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.

Preferential involvement of the pelvis and hips along with active sacroiliitis in chronic nonbacterial osteomyelitis: MRI of 97 patients from a single tertiary referral center.

OBJECTIVE: To present MRI distribution of active osteitis in a single tertiary referral center cohort of patients with chronic nonbacterial osteomyelitis (CNO). METHODS: Two musculoskeletal radiologists retrospectively reviewed MRI examinations of all patients with a final clinical diagnosis of CNO over 15 years. Sites of active osteitis at any time during the course of disease were divided into seven groups: (A) mandible, sternum, clavicles, or scapulas; (B) upper extremities; (C) subchondral sacrum and ilium immediately subjacent to sacroiliac joints (active osteitis denoting "active sacroiliitis" here); (D) pelvis and proximal 1/3 of femurs (excluding group C); (E) bones surrounding knees including distal 2/3 of femurs and 1/2 of proximal tibias and fibulas; (F) distal legs (including distal 1/2 of tibias and fibulas), ankles, or feet; (G) spine (excluding group C). Temporal changes of lesions in response to treatment (or other treatment-related changes such as pamidronate lines) were not within the scope of the study. RESULTS: Among 97 CNO patients (53 males [55%], 44 females; age at onset, mean ± SD, 8.5 ± 3.2 years; age at diagnosis, 10.3 ± 3.3 years), whole-body (WB) MRI was performed in 92%, mostly following an initial targeted MRI (94%). A total of 557 (346 targeted and 211 WB) MRIs were analyzed. Biopsy was obtained in 39 patients (40%), all consistent with CNO or featuring supporting findings. The most common locations for active osteitis were groups D (78%; 95% CI 69‒85%) and C (72%; 95% CI 62‒80%). CONCLUSION: Pelvis and hips were preferentially involved in this cohort of CNO patients along with a marked presence of active sacroiliitis. CLINICAL RELEVANCE STATEMENT: When suggestive findings of CNO are identified elsewhere in the body, the next targeted site of MRI should be the pelvis (entirely including sacroiliac joints) and hips, if whole-body MRI is not available or feasible. KEY POINTS: • Heavy reliance on MRI for diagnosis of CNO underscores the importance of suggestive distribution patterns. • Pelvis and hips are the most common (78%) sites of CNO involvement along with active sacroiliitis (72%). • Pelvis including sacroiliac joints and hips should be targeted on MRI when CNO is suspected.

T2* cartilage mapping in early axial spondyloarthritis: diagnostic accuracy and correlation with clinical characteristics, sacroiliitis MRI scorings, and diffusion metrics.

PURPOSE: To determine the performance of T2* cartilage mapping in diagnosing and assessing disease activity in early axial spondyloarthritis (axSpA), and to investigate the interaction of cartilage damage with clinical characteristics, sacroiliitis MRI scorings, and diffusion metrics. MATERIALS AND METHODS: This prospective study included 83 axSpA patients and 37 no-axSpA patients. Clinical characteristics, the Assessment of SpondyloArthritis International Society-defined active sacroiliitis on MRI, and T2* SIJs values were recorded. In axSpA, disease activity was evaluated using the ankylosing spondylitis disease activity score-C-reactive protein; active sacroiliitis was evaluated using Spondyloarthritis Research Consortium of Canada, intravoxel incoherent motion, and diffusion kurtosis imaging; chronic sacroiliitis was assessed using composite structural damage score (CSDS) and structural score fat. Mann-Whitney U-test, Kruskal-Wallis test with false discovery rate (FDR), ROC curve, and linear regression were used for statistical analysis. RESULTS: AxSpA patients had significantly higher T2*SIJs values than no-axSpA patients. (22.86 ± 2.42 ms vs 20.36 ± 1.30 ms, p < 0.001). The combination of T2*SIJs values and active sacroiliitis on MRI had the highest AUC for identifying axSpA. T2*SIJs values were significantly different between the inactive and very high, moderate and very high, high and very high, as well as inactive and high disease activity groups (all pFDR < 0.05). Dk (ß = 0.48) and CSDS (ß = 0.48) were independently associated with T2*SIJs values. CONCLUSION: T2* values may be a promising biomarker for diagnosing and differentiating disease activity in early axSpA. Both acute and chronic sacroiliitis influence cartilage properties. CLINICAL RELEVANCE STATEMENT: Sacroiliac joint cartilage abnormalities can be quantified with T2* relaxation time and allow better characterization of early axSpA. KEY POINTS: T2* mapping may have value in evaluating axSpA. The combination of T2* values and active sacroiliitis on MRI enhances diagnostic performance for axSpA. Abnormalities measured with T2* values correlate with disease activity, acute sacroiliitis, and degree of structural damage.

