深度学习加速3D FLAIR可可靠检测多发性硬化病灶
前瞻性研究纳入76例多发性硬化患者，对比深度学习重建与常规3D FLAIR序列。深度学习重建序列检出所有≥3mm临床相关病灶，读者间完全一致；仅3例（3.95%）漏诊6个<3mm亚阈值病灶，均使用20通道线圈。64通道线圈下两序列质量与病灶检出无差异，深度学习重建序列信噪比和对比噪声比显著更高。
要点
- 深度学习重建3D FLAIR可可靠检出多发性硬化≥3mm病灶，与常规序列读者间完全一致。
- 使用20通道线圈时可能漏诊<3mm亚阈值病灶，64通道线圈可消除此差异。
- 深度学习重建序列信噪比和对比噪声比显著更高，且扫描时间缩短。
关键影像表现/征象
- 深度学习重建FLAIR序列检出所有临床相关病灶（≥3mm），读者间完全一致。
- 3例患者（3.95%；95% CI，1.03%-11.88%）漏诊6个亚阈值病灶（<3mm），均使用20通道线圈扫描。
- 参考FLAIR序列整体图像质量评分略高（均值4.86 [SD，0.35] 对比4.72 [SD，0.52]，P = .01）。
- 使用64通道线圈时，两序列间图像质量和病灶检出无差异。
- 深度学习重建FLAIR序列在所有病例中信噪比和对比噪声比显著更高（P < .001），64通道线圈对比度进一步增加（P = .007）。
诊断标准与关键数值
- 病灶检出：深度学习重建FLAIR序列检出所有≥3mm临床相关病灶，读者间完全一致。
- 亚阈值病灶漏诊率：3.95%（95% CI，1.03%-11.88%），均为20通道线圈扫描的<3mm病灶。
- 图像质量评分：参考序列均值4.86（SD，0.35）对比深度学习重建序列4.72（SD，0.52），P = .01。
- 信噪比和对比噪声比：深度学习重建序列显著更高（P < .001），64通道线圈对比度增加（P = .007）。
临床应用与阅片要点
- 深度学习重建3D FLAIR可用于多发性硬化病灶筛查和随访，尤其适合需要缩短扫描时间的场景。
- 使用20通道线圈时需注意<3mm亚阈值病灶可能漏诊，建议结合64通道线圈或常规序列确认。
- 定量指标（信噪比、对比噪声比）支持深度学习重建图像质量更优，但主观评分略低，阅片时需综合判断。
- 人工智能自动病灶检测与深度学习重建序列结合可保持病灶检出一致性。
局限性
- 单中心前瞻性研究，样本量76例。
- 亚阈值病灶漏诊仅见于20通道线圈，64通道线圈未观察到差异。
- 主观图像质量评分参考序列略高，与定量指标不一致。
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）。
英文原文（摘要）· 点击展开
BACKGROUND AND PURPOSE: Deep learning-based reconstruction has the potential to shorten MRI acquisition while preserving diagnostic image quality, but its reliability for MS lesion detection on 3D FLAIR requires validation. Our aim was to evaluate the diagnostic performance and image quality of a deep learning-reconstructed 3D FLAIR sequence in detecting demyelinating lesions in patients with MS, compared with the conventional reference FLAIR sequence, and to assess the impact of different head coil configurations.
MATERIALS AND METHODS: In this prospective study, 76 patients with MS underwent 3T MRI using both reference and deep learning-reconstructed FLAIR sequences, with identical spatial and contrast parameters. Imaging was alternately performed using either a 20- or a 64-channel head coil. Two blinded radiologists independently assessed the image quality using a 5-point Likert scale and evaluated lesion detection. The SNR and contrast-to-noise ratios were measured, and automated lesion detection was performed using a certified artificial intelligence device.
RESULTS: All clinically relevant lesions (≥3 mm) were detected on the deep learning-reconstructed FLAIR sequence with complete agreement between readers. Six subthreshold lesions (<3 mm) were missed in 3 patients (3.95%; 95% CI, 1.03%-11.88%), all scanned with the 20-channel coil. The reference FLAIR sequence had slightly higher image quality scores overall (mean, 4.86 [SD, 0.35] versus 4.72 [SD, 0.52] P = .01). However, no difference in quality or lesion detection was observed between sequences when using the 64-channel coil. The deep learning-reconstructed FLAIR sequence demonstrated significantly higher SNR and contrast-to-noise ratios across all cases (P < .001), with an additional contrast increase using the 64-channel coil (P = .007). Although subjective evaluation favored the standard reconstruction, quantitative metrics indicated improved image quality with deep learning reconstruction. Automated analysis using an artificial intelligence-based tool confirmed complete concordance in lesion detection between the two sequences.
CONCLUSIONS: The deep learning-reconstructed FLAIR enables reliable detection of demyelinating lesions in MS with significantly reduced scan time without the loss of diagnostic information. Use of a 64-channel coil further enhances image quality, supporting the integration of this accelerated technique into clinical practice.
引用
- Verclytte S, Beaugrard G, Nickel D, et al. Deep Learning-Accelerated 3D FLAIR Enables Reliable MS Lesion Detection. AJNR Am J Neuroradiol. 2026. PMID: 42209146. doi:10.3174/ajnr.A9140
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。