Axial Spondyloarthritis: Mimics and Pitfalls of Imaging Assessment

Enhanced diagnosis of axial spondyloarthritis using machine learning with sacroiliac joint MRI: a multicenter study

OBJECTIVES

To develop a machine learning (ML)-based model using MRI and clinical risk factors to enhance diagnostic accuracy for axial spondyloarthritis (axSpA).

METHODS

We retrospectively analyzed datasets from four centers (A-D), focusing on patients with chronic low back pain. A subset from center A was used for prospective validation. A deep learning (DL) model based on ResNet50 was constructed using sacroiliac joint MRI. Clinical variables were integrated with DL scores in ML algorithms to distinguish axSpA from non-axSpA patients. Model performance was assessed by the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy.

RESULTS

The study included 1294 patients (median age 31 years [interquartile range 24-42]; 35.5% females). Clinical risk factors identified were age, sex, and human leukocyte antigen-B27 status. The MRI-based DL model demonstrated an AUC of 0.837, 0.636, 0.724, 0.710, and 0.812 on the internal test set, three external test sets, and the prospective validation set, respectively. The combined model, particularly the K-nearest-neighbors-11 algorithm, demonstrated superior performance across multiple test sets with AUCs ranging from 0.853 to 0.912. It surpassed the Assessment of SpondyloArthritis International Society criteria with better AUC (0.858 vs. 0.650, p < 0.001), sensitivity (87.8% vs. 42.4%, p < 0.001), and accuracy (78.7% vs. 56.9%, p < 0.001).

CONCLUSION

The ML method integrating MRI and clinical risk factors effectively identified axSpA, representing a promising tool for the diagnosis and management of axSpA.

CLINICAL RELEVANCE STATEMENT

The machine learning model combining MRI and clinical risk factors potentially enables earlier diagnosis and intervention for axial spondyloarthritis patients, reducing the delays commonly associated with traditional diagnostic approaches.

KEY POINTS

Axial spondyloarthritis (AxSpA) lacks definitive diagnostic criteria or markers, leading to diagnostic delay. MRI-based deep learning provided quantitative analysis of sacroiliac joint changes indicative of axSpA. A machine learning model combining sacroiliac joint MRI and clinical risk factors enhanced axSpA identification.

Zero Echo Time and Similar Techniques for Structural Changes in the Sacroiliac Joints

Spondyloarthritis (SpA) encompasses inflammatory disorders affecting the axial skeleton, with sacroiliitis as a hallmark feature of axial SpA (axSpA). Imaging plays a vital role in early diagnosis and disease monitoring. Magnetic resonance imaging (MRI) is the preferred modality for detecting early inflammatory changes in axSpA, whereas structural lesions are better visualized using computed tomography (CT). However, synthetic computed tomography (sCT), a technique that generates CT-like images from MRI data, including deep learning methods, zero echo time, ultrashort echo time, and gradient-recalled echo sequences, has emerged as an innovative tool. It offers detailed anatomical resolution without ionizing radiation and combines the advantages of both, MRI and CT, by enabling the simultaneous evaluation of inflammatory and structural lesions. This review explores the potential role of MRI-based sCT in assessing structural changes in the sacroiliac joints, particularly in the context of axSpA, discussing conventional imaging and highlighting the potential of sCT to enhance early detection and monitoring of sacroiliitis.

Diagnostic features of osteitis condensans ilii by MRI-a systematic literature review

OBJECTIVE

To describe and  evaluate the current knowledge of MRI characteristics of osteitis condensans ilii (OCI) in the diagnostics and differentiation of OCI from other conditions.

MATERIALS AND METHODS

The databases PubMed, EMBASE, Scopus, and Web of Science were searched from their inception to March 2024 using the search terms "Magnetic Resonance Imaging" (MESH term in PubMed) and "osteitis condensans ilii" and limited to English language. Two reviewers independently screened titles, abstracts, and full-text eligibility and assessed the risk of bias according to Quality Assessment of Diagnostic Accuracy Studies, QUADAS-2.