ESR Essentials: Imaging of sacroiliitis-practice recommendations by ESSR.

Sacroiliitis is commonly seen in patients with axial spondyloarthritis, in whom timely diagnosis and treatment are crucial to prevent irreversible structural damage. Imaging has a prominent place in the diagnostic process and several new imaging techniques have been examined for this purpose. We present a summary of updated evidence-based practice recommendations for imaging of sacroiliitis. MRI remains the imaging modality of choice for patients with suspected sacroiliitis, using at least four sequences: coronal oblique T1-weighted and fluid-sensitive sequences, a perpendicular axial oblique sequence, and a sequence for optimal evaluation of the bone-cartilage interface. Both active inflammatory and structural lesions should be described in the report, indicating location and extent. Radiography and CT, especially low-dose CT, are reasonable alternatives when MRI is unavailable, as patients are often young. This is particularly true to evaluate structural lesions, at which CT excels. Dual-energy CT with virtual non-calcium images can be used to depict bone marrow edema. Knowledge of normal imaging features in children (e.g., flaring, blurring, or irregular appearance of the articular surface) is essential for interpreting sacroiliac joint MRI in children because these normal processes can simulate disease. CLINICAL RELEVANCE STATEMENT: Sacroiliitis is a potentially debilitating disease if not diagnosed and treated promptly, before structural damage to the sacroiliac joints occurs. Imaging has a prominent place in the diagnostic process. We present a summary of practice recommendations for imaging of sacroiliitis, including several new imaging techniques. KEY POINTS: • MRI is the modality of choice for suspected inflammatory sacroiliitis, including a joint-line-specific sequence for optimal evaluation of the bone-cartilage interface to improve detection of erosions. • Radiography and CT (especially low-dose CT) are reasonable alternatives when MRI is unavailable. • Knowledge of normal imaging features in children is mandatory for interpretation of MRI of pediatric sacroiliac joints.

Predictors of treatment failure of non-steroidal anti-inflammatory drugs in patients with axial spondyloarthritis with focus on haptoglobin, haptoglobin polymorphism and zonulin.

According to the Assessment of SpondyloArthritis International Society-European Alliance of Associations for Rheumatology (ASAS-EULAR) recommendations for the management of axial spondyloarthritis (axSpA), patients should undergo at least two courses of non-steroidal anti-inflammatory drugs (NSAIDs) therapy. In our study, we enrolled axSpA patients both at onset and in a flare who had already been treated with NSAIDs ineffectively. Subsequently, according to the recommendations, they received modified NSAID treatment as another attempt to the first-line drug therapy and were monitored from there. We aimed to identify risk factors for treatment failure after 4 weeks (Bath Ankylosing Spondylitis Disease Activity Index (BASDAI) score ≥ 4) especially amongst zonulin and haptoglobin concentrations, and haptoglobin polymorphism. Treatment failure was observed in 71% of patients, and the following variables were contributed for occurrence of this state: higher zonulin levels, ankylosing spondylitis, X-ray sacroiliitis, magnetic resonance imaging sacroiliitis, long duration of symptoms, high BASDAI, and high value of spinal pain intensity on visual analogue scale. In addition, the following positive correlations were found: haptoglobin concentration with C-reactive protein (r = 0.56; p = 0.0004), and erythrocyte sedimentation rate (r = 0.62; p < 0.0001), as well as between zonulin levels and white blood count (r = 0.5; p = 0.0003). The results of the study presented the identified factors related to the standard treatment failure in axSpA, amongst them zonulin levels. They might be applied to point out the patients for whom the search for a more appropriate method of treatment should be considered.

Sacroiliitis in familial Mediterranean fever: A rare joint involvement of the disease.

