深度学习生成合成双反转恢复图像改善多发性硬化病灶检测
该回顾性研究从2014至2016年前瞻性观察队列中随机选取100例多发性硬化患者,用其中50例训练人工神经网络(DiamondGAN)由T1、T2和FLAIR生成合成双反转恢复(synthDIR)图像,并在另50例中与常规DIR(trueDIR)及FLAIR比较病灶检出;synthDIR检出病灶数显著多于FLAIR(31.4±20.7 vs 22.8±12.7,P<0.001),主要归因于近皮质病灶显示改善(12.3±10.8 vs 7.2±5.6,P<0.001),synthDIR对比噪声比高于FLAIR(22.0±6.4 vs 16.7±3.6,P=0.009),与trueDIR无显著差异(22.0±6.4 vs 22.4±7.9,P=0.87)。
要点
- synthDIR检出多发性硬化病灶数显著多于FLAIR(31.4±20.7 vs 22.8±12.7,P<0.001)。
- 病灶检出提升主要来自近皮质病灶显示改善(12.3±10.8 vs 7.2±5.6,P<0.001)。
- synthDIR对比噪声比高于FLAIR(22.0±6.4 vs 16.7±3.6,P=0.009),与trueDIR无显著差异(22.0±6.4 vs 22.4±7.9,P=0.87)。
核心结论
- 计算生成的DIR图像较标准序列改善病灶显示,提示人工智能可帮助改善特定病变的影像检查。
研究设计与样本
- 回顾性分析,从2014至2016年前瞻性观察队列中随机选取100例多发性硬化患者(65例女性,年龄37[22-68]岁);50例用于训练人工神经网络(DiamondGAN)由T1、T2和FLAIR生成synthDIR,另50例用于评估;由2名独立读者在不知DIR图像来源的情况下评估病灶,以Wilcoxon符号秩检验比较病灶数并进行读者间分析。
关键影像表现/征象
- synthDIR检出病灶数显著多于FLAIR(31.4±20.7 vs 22.8±12.7,P<0.001)。
- 近皮质病灶在synthDIR上检出数显著多于FLAIR(12.3±10.8 vs 7.2±5.6,P<0.001)。
- synthDIR对比噪声比高于FLAIR(22.0±6.4 vs 16.7±3.6,P=0.009),与trueDIR无显著差异(22.0±6.4 vs 22.4±7.9,P=0.87)。
诊断标准与关键数值
- 读者间可靠性:FLAIR为0.92(95%CI 0.85-0.95),synthDIR为0.93(95%CI 0.87-0.96),trueDIR为0.95(95%CI 0.85-0.98)。
临床应用与阅片要点
- synthDIR由标准采集的T1、T2和FLAIR生成,阅片时可将其与常规序列对照以辅助多发性硬化病灶检测。
- synthDIR对近皮质病灶显示优于FLAIR,阅片时关注近皮质区域病灶计数。
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
OBJECTIVES: The aim of the study was to implement a deep-learning tool to produce synthetic double inversion recovery (synthDIR) images and compare their diagnostic performance to conventional sequences in patients with multiple sclerosis (MS).
MATERIALS AND METHODS: For this retrospective analysis, 100 MS patients (65 female, 37 [22-68] years) were randomly selected from a prospective observational cohort between 2014 and 2016. In a subset of 50 patients, an artificial neural network (DiamondGAN) was trained to generate a synthetic DIR (synthDIR) from standard acquisitions (T1, T2, and fluid-attenuated inversion recovery [FLAIR]). With the resulting network, synthDIR was generated for the remaining 50 subjects. These images as well as conventionally acquired DIR (trueDIR) and FLAIR images were assessed for MS lesions by 2 independent readers, blinded to the source of the DIR image. Lesion counts in the different modalities were compared using a Wilcoxon signed-rank test, and interrater analysis was performed. Contrast-to-noise ratios were compared for objective image quality.
RESULTS: Utilization of synthDIR allowed to detect significantly more lesions compared with the use of FLAIR images (31.4 ± 20.7 vs 22.8 ± 12.7, P < 0.001). This improvement was mainly attributable to an improved depiction of juxtacortical lesions (12.3 ± 10.8 vs 7.2 ± 5.6, P < 0.001). Interrater reliability was excellent in FLAIR 0.92 (95% confidence interval [CI], 0.85-0.95), synthDIR 0.93 (95% CI, 0.87-0.96), and trueDIR 0.95 (95% CI, 0.85-0.98).Contrast-to-noise ratio in synthDIR exceeded that of FLAIR (22.0 ± 6.4 vs 16.7 ± 3.6, P = 0.009); no significant difference was seen in comparison to trueDIR (22.0 ± 6.4 vs 22.4 ± 7.9, P = 0.87).
CONCLUSIONS: Computationally generated DIR images improve lesion depiction compared with the use of standard modalities. This method demonstrates how artificial intelligence can help improving imaging in specific pathologies.
引用
- Finck T, Li H, Grundl L, et al. Deep-Learning Generated Synthetic Double Inversion Recovery Images Improve Multiple Sclerosis Lesion Detection. Invest Radiol. 2020. PMID: 31977602. doi:10.1097/RLI.0000000000000640
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。