RESULTS

The search identified 53 records. Case reports, letters/notes, and conference abstracts were excluded, resulting in 24 reports assessed by full-text, 9 research articles, 14 reviews, and a book chapter. Five retrospective research studies were found eligible for the review. Detailed MRI features of OCI were only described in two studies of patients with pain where they encompassed manifest subchondral iliac sclerosis often accompanied by bone marrow edema (BME) located peripheral to the sclerosis and displaying a continuous distribution and frequently accompanied by sacral BME. Erosions were rare and ankylosis did not occur. Fat deposition in the bone marrow was frequent and similar to BME often located to anterior strain-related joint areas. The QUADAS-2 assessments revealed risks of bias in all studies analyzed, especially regarding general applicability of the MRI features.

CONCLUSION

There is a lack of valid data describing characteristic MRI features in general groups of OCI patients with and without pain.

Defining normal enthesis stiffness range in a healthy adult population

OBJECTIVES

This study explores the correlation between volunteer demographics with enthesis stiffness and intra- and interobserver agreements using shear wave elastography (SWE).

METHODS

Ninety-eight healthy volunteers were recruited. SWE was performed on quadriceps, suprapatellar, infrapatellar, and Achilles entheses. The stiffness measurements were measured in shear wave velocity (SWV).

RESULTS

Mann-Whitney test revealed insignificant difference in SWV among gender. Wilcoxon signed-rank test showed significant difference in SWV between left and right Achilles entheses. Spearman correlation test revealed moderate negative correlation between SWV and age group in quadriceps (ρ, -0.45, P < .01), and weak negative correlation in suprapatellar (ρ, -0.31, P < .01), and left Achilles (ρ, -0.29, P < .01). Multiple linear regression analysis showed subjects' demographic significantly predicted quadriceps, suprapatellar, and left Achilles entheses stiffness with only age statistically significantly to the prediction (P < .05). Kruskal-Wallis showed significant differences in SWV for quadriceps (P = .01), suprapatellar (P = .03), and left Achilles (P = .01) among different age groups. Good interobserver [0.79-0.86 (95% CI, 0.32-0.94)] and interobserver agreement [0.78-0.89 (95% CI, 0.62-0.95)] were found in all the entheses.

CONCLUSION

SWE emerges as a reproducible method for entheses stiffness quantification, with the study highlighting age as a significant factor impacting SWV in quadriceps, suprapatellar, and left Achilles entheses. Among the studied entheses, SWV for Achilles enthesis is the highest in all age groups.

ADVANCES IN KNOWLEDGE

The study significantly contributes to the understanding of enthesis stiffness by exploring the influence of gender, BMI, and age.

Pseudolesions involving bone and soft tissue regarding orthopedic oncology

Pseudolesions in bone and muscle are encountered mostly incidentally in routine imaging studies, especially due to the recent advancements on many different imaging modalities. These lesions can be categorized into the following categories: normal variants; congenital; iatrogenic; degenerative; and postoperative. In this review, we discuss the many different radiological characteristics of musculoskeletal pseudolesions that appear on imaging, which can prevent non-essential additional studies.

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.

Paraneoplastic sacroiliitis

A man in his early 70s presented with stiffness and aching in the shoulder and pelvic girdles. His C reactive protein level was elevated at 116 mg/L, leading to an initial diagnosis of polymyalgia rheumatica. Treatment with prednisone at 20 mg/day provided limited improvement and relapses recurred despite concomitant immunosuppressive agents. Extensive investigations failed to reveal an underlying aetiology.Five years later, gross painless haematuria led to the detection of an invasive papillary urothelial carcinoma. A review of the staging CT scan revealed findings compatible with bilateral erosive sacroiliitis, which had developed since his initial presentation. Radical cystoprostatectomy provided temporary relief but after a further 9 months, symptoms relapsed, and metastatic spread was discovered.Paraneoplastic sacroiliitis is a rare clinical entity; and to the best of our knowledge, this is the first reported case associated with a solid tumour.