AIM: Familial Mediterranean fever (FMF) is a monogenic autoinflammatory disease characterised by recurrent episodes of fever and polyserositis. Sacroiliac joint involvement is rare in FMF patients. The purpose of this study was to evaluate the demographic, clinical, laboratory and imaging findings of patients with FMF who developed sacroiliitis. METHODS: The files of paediatric patients aged 0-18 years who were followed up with a diagnosis of FMF were retrospectively reviewed. FMF patients with evidence of sacroiliitis on magnetic resonance imaging (MRI) were included in the study. RESULTS: Among 1062 FMF patients, 22 (12 males; median age 8.5) (2.1%) of them were found to have sacroiliitis. FMF was diagnosed before sacroiliitis in nine (40.9%) patients and after in 13 (59.1%) patients. The most common symptom in patients with sacroiliitis was low back pain (n = 21, 95.5%). In MEFV gene analysis, M694V was found in 16 (72.7%) patients and was the most common mutation. MRI showed evidence of sacroiliitis in all patients. All patients were using colchicine. Patients with FMF-associated sacroiliitis, remission was achieved with non-steroidal anti-inflammatory drugs in 12 (54.5%), conventional disease-modifying antirheumatic drugs in six (27.3%) and tumour necrosis factor inhibitor treatment in four (31.8%). Four (31.8%) patients experienced sacroiliitis when colchicine incompatible and four (31.8%) patients experienced sacroiliitis while using biologic agents for colchicine-resistant FMF. CONCLUSIONS: FMF-associated sacroiliitis should be considered especially in patients with M694V mutation if they have symptoms such as low back pain. Colchicine-resistant FMF patients should be evaluated for sacroiliitis symptoms at each visit.

Infectious sacroiliitis: MRI- and CT-based assessment of disease extent, complications, and anatomic correlation.

OBJECTIVE: To describe the frequency of MR and CT features of infectious sacroiliitis (ISI) and assess its extent and complications MATERIALS AND METHODS: This retrospective study included patients with ISI who were evaluated between 2008 and 2021 in a single center. Two radiologists reviewed MRI and CT images to determine the anatomical distribution (unilateral/bilateral, iliac/sacral bone, proximal/middle/distal), severity (bone marrow edema [BME]/periostitis/erosions), concurrent infection (vertebral/nonvertebral), and complications (abscess/probable adjacent osteomyelitis/cavitation/devitalized areas/sequestrum/pelvic venous thrombosis) of ISI. Interobserver reproducibility was assessed. Correlation analysis evaluated the effect of the causative microorganism on severity. Two human bodies were dissected to outline possible ways that ISI can spread. RESULTS: Forty patients with ISI (40 years ± 22; 26 women) were evaluated. Ten patients had bilateral ISI. Concurrent vertebral infection was associated in 15% of cases. Reproducibility of sacral BME, periostitis, and reactive locoregional abnormalities was perfect (κ = 1). Reproducibility was low for erosion count (κ = 0.52[0.52-0.82]) and periarticular osteopenia (κ = 0.50[0.18-0.82]). Inflammatory changes were BME (42/42 joints), muscle edema (38/42), and severe periostitis along the ilium (33/37). Destructive structural changes occurred with confluent erosions (iliac, 20/48; sacral, 13/48), sequestrum (20/48), and cavitation (12/48). Complications occurred in 75% of cases, including periarticular abscesses (n = 30/47), probable adjacent osteomyelitis (n = 16/37), and pelvic thrombophlebitis (n = 3). Tuberculous ISI (6/40) correlated with sclerosis (rs = 0.45[0.16; 0.67]; p < 10-2) and bone devitalization (rs = 0.38[0.16; 0.67]; p = .02). The anatomical study highlighted the shared venous vascularization of sacroiliac joints, pelvic organs, and mobile spine. CONCLUSION: Complications of ISI are frequent, including abscesses, adjacent osteomyelitis, and periostitis. ISI had bilateral involvement nonrarely and is commonly associated with another spinal infection.

Baron Dominique-Jean Larrey (1766-1842): innovator of the triage.

BACKGROUND: During times of war, it is common for some of the most valiant physicians to practice their skills at the battlefields. Only few of them, however, manage to excel. Among those physicians who seemed like the battlefield was their natural environment, was the military surgeon of the French army, Baron Dominique Jean Larrey (1766-1842). He studied medicine and served in the French Navy. Baron Larrey was one of the most significant medical innovators. METHODS: International literature was digitally searched. DISCUSSION: Larrey optimized a variety of procedures, even early neurosurgical ones. He also wrote medical treatises and most importantly invented the world famous 'flying ambulance'. During his 53-year service in the army he became the symbol of protection of the French warrior. That is why he was widely known as the 'protector of the soldier'. Nevertheless, his most eminent invention was the formation of the new 'triage' method. Due to Larrey's priceless impact in the domain of surgical innovation, a notable NATO award was created that is named after him. CONCLUSION: All references presented describe clearly Baron Larrey's contribution to medicine. His innovations in the sphere of the medical science renovated radically the medical ideas of his era.

