深度学习系统用于合成膝关节磁共振成像:基于人工智能的脂肪抑制成像是否可行?
单中心研究利用改良卷积神经网络U-Net深度学习系统,从非脂肪抑制图像生成人工智能脂肪抑制MRI,由3名肌骨放射科医生对88例膝关节MR进行两阶段阅片。合成方案对半月板、交叉韧带、副韧带及肌腱撕裂诊断敏感度/特异度高,对软骨缺损和骨髓异常敏感度较低;除软骨评估外,各结构异常两种方法无显著差异,原始与合成方案可互换,合成图像组织对比噪声比更高。
要点
- 人工智能脂肪抑制MRI质量98.9%(87/88)至100%(88/88)评为可诊断。
- 合成方案对半月板、交叉韧带、副韧带及肌腱撕裂诊断敏感度/特异度高。
- 软骨缺损和骨髓异常敏感度较低(77%和76%),除软骨外两方法无显著差异。
核心结论
- 基于人工智能的脂肪抑制MRI(3D AFSMRI)可行,提供快速成像方法,与原始3D MR序列相比膝关节结构异常检出率相似。
研究设计与样本
- 单中心研究,经机构审查委员会批准;使用改良卷积神经网络U-Net深度学习系统,训练集25,920幅图像、验证集16,416幅图像;3名肌骨放射科医生分2次阅片88例膝关节MR(原始PD+FSPD与合成PD+AFSMRI);以原始MRI序列为参考标准;采用完全平衡设计,所有读者阅所有图像相同次数。
关键影像表现/征象
- 人工智能脂肪抑制MRI质量评为可诊断的比例为98.9%(87/88)至100%(88/88),所有读者一致。
- 通过对比噪声比评估的所有组织显着性在AFSMRI上高于原始FSPD图像(P < 0.05)。
诊断标准与关键数值
- 合成方案诊断半月板撕裂敏感度91%(71/78)、特异度86%(84/98)。
- 合成方案诊断交叉韧带撕裂敏感度92%(12/13)、特异度98%(160/163)。
- 合成方案诊断副韧带撕裂敏感度80%(16/20)、特异度100%(156/156)。
- 合成方案诊断肌腱撕裂敏感度90%(9/10)、特异度100%(166/166)。
- 合成方案诊断软骨缺损总体敏感度77%(170/221)、特异度93%(287/307);诊断骨髓异常总体敏感度76%(95/125)、特异度90%(443/491)。
临床应用与阅片要点
- 合成方案与原始方案在几乎所有评估结构(半月板、交叉韧带、副韧带、骨髓异常)的方法间一致性为中等到相当。
- 所有读者对所有结构异常两方法间无显著差异(P > 0.05),软骨评估除外。
- 几乎所有评估结构的观察者间一致性为中等到相当。
- 原始与合成方案对所有评估结构的诊断可互换;所有组合常见精确匹配比例无显著差异(P > 0.01)。
局限性
- 原文未报告局限性。
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)。
英文原文(摘要)· 点击展开
MATERIALS AND METHODS: This single-center study was approved by the institutional review board. Artificial intelligence-based FS MRI scans were created from non-FS images using a deep learning system with a modified convolutional neural network-based U-Net that used a training set of 25,920 images and validation set of 16,416 images. Three musculoskeletal radiologists reviewed 88 knee MR studies in 2 sessions, the original (proton density [PD] + FSPD) and the synthetic (PD + AFSMRI). Readers recorded AFSMRI quality (diagnostic/nondiagnostic) and the presence or absence of meniscal, ligament, and tendon tears; cartilage defects; and bone marrow abnormalities. Contrast-to-noise rate measurements were made among subcutaneous fat, fluid, bone marrow, cartilage, and muscle. The original MRI sequences were used as the reference standard to determine the diagnostic performance of AFSMRI (combined with the original PD sequence). This is a fully balanced study design, where all readers read all images the same number of times, which allowed the determination of the interchangeability of the original and synthetic protocols. Descriptive statistics, intermethod agreement, interobserver concordance, and interchangeability tests were applied. A P value less than 0.01 was considered statistically significant for the likelihood ratio testing, and P value less than 0.05 for all other statistical analyses.
RESULTS: Artificial intelligence-based FS MRI quality was rated as diagnostic (98.9% [87/88] to 100% [88/88], all readers). Diagnostic performance (sensitivity/specificity) of the synthetic protocol was high, for tears of the menisci (91% [71/78], 86% [84/98]), cruciate ligaments (92% [12/13], 98% [160/163]), collateral ligaments (80% [16/20], 100% [156/156]), and tendons (90% [9/10], 100% [166/166]). For cartilage defects and bone marrow abnormalities, the synthetic protocol offered an overall sensitivity/specificity of 77% (170/221)/93% (287/307) and 76% (95/125)/90% (443/491), respectively. Intermethod agreement ranged from moderate to substantial for almost all evaluated structures (menisci, cruciate ligaments, collateral ligaments, and bone marrow abnormalities). No significant difference was observed between methods for all structural abnormalities by all readers (P > 0.05), except for cartilage assessment. Interobserver agreement ranged from moderate to substantial for almost all evaluated structures. Original and synthetic protocols were interchangeable for the diagnosis of all evaluated structures. There was no significant difference for the common exact match proportions for all combinations (P > 0.01). The conspicuity of all tissues assessed through contrast-to-noise rate was higher on AFSMRI than on original FSPD images (P < 0.05).
CONCLUSIONS: Artificial intelligence-based FS MRI (3D AFSMRI) is feasible and offers a method for fast imaging, with similar detection rates for structural abnormalities of the knee, compared with original 3D MR sequences.
引用
- Fayad LM, Parekh VS, de Castro Luna R, et al. A Deep Learning System for Synthetic Knee Magnetic Resonance Imaging: Is Artificial Intelligence-Based Fat-Suppressed Imaging Feasible? Invest Radiol. 2021. PMID: 33350717. doi:10.1097/RLI.0000000000000751
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。