MRI Findings in Axial Psoriatic Spondylarthritis

Psoriatic arthritis is a significant medical condition with a high prevalence, a wide variety of non-specific symptoms, and a high degree of overlap with other spondylarthritis disorders, particularly ankylosing spondylitis. Hence, knowledge of the magnetic resonance imaging (MRI) manifestations and a multidisciplinary strategy are required for the better management of these patients. We searched publications from the last 10 years and focused on the most relevant ones which discussed the classification criteria, the MRI characteristics of axial psoriatic arthritis, the importance of MRI for follow up, and the reliability of skin and synovial biopsy. Axial spondylarthritis can be diagnosed and followed up on using the well-established MRI technique and, additionally, a biopsy. The analysis and concordance between them can provide new directions for future studies.

Spondyloarthritis and nonbacterial thrombotic endocarditis as paraneoplastic manifestations in treatment-naive Burkitt lymphoma

Non-radiographic axial spondyloarthropathy (nr-axSpA) is a clinical diagnosis of symptoms matching inflammatory back pain criteria without radiological lesions at the sacroiliac joint. The frequency of an early nr-axSpA-like presentation in lymphoma patients has not been clarified. Here we report a woman in her 20s with a fever and musculoskeletal discomfort. Detailed investigations revealed that she was suffering from Burkitt lymphoma in which nr-axSpA-like symptoms were a musculoskeletal manifestation of the disease, irrelevant to the anti-neoplastic treatment.

The value of magnetic resonance imaging and computed tomography in the study of spinal disorders

Computed tomography (CT) and magnetic resonance imaging (MRI) have replaced conventional radiography in the study of many spinal conditions, it is essential to know when these techniques are indicated instead of or as complementary tests to radiography, which findings can be expected in different clinical settings, and their significance in the diagnosis of different spinal conditions. Proper use of CT and MRI in spinal disorders may facilitate diagnosis and management of spinal conditions. An adequate clinical approach, a good understanding of the pathological manifestations demonstrated by these imaging techniques and a comprehensive report based on a universally accepted nomenclature represent the indispensable tools to improve the diagnostic approach and the decision-making process in patients with spinal pain. Several guidelines are available to assist clinicians in ordering appropriate imaging techniques to achieve an accurate diagnosis and to ensure appropriate medical care that meets the efficacy and safety needs of patients. This article reviews the clinical indications of CT and MRI in different pathologic conditions affecting the spine, including congenital, traumatic, degenerative, inflammatory, infectious and tumor disorders, as well as their main imaging features. It is intended to be a pictorial guide to clinicians involved in the diagnosis and treatment of spinal disorders.

Future of Low-Dose Computed Tomography and Dual-Energy Computed Tomography in Axial Spondyloarthritis

Purpose of Review

Recent technical advances in computed tomography (CT) such as low-dose CT and dual-energy techniques open new applications for this imaging modality in clinical practice and for research purposes. This article will discuss the latest innovations and give a perspective on future developments.

Recent Findings

Low-dose CT has increasingly been used for assessing structural changes at the sacroiliac joints and the spine. It has developed into a method with similar or even lower radiation exposure than radiography while outperforming radiography for lesion detection. Despite being incompatible with low-dose scanning, some studies have shown that dual-energy CT can provide additional information that is otherwise only assessable with magnetic resonance imaging (MRI). However, it is unclear whether this additional information is reliable enough and if it would justify the additional radiation exposure, i.e. whether the performance of dual-energy CT is close enough to MRI to replace it in clinical practice.

Summary

While the role of dual-energy CT in patients with axial spondyloarthritis remains to be established, low-dose CT has developed to an appropriate modality that should replace radiography in many circumstances and might supplement MRI.