[Coexistence of familial Mediterranean fever and seronegative spondyloarthritis: peculiarities of the course].

Familial Mediterranean fever (FMF) is an autosomal recessive disease distributed among populations of Mediterranean origin - Armenians, Sephardi Jews, Arabs, Turks. There are numerous clinical observations regarding combination of FMF, as a classical representative of autoinflammatory diseases, with systemic diseases of connective tissue. Seronegative spondyloarthritis (SpA) are the most interesting disorders from this point of view, as far as sacroiliitis - an essential feature of SpA, may also present as a part of joint syndrome in FMF. The main objective of this clinical study was the investigation of the peculiarities of courses of FMF and SpA in case of their coexistence. We studied 126 patients with FMF, SpA and coexistence of both. According to results, patients with the overlap of FMF with SpA had relatively milder course of disease in comparison with each disease separately. Comparative clinical and instrumental characteristics of FMF-associated disorders had shown that in FMF-SpA overlap the symptoms of both diseases are less severe.

Comparing Canadian paediatric rheumatology practice to the 2019 ACR Juvenile Idiopathic Arthritis guidelines: results from the CAPRI Registry.

OBJECTIVE: To identify differences between baseline Canadian JIA practices and the 2019 ACR guidelines for JIA. METHODS: Canadian paediatric rheumatologists were surveyed for their opinions on reasonable a priori target adherence rates for JIA guideline recommendations. Prospectively collected data for 266 newly diagnosed children from 2017 to 2019 were analysed to calculate observed adherence rates. Kaplan-Meier survival curves were used to estimate the cumulative incidence of starting synthetic or biologic DMARDs (sDMARD or bDMARD, respectively) for different patient groups. RESULTS: A total of 25/61 (41%) eligible physicians answered the survey. Most survey respondents (64%) felt that adherence targets should vary depending on the strength of the recommendation and quality of evidence, from a mean of 84% for strong recommendations with high-quality evidence to 29% for conditional recommendations with very low-quality evidence. Data showed 13/19 (68%) recommendations would have met proposed targets and 10/19 (53%) had ≥80% observed adherence. Exceptions were the use of subcutaneous vs oral MTX (53%) and infrequent treatment escalation from NSAIDs to bDMARDs in patients with sacroiliitis (31%) or enthesitis (0%). By 12 weeks, 95% of patients with polyarthritis received sDMARDs, 38% of patients with systemic JIA received bDMARDs and 22% of patients with sacroiliitis received bDMARDs. CONCLUSION: Canadian paediatric rheumatology practices were in line with many 2019 JIA guideline recommendations before their publication, except for frequent use of oral MTX and infrequent direct escalation from NSAIDs to bDMARDs in sacroiliitis and enthesitis.

Comparing MRI and conventional radiography for the detection of structural changes indicative of axial spondyloarthritis in the ASAS cohort.

OBJECTIVES: To compare MRI and conventional radiography of SI joints for detection of structural lesions typical for axial spondyloarthritis (axSpA). METHODS: Adult patients from the Assessment of SpondyloArthritis international Society (ASAS) cohort with symptoms suggestive of axSpA and both SI joint MRI and radiographs available for central reading were included. Radiographs were evaluated by three readers according to the modified New York (mNY) criteria grading system. The presence of structural damage on radiographs was defined as fulfilment of the radiographic mNY criterion and, additionally, a lower threshold for sacroiliitis of at least grade 2 unilaterally. MRI scans were assessed for the presence of structural changes indicative of axSpA by seven readers. Diagnostic performance [sensitivity, specificity, positive and negative predictive values (PPV and NPV) and positive and negative likelihood ratios (LR+ and LR-)] of MRI and radiographs (vs rheumatologist's diagnosis of axSpA) were calculated. RESULTS: Overall, 183 patients were included and 135 (73.7%) were diagnosed with axSpA. Structural lesions indicative of axSpA on MRI had sensitivity 38.5%, specificity 91.7%, PPV 92.9%, NPV 34.6%, LR+ 4.62 and LR- 0.67. Sacroiliitis according to the mNY criteria had sensitivity 54.8%, specificity 70.8%, PPV 84.1%, NPV 35.8%, LR+ 1.88 and LR- 0.64. Radiographic sacroiliitis of at least grade 2 unilaterally had sensitivity 65.2%, specificity 50.0%, PPV 78.6%, NPV 33.8%, LR+ 1.30 and LR- 0.69. CONCLUSION: Structural lesions of the SI joint detected by MRI demonstrated better diagnostic performance and better interreader reliability compared with conventional radiography.

