文献速递脊柱关节炎

高分辨率深度学习Dixon磁共振对疑似中轴型脊柱关节炎骶髂关节的诊断非劣效于标准磁共振

High-Resolution Deep Learning Dixon Magnetic Resonance Imaging of the Sacroiliac Joints Is Noninferior to Standard Magnetic Resonance Imaging in Patients With Suspected Axial Spondyloarthritis.
PubMed 文献 · Arthritis Rheumatol · 2026-04-21

研究纳入76例慢性下背痛疑似中轴型脊柱关节炎患者,比较标准多序列3T磁共振与单次高分辨率深度学习重建Dixon序列。DL-Dixon诊断准确性与标准磁共振相似(AUC 0.86对0.87)并满足非劣效标准,扫描时间减少73%,但读者间一致性略低(κ=0.71对0.81)。

要点

  • DL-Dixon诊断疑似axSpA的AUC为0.86,非劣效于标准磁共振的0.87。
  • DL-Dixon将扫描时间从19:49分钟缩短至5:24分钟,减少73%。
  • DL-Dixon对侵蚀、脂肪化生和关节间隙改变的诊断性能良好,对骨炎和硬化仅为一般。

核心结论

  • DL-Dixon在疑似axSpA的骶髂关节MRI评估中提供临床可接受的诊断性能,同时大幅缩短扫描时间。

研究设计与样本

  • 前瞻性比较研究,纳入76例慢性下背痛且疑似axSpA的患者,均接受临床、实验室和遗传评估后行3T标准磁共振与高分辨率DL-Dixon成像,由三名盲法读者评估。
  • 以临床诊断为参考标准评估诊断准确性,以标准磁共振为参考标准进行病变分析,非劣效界值为0.05。

主要发现

  • 19例患者被诊断为axSpA。
  • DL-Dixon的AUC为0.86(95%CI 0.76-0.96),标准磁共振的AUC为0.87(95%CI 0.78-0.96),DL-Dixon满足非劣效标准。
  • 读者间一致性标准磁共振几乎完全一致(κ=0.81),DL-Dixon为实质性一致(κ=0.71)。
  • 病变层面DL-Dixon对侵蚀(AUC 0.83)、脂肪化生(AUC 0.80)和关节间隙改变(AUC 0.80)性能良好,对骨炎(AUC 0.73)和硬化(AUC 0.64)性能一般。
  • DL-Dixon使扫描时间减少73%。

关键数值与推荐

  • 非劣效界值预设为0.05,即DL-Dixon的AUC较标准磁共振下降≤0.05定义为临床可接受。
  • 标准磁共振协议扫描时间19:49分钟,DL-Dixon扫描时间5:24分钟(1 mm各向同性)。

临床怎么用

  • DL-Dixon可作为疑似axSpA骶髂关节MRI的替代方案,在保持临床可接受诊断准确性的同时显著缩短扫描时间,有望提高MRI检查效率和可及性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVE: To compare the multisequence standard magnetic resonance imaging (sMRI) protocol of the sacroiliac joints with a single high-resolution deep learning-reconstructed Dixon sequence (DL-Dixon) in patients with suspected axial spondyloarthritis (axSpA). METHODS: Seventy-six patients with chronic low back pain and suspected axSpA underwent clinical, laboratory, and genetic assessment followed by 3T sMRI (T1, T2 fat saturation, volumetric interpolated breath-hold examination, STIR; 19:49 minutes) and high-resolution DL-Dixon imaging (1 mm isotropic; 5:24 minutes). Three blinded readers assessed overall imaging diagnosis, diagnostic confidence, and lesion presence (osteitis, fat metaplasia, erosions, sclerosis, joint space changes). DL was used solely for image reconstruction. The clinical diagnosis served as the reference for diagnostic accuracy; sMRI served as the reference for lesion analysis. Diagnostic accuracy was expressed as the area under the curve (AUC; balanced accuracy). Noninferiority was tested using a predefined margin of 0.05. A decrease of ≤0.05 compared to sMRI was defined as clinically acceptable. RESULTS: Nineteen patients were diagnosed with axSpA. DL-Dixon showed similar diagnostic performance (AUC 0.86 [95% confidence interval (CI) 0.76-0.96]) compared to sMRI (AUC 0.87 [95% CI 0.78-0.96]) and met noninferiority criteria. Interreader agreement was almost perfect for sMRI (κ = 0.81) and substantial for DL-Dixon (κ = 0.71). At the lesion level, DL-Dixon achieved good performance for erosions (AUC 0.83), fat metaplasia (AUC 0.80), and joint space changes (AUC 0.80), and fair performance for osteitis (AUC 0.73) and sclerosis (AUC 0.64). Using DL-Dixon, scan time was reduced by 73%. CONCLUSION: DL-Dixon provides clinically acceptable diagnostic performance while substantially reducing scan time. This approach may improve efficiency and accessibility of MRI for axSpA assessment.

来源:Arthritis Rheumatol,查看原文。版权归原作者所有。

引用

  1. Deppe D, Koka M, Proft F, et al. High-Resolution Deep Learning Dixon Magnetic Resonance Imaging of the Sacroiliac Joints Is Noninferior to Standard Magnetic Resonance Imaging in Patients With Suspected Axial Spondyloarthritis. Arthritis Rheumatol. 2026. PMID: 42011796. doi:10.1002/art.70195

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。