深度学习重建的高分辨率3T MRI显示膜迷路
本研究在患者中采集3D-T2及结合深度学习重建的改进T2加权涡轮自旋回波序列(DLR-3D-T2),由两名放射科医生对螺旋板、鼓阶、前庭阶、中阶、椭圆囊、球囊、椭圆囊斑和球囊斑、膜半规管及壶腹神经进行4分制可见度评分,并以离体9.4T MRI作为解剖参考。DLR-3D-T2显著提高了椭圆囊和椭圆囊斑的可见度,95%病例评分≥3(P<.001),但球囊仅10%病例评分≥3,半规管仅部分显示,壶腹神经中度改善。作者认为DLR尚不能提供完整解剖评估,但在无创评估内耳结构方面是重要进步,可能有助于减少对延迟钆增强技术的依赖。
要点
- DLR-3D-T2使椭圆囊和椭圆囊斑95%病例评分≥3(P<.001),球囊仅10%病例评分≥3。
- 耳蜗螺旋板和鼓阶在前2转显示较好,顶转仍显示不佳。
- 半规管仅部分显示,评分≥3者占12.5%至20%,壶腹神经评分≥3者占52.5%至55%。
核心结论
- DLR尚不能提供完整的解剖评估,但在无创评估内耳结构方面是重要进步;在进一步技术改进之前,该方法可能有助于减少对延迟钆增强技术显示膜性结构的依赖。
研究设计与样本
- 研究论文;在患者中采集高分辨率重T2加权TSE SPACE图像,使用3D-T2序列和结合深度学习重建的改进T2加权涡轮自旋回波序列(DLR-3D-T2);两名放射科医生进行4分制定性评分;离体9.4T MRI作为解剖参考。
关键影像表现/征象
- 椭圆囊和椭圆囊斑系统性显示,95%病例评分≥3(P<.001)。
- 球囊仍难以评估,仅10%病例评分≥3。
- 耳蜗螺旋板和鼓阶在前2转显示较好,顶转仍显示不佳。
- 半规管仅部分显示,评分≥3者占12.5%至20%,可能与其直径相关的分辨率限制有关。
- 壶腹神经中度改善,评分≥3者占52.5%至55%,具体取决于神经。
诊断标准与关键数值
- 采用4分制定性评分评估结构可见度,评分≥3定义为可见度良好。
- DLR-3D-T2上椭圆囊和椭圆囊斑评分≥3的病例占95%(P<.001)。
- DLR-3D-T2上球囊评分≥3的病例占10%。
- DLR-3D-T2上半规管评分≥3的病例占12.5%至20%。
- DLR-3D-T2上壶腹神经评分≥3的病例占52.5%至55%。
临床应用与阅片要点
- 阅片时可关注DLR-3D-T2对椭圆囊和椭圆囊斑的显示,95%病例评分≥3。
- 球囊在DLR-3D-T2上仍难以评估,仅10%病例评分≥3。
- 耳蜗螺旋板和鼓阶在前2转显示较好,顶转显示不佳。
- 半规管仅部分显示,评分≥3者占12.5%至20%。
- 壶腹神经中度改善,评分≥3者占52.5%至55%。
局限性
- DLR尚不能提供完整的解剖评估。
- 球囊仍难以评估,仅10%病例评分≥3。
- 耳蜗螺旋板和鼓阶在顶转仍显示不佳。
- 半规管仅部分显示,评分≥3者占12.5%至20%,可能与其直径相关的分辨率限制有关。
- 需进一步技术改进(pending further technical refinements)。
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: The labyrinth is a complex anatomic structure in the temporal bone. However, high-resolution imaging of its membranous portion is challenging because of its small size and the limitations of current MRI techniques. Deep learning reconstruction (DLR) represents a promising approach to advancing MR image quality, enabling higher spatial resolution and reduced noise. This study aims to evaluate DLR high-resolution 3D heavy T2-weighted TSE (3D-T2) MRI sequences for visualizing the labyrinthine structures, comparing them with conventional 3D-T2 sequences. The goal is to improve spatial resolution without prolonging acquisition times, allowing a more detailed view of the labyrinthine microanatomy.
MATERIALS AND METHODS: High-resolution heavy T2-weighted TSE SPACE images were acquired in patients by using 3D-T2 and improved T2 weighted turbo spin-echo sequence incorporating deep learning reconstruction (DLR-3D-T2). Two radiologists rated structure visibility on a 4-point qualitative scale for the spiral lamina, scala tympani, scala vestibuli, scala media, utricle, saccule, utricular and saccular maculae, membranous semicircular ducts, and ampullary nerves. Ex vivo 9.4T MRI served as an anatomic reference.
RESULTS: DLR-3D-T2 significantly improved the visibility of several inner ear structures. The utricle and utricular macula were systematically visualized, achieving grades ≥3 in 95% of cases (P < .001), while the saccule remained challenging to assess, with grades ≥3 in only 10% of cases. The cochlear spiral lamina and scala tympani were better delineated in the first 2 turns but remained poorly visible in the apical turn. Semicircular ducts were only partially visualized, with grades ≥3 in 12.5% to 20% of cases, likely due to resolution limitations relative to their diameter. Ampullary nerves were moderately improved, with grades ≥3 in 52.5% to 55% of cases, depending on the nerve.
CONCLUSIONS: While DLR does not yet provide a complete anatomic assessment, it represents a important step forward in the noninvasive evaluation of inner ear structures. Pending further technical refinements, this approach may help reduce reliance on delayed gadolinium-enhanced techniques for imaging membranous structures.
引用
- Boubaker F, Lane JI, Puel U, et al. High-Resolution 3T MRI of the Membranous Labyrinth Using Deep Learning Reconstruction. AJNR Am J Neuroradiol. 2026. PMID: 40876943. doi:10.3174/ajnr.A8989
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。