Extra-osseous manifestations in chronic recurrent multifocal osteomyelitis: a retrospective study.

OBJECTIVES: Extra-osseous (EO) manifestations are poorly characterized in chronic recurrent multifocal osteomyelitis (CRMO). This study aimed to further define the frequency, characteristics and treatment of EO events in CRMO and whether different phenotypes can be distinguished and benefit from special management. METHODS: This multicentre retrospective study included CRMO patients followed in several paediatric rheumatology departments in France, between 2015 and 2022. EO manifestations were defined as skin lesions, gastrointestinal manifestations, arthritis, enthesitis, sacroiliitis, uveitis, vasculitis, and fever. At the last visit, the physician defined CRMO as active in the presence of clinical manifestations including both osseous and EO symptoms. RESULTS: We included 133 patients; 87 (65.4%) were girls; the median age at first symptoms was 9.0 years (interquartile range 7.0-10.0). EO manifestations were described in 90 (67.7%) patients, with a predominance of skin lesions (n = 51/90; 56.7%), followed by sacroiliitis (n = 38/90; 42.2%), enthesitis (n = 21/90; 23.3%), arthritis (n = 14/90, 15.6%) and gastrointestinal manifestations (n = 6/90, 6.7%). The use of non-steroidal anti-inflammatory drugs and bisphosphonates did not differ by presence or not of EO manifestations. Biologics were taken more frequently by patients with than without EO manifestations (p< 0.001); tumour necrosis factor inhibitors were used in 33 (36.7%) EO+ patients. Under this treatment, 18 (54.5%) patients achieved complete remission of osseous and EO manifestations. At the last visit, more EO-positive than EO-negative patients were on treatment (p= 0.009), with active disease in 58 (64.4%) patients. CONCLUSION: The analysis of EO manifestations in CRMO delineates 2 groups of patients in terms of severity and treatments used. Our study opens up new pathophysiological leads that may underlie the wide range of CRMO phenotypes.

Sacroiliac joint MRI for diagnosis of ax-SpA: algorithm to improve the specificity of the current ASAS MRI criteria.

OBJECTIVE: To compare sacroiliac joint (SIJ) lesions on MRI in women with versus without axial spondyloarthritis (ax-SpA) and establish an algorithm to determine whether such lesions are due to ax-SpA. METHODS: This retrospective comparative study assessed bone marrow edema (BME), sclerosis, erosions, osteophytes, and ankylosis at the SIJ in two groups of women, one with and another without ax-SpA. Sensitivity and specificity were calculated for combinations/characteristics of lesions, using rheumatologists' assessment with assessment of spondyloarthritis international society (ASAS) criteria as the gold standard for diagnosis of ax-SpA. RESULTS: Compared to women without ax-SpA, women with ax-SpA had more BME (61% vs 17%, p < 0.001), sclerosis (40% vs 22%, p < 0.001), erosions (35% vs 5%, p < 0.001), and ankylosis (2% vs 0%, p = 0.007), but less osteophytes (5% vs 33%, p < 0.001). The ASAS MRI criteria yielded 59% sensitivity and 88% specificity, while a new algorithm achieved 56% sensitivity and 95% specificity using the following criteria: no osteophytes at the SIJ and either (i) BME at the SIJ with at least one dimension ≥ 8 mm or (ii) at least one erosion at the SIJ. CONCLUSIONS: We recommend the following pragmatic algorithm for MRI diagnosis of ax-SpA in women: no osteophytes at the SIJ and either (i) BME at the SIJ with at least one dimension ≥ 8 mm or (ii) at least one erosion at the SIJ. The false positive rate when using the new algorithm (3.3%) is less than half than when using the ASAS MRI criteria (7.7%); thus, its application in clinical practice could reduce overdiagnosis and prevent overtreatment of ax-SpA. CLINICAL RELEVANCE STATEMENT: The developed algorithm has a false-positive rate that is less than half than when using the ASAS MRI criteria (3.3% vs 7.7%), thus its application in clinical practice could reduce overdiagnosis and prevent overtreatment of axial spondyloarthritis. KEY POINTS: • Compared to women without axial spondyloarthritis (ax-SpA), women with ax-SpA had a significantly higher prevalence of bone marrow edema (BME), sclerosis, erosions, and ankylosis, but a significantly lower prevalence of osteophytes. • A new algorithm for positive ax-SpA based on sacroiliac joint MRI was developed: no osteophytes at the sacroiliac joint (SIJ) and either (i) BME at the SIJ with at least one dimension ≥ 8 mm or (ii) at least one erosion at the SIJ. • We recommend this new algorithm for diagnosis of ax-SpA in women, as it has a significantly better specificity than the assessment of spondyloarthritis international society (ASAS) MRI criteria and less than half the false positive rate; thus, its application in clinical practice could reduce overdiagnosis and prevent overtreatment of ax-SpA.

