Improved detection of subchondral erosions in the sacroiliac joints with T1-weighted fat-suppressed MRI

An Evaluation of Magnetic Resonance Imaging Dixon Sequence Fat-Water Separation Techniques (T2w Dixon FSTs) to Detect Dorso-Lumbar Structural Lesions in Patients with Axial Spondyloarthritis

OBJECTIVE

The aim of this study was to assess and compare the diagnostic accuracy of two MRI techniques for identifying structural bone lesions (fatty lesions [BMFs], subchondral erosions [BMEs], sclerosis [BMS], and ankylosis [A]) in the dorso-lumbar joints. This assessment specifically focused on the application of MRI Dixon sequence fat-water separation techniques (T2w Dixon FSTs) when acquiring T1-weighted (T1w) images as the reference standard, among patients diagnosed with axial spondyloarthritis (SpA).

METHODS

Conducted at a single center, this study involved the recruitment of patients who underwent both spinal and sacroiliac (SI) joint MRI between 2019 and 2022, with follow-up continuing until 2023. In 2023, three independent readers reassessed the initial MRI datasets to evaluate specific radiological features of SpA. They recorded confidence estimates regarding the use of T2w Dixon FSTs when acquiring T1w images. The centralized MRI interpretations were then compared to established rheumatologic diagnoses.

RESULTS

A total of 73 patients (42 men and 31 women) were included in the study. The mean sensitivity, specificity, and accuracy of T2w Dixon FSTs (fat-only images) were at least 75%, 100%, and 96%, respectively, based on the 2023 assessment for all considered items. The diagnostic performance of T2w Dixon FSTs was comparable to that of T1w images.

CONCLUSIONS

The diagnostic performance of T2w Dixon FSTs (fat-only images) matched that of T1w images not only in assessing structural and fatty lesions, but also in the evaluation of subchondral erosions, sclerosis, and ankylosis in the dorso-lumbar joints of patients with a rheumatologic diagnosis of SpA. These findings suggest the potential avoidance of T1-weighted images when employing multi-parameter, multi-sequence imaging, such as the Dixon sequence.

Update of imaging in the assessment of axial spondyloarthritis

This update addresses new developments in imaging of axial spondyloarthritis from the past 5 years. These have focused mostly on enhanced CT and MRI-based technologies that bring greater precision to the assessment of both inflammatory and structural lesions in the sacroiliac joint. An international consensus has recommended a 4-sequence MRI for routine diagnostic evaluation of the sacroiliac joint aimed at depicting the location and extent of inflammation as well as an erosion-sensitive sequence for structural damage. The latter include high resolution thin slice sequences that accentuate the interface between subchondral bone and the overlying cartilage and joint space as well as synthetic CT, a deep learning-based technique that transforms certain MRI sequences into images resembling CT. Algorithms based on deep learning derived from plain radiographic, CT, and MRI datasets are increasingly more accurate at identifying sacroiliitis and individual lesions observed on images of the sacroiliac joints and spine.

Imaging of Sacroiliac Joints

The central role of imaging in diagnosing disorders affecting the sacroiliac joints (SIJs) necessitates a comprehensive understanding of the advantages, limitations, and potential pitfalls of the imaging techniques that can be used. In this article, the anatomy and biomechanics of SIJs are exposed, outlining their unique features, particularly the division into anteroinferior cartilaginous and postero-superior ligamentous parts. Overall, the goal of this article is to offer a comprehensive understanding of imaging techniques, anatomic complexity, and diagnostic considerations relevant to SIJs disorders, facilitating accurate diagnosis and patient management in clinical practice and research.

Research on automatic recognition radiomics algorithm for early sacroiliac arthritis based on sacroiliac MRI imaging

OBJECTIVE

To create an automated machine learning model using sacroiliac joint MRI imaging for early sacroiliac arthritis detection, aiming to enhance diagnostic accuracy.

METHODS

We conducted a retrospective analysis involving 71 patients with early sacroiliac arthritis and 85 patients with normal sacroiliac joint MRI scans. Transverse T1WI and T2WI sequences were collected and subjected to radiomics analysis by two physicians. Patients were randomly divided into training and test groups at a 7:3 ratio. Initially, we extracted the region of interest on the sacroiliac joint surface using ITK-SNAP 3.6.0 software and extracted radiomic features. We retained features with an Intraclass Correlation Coefficient > 0.80, followed by filtering using max-relevance and min-redundancy (mRMR) and LASSO algorithms to establish an automatic identification model for sacroiliac joint surface injury. Receiver operating characteristic (ROC) curves were plotted, and the area under the ROC curve (AUC) was calculated. Model performance was assessed by accuracy, sensitivity, and specificity.

RESULTS

We evaluated model performance, achieving an AUC of 0.943 for the SVM-T1WI training group, with accuracy, sensitivity, and specificity values of 0.878, 0.836, and 0.943, respectively. The SVM-T1WI test group exhibited an AUC of 0.875, with corresponding accuracy, sensitivity, and specificity values of 0.909, 0.929, and 0.875, respectively. For the SVM-T2WI training group, the AUC was 0.975, with accuracy, sensitivity, and specificity values of 0.933, 0.889, and 0.750. The SVM-T2WI test group produced an AUC of 0.902, with accuracy, sensitivity, and specificity values of 0.864, 0.889, and 0.800. In the SVM-bimodal training group, we achieved an AUC of 0.974, with accuracy, sensitivity, and specificity values of 0.921, 0.889, and 0.971, respectively. The SVM-bimodal test group exhibited an AUC of 0.964, with accuracy, sensitivity, and specificity values of 0.955, 1.000, and 0.875, respectively.

CONCLUSION

The radiomics-based detection model demonstrates excellent automatic identification performance for early sacroiliitis.

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.