly more frequent in patients with axSpA, was independent of age and also allowed for discrimination. FL occurred more frequently only in older age groups and were less reliable for discrimination vs. non-SpA patients.