Neural network algorithm for detection of erosions and ankylosis on CT of the sacroiliac joints: multicentre development and validation of diagnostic accuracy.

OBJECTIVES: To evaluate the feasibility and diagnostic accuracy of a deep learning network for detection of structural lesions of sacroiliitis on multicentre pelvic CT scans. METHODS: Pelvic CT scans of 145 patients (81 female, 121 Ghent University/24 Alberta University, 18-87 years old, mean 40 ± 13 years, 2005-2021) with a clinical suspicion of sacroiliitis were retrospectively included. After manual sacroiliac joint (SIJ) segmentation and structural lesion annotation, a U-Net for SIJ segmentation and two separate convolutional neural networks (CNN) for erosion and ankylosis detection were trained. In-training validation and tenfold validation testing (U-Net-n = 10 × 58; CNN-n = 10 × 29) on a test dataset were performed to assess performance on a slice-by-slice and patient level (dice coefficient/accuracy/sensitivity/specificity/positive and negative predictive value/ROC AUC). Patient-level optimisation was applied to increase the performance regarding predefined statistical metrics. Gradient-weighted class activation mapping (Grad-CAM++) heatmap explainability analysis highlighted image parts with statistically important regions for algorithmic decisions. RESULTS: Regarding SIJ segmentation, a dice coefficient of 0.75 was obtained in the test dataset. For slice-by-slice structural lesion detection, a sensitivity/specificity/ROC AUC of 95%/89%/0.92 and 93%/91%/0.91 were obtained in the test dataset for erosion and ankylosis detection, respectively. For patient-level lesion detection after pipeline optimisation for predefined statistical metrics, a sensitivity/specificity of 95%/85% and 82%/97% were obtained for erosion and ankylosis detection, respectively. Grad-CAM++ explainability analysis highlighted cortical edges as focus for pipeline decisions. CONCLUSIONS: An optimised deep learning pipeline, including an explainability analysis, detects structural lesions of sacroiliitis on pelvic CT scans with excellent statistical performance on a slice-by-slice and patient level. CLINICAL RELEVANCE STATEMENT: An optimised deep learning pipeline, including a robust explainability analysis, detects structural lesions of sacroiliitis on pelvic CT scans with excellent statistical metrics on a slice-by-slice and patient level. KEY POINTS: • Structural lesions of sacroiliitis can be detected automatically in pelvic CT scans. • Both automatic segmentation and disease detection yield excellent statistical outcome metrics. • The algorithm takes decisions based on cortical edges, rendering an explainable solution.

MRI in pediatric sacroiliitis, what radiologists should know.

MRI is used for early detection of inflammation of sacroiliac joints as it shows active lesions of sacroiliitis long before radiographs show damage to the sacroiliac joints. Early diagnosis of arthritis allows early treatment of inflammation and can help delay disease progression and prevent irreversible damage. Also, early identification of axial involvement in juvenile spondyloarthropathy is crucial, as treatment options are different than for peripheral juvenile spondyloarthropathy. In general, standard sequences used in adults are also applied to children. However, interpreting MR images of pediatric sacroiliac joints is more challenging than in adults, because of normal physiological changes during skeletal maturation, which can simulate disease on MR images. Furthermore, classical definitions of sacroiliitis used in adults, for both active inflammatory and structural lesions, can be difficult to extrapolate to children. The development of reliable pediatric-specific definitions for sacroiliitis is still in active study. Understanding both normal and pathological signal changes in children is important to distinguish physiologic findings from disease and to make a correct diagnosis. In this review, the main imaging characteristics of sacroiliitis on MRI in children and its frequent pitfalls will be illustrated, while also citing some discussion points regarding the scan protocol.

Prevalence and neglected rate of sacroiliitis on lumbar spine CT in patients with low back pain.

OBJECTIVE: The study aims to investigate the prevalence and neglected rate of sacroiliitis on lumbar spine computed tomography (CT) in patients with low back pain. MATERIALS AND METHODS: From January 2016 to December 2020, a total of 4827 patients (mean age: 35.4 ± 9.5 years) who underwent lumbar spine CT examinations were included in this retrospective study. The CT degree of sacroiliitis in all study population were retrospectively reviewed by two radiologists. The independent sample t-test was used to compare the continuous values and chi-squared or Fisher's exact test was used to compare the categorized values. RESULTS: Sacroiliitis was identified in 514 of 4827 patients (10.6%). Patients with sacroiliitis were significantly younger than those without sacroiliitis (32.1 ± 8.9 vs. 35.8 ± 9.5 years, p < 0.001). Moreover, significantly more patients with sacroiliitis had HLA-B27 (p < 0.001) positivity and inflammatory back pain syndrome (p = 0.003) than those without sacroiliitis. Among the 514 patients, sacroiliitis was recognized on primary reading in 386 patients (75.1%) but was neglected in the remaining 128 patients (24.9%). Of the 386 patients, 371 patients were followed up, and finally, 295 patients of them (79.5%) were diagnosed with axSpA. CONCLUSION: Radiologists should pay careful and more attention to sacroiliac joint on lumbar spine CT for early diagnosis of sacroiliitis in young patients with low back pain, which could result in early diagnosis and treatment of axSpA.

Fusion and patient-reported outcomes after navigated decortication and direct arthrodesis in minimally invasive sacroiliac joint fusion using cylindrical threaded implants: a case series and literature review.

OBJECTIVE: Sacroiliac joint (SIJ) dysfunction is a significant cause of back pain. Despite recent advances in minimally invasive (MIS) SIJ fusion, the fusion rate remains controversial. This study sought to demonstrate that a navigated decortication and direct arthrodesis technique in MIS SIJ fusion would result in satisfactory fusion rates and patient-reported outcomes (PROs). METHODS: The authors retrospectively reviewed consecutive patients who underwent MIS SIJ fusion from 2018 to 2021. SIJ fusion was performed using cylindrical threaded implants and SIJ decortication employing the O-arm surgical imaging system and StealthStation. The primary outcome was fusion, evaluated using CT at 6, 9, and 12 months postoperatively. Secondary outcomes included revision surgery, time to revision surgery, visual analog scale (VAS) score for back pain, and the Oswestry Disability Index (ODI), measured preoperatively and 6 and 12 months postoperatively. Patient demographics and perioperative data were also collected. PROs over time were analyzed using ANOVA followed by a post hoc analysis. RESULTS: One hundred eighteen patients were included in this study. The mean (± SD) patient age was 58.56 ± 13.12 years, and most patients were female (68.6% vs 31.4% male). There were 19 smokers (16.1%) with an average BMI of 29.92 ± 6.73. One hundred twelve patients (94.9%) underwent successful fusion on CT. The ODI improved significantly from baseline to 6 months (Δ7.73, 95% CI 2.43-13.03, p = 0.002) and from baseline to 12 months (Δ7.54, 95% CI 1.65-13.43, p = 0.008). Similarly, VAS back pain scores improved significantly from baseline to 6 months (Δ2.31, 95% CI 1.07-3.56, p < 0.001) and from baseline to 12 months (Δ1.63, 95% CI 0.25-3.00, p = 0.015). CONCLUSIONS: MIS SIJ fusion with navigated decortication and direct arthrodesis was associated with a high fusion rate and significant improvement in disability and pain scores. Further prospective studies examining this technique are warranted.

Clues for inflammatory diseases in the differential diagnosis of a child with sacroiliitis.

BACKGROUND: The purpose of this study was to compare the demographic, clinical and laboratory characteristics of patients with enthesitis-related arthritis (ERA), familial Mediterranean fever (FMF) and inflammatory bowel disease (IBD), which are inflammatory diseases that may develop sacroiliitis. Thus, it was aimed to reveal various findings that may indicate primary disease in patients with sacroiliitis. METHODS: Pediatric patients aged 6-18 years, who were being followed with a diagnosis of ERA (n = 62), FMF (n = 590), and IBD (n = 56) over the period 2013-2021 were included in the study. Sacroiliitis (n = 55) was diagnosed by magnetic resonance imaging of the sacroiliac joint, obtained from clinically suspected patients. RESULTS: Sacroiliitis was detected in 54.8% of ERA patients, 2.3% of FMF patients, and 12.5% of IBD patients. The mean follow-up period was 4.1 ± 2.8 years (10 months-8 years) for the entire study group. The most common MRI finding for sacroiliitis was bone marrow edema. Peripheral joint involvement (73.5%) and HLA B27 positivity (64.7%) was significantly higher in ERA patients, and ERA was diagnosed more frequently in patients presenting with sacroiliitis. Non-steroidal anti-inflammatory drugs (NSAIDs) were the first choice of treatment agent when sacroiliitis developed in all three patient groups. CONCLUSIONS: The clinical and laboratory findings of ERA, FMF and IBD can sometimes be intertwined or can even coexist. Treatment may differ depending on the disease associated with sacroiliitis, although NSAIDs may be used in the first-line treatment of all three diseases. Sacroiliitis patients with HLA B27 positivity and peripheral arthritis may need to be addressed as ERA.

Automatic Image Segmentation and Grading Diagnosis of Sacroiliitis Associated with AS Using a Deep Convolutional Neural Network on CT Images.

Ankylosing spondylitis (AS) is a chronic inflammatory disease that causes inflammatory low back pain and may even limit activity. The grading diagnosis of sacroiliitis on imaging plays a central role in diagnosing AS. However, the grading diagnosis of sacroiliitis on computed tomography (CT) images is viewer-dependent and may vary between radiologists and medical institutions. In this study, we aimed to develop a fully automatic method to segment sacroiliac joint (SIJ) and further grading diagnose sacroiliitis associated with AS on CT. We studied 435 CT examinations from patients with AS and control at two hospitals. No-new-UNet (nnU-Net) was used to segment the SIJ, and a 3D convolutional neural network (CNN) was used to grade sacroiliitis with a three-class method, using the grading results of three veteran musculoskeletal radiologists as the ground truth. We defined grades 0-I as class 0, grade II as class 1, and grades III-IV as class 2 according to modified New York criteria. nnU-Net segmentation of SIJ achieved Dice, Jaccard, and relative volume difference (RVD) coefficients of 0.915, 0.851, and 0.040 with the validation set, respectively, and 0.889, 0.812, and 0.098 with the test set, respectively. The areas under the curves (AUCs) of classes 0, 1, and 2 using the 3D CNN were 0.91, 0.80, and 0.96 with the validation set, respectively, and 0.94, 0.82, and 0.93 with the test set, respectively. 3D CNN was superior to the junior and senior radiologists in the grading of class 1 for the validation set and inferior to expert for the test set (P < 0.05). The fully automatic method constructed in this study based on a convolutional neural network could be used for SIJ segmentation and then accurately grading and diagnosis of sacroiliitis associated with AS on CT images, especially for class 0 and class 2. The method for class 1 was less effective but still more accurate than that of the senior radiologist.

[Computed tomography versus magnetic resonance imaging : Pros and cons in axial spondyloarthritis]. / Computertomographie versus Magnetresonanztomographie : Pro und Kontra in der axialen Spondyloarthritis.

The diagnosis of axial spondyloarthritis depends on direct visualization of the sacroiliitis in addition to clinical assessment and determination of the histocompatibility antigen HLA-B27. While the value of conventional radiographic images has meanwhile been described in many studies as insufficient to diagnose the disease at an early stage, magnetic resonance imaging and also computed tomography now offer the possibility to visualize findings, such as bone marrow edema, erosion, fat metaplasia, backfill and ankylosis. Thus, it is necessary to decide which procedure should be used and when. Furthermore, both cross-sectional imaging techniques are currently undergoing major changes, and technical advancements are making great strides every year. This article provides an overview of which future technologies will be included in the rheumatological diagnostics of the sacroiliac joints. This overview also illustrates which standard methods are established in the diagnostics of axial spondyloarthritis and how they are used.