文献速递神经技术与安全MR

人工智能T1加权增强脑MRI:一种用于对比信号提取的深度学习方法

Artificial T1-Weighted Postcontrast Brain MRI: A Deep Learning Method for Contrast Signal Extraction.
PubMed 文献 · Invest Radiol · 2024-07-30

这项前瞻性研究纳入213名接受脑MRI的参与者,比较两种重实现的先进深度学习方法和一种提出的对比信号提取方法,从平扫和低剂量(0.02 mmol/kg)图像合成人工全剂量(0.1 mmol/kg)T1加权图像。基于读者的研究显示,提出的方法C在可互换性和病灶强化符合度上显著优于设置A和B,但该剂量下仍有相当比例图像与参考图像互换性不足。

要点

  • 在低剂量0.02 mmol/kg下,方法C合成的人工全剂量图像完全或大部分可互换的比例为70/100,高于方法A的40/100和方法B的57/100。
  • 方法C的病灶强化平均降低幅度为-0.50±0.55,小于方法A的-1.10±0.98和方法B的-0.91±0.67。
  • 方法C的病灶符合度平均评分为2.48±0.91,高于方法A的1.75±1.07和方法B的2.19±1.04。

核心结论

  • 提出的对比信号提取方法在合成增强后图像方面显示出显著改善,但该剂量下仍有相当比例图像与参考图像的互换性不足。

研究设计与样本

  • 前瞻性研究,纳入213名参与者,于2021年8月至10月接受脑MRI,包括低剂量(0.02 mmol/kg)和全剂量(0.1 mmol/kg)图像;训练前随机留出50名参与者作为测试集(平均年龄±标准差52.6±15.3岁;30名男性);比较两种重实现的先进深度学习方法(设置A和B)和提出的对比信号提取方法(设置C)。

诊断标准与关键数值

  • 基于读者的研究由两名读者记录所有假阳性病灶并以5点Likert量表(0为最差)评分:设置A-C每名参与者的平均假阳性数分别为0.33±0.93、0.07±0.33和0.05±0.22;设置C被评为完全或大部分可互换的扫描比例为70/100,高于设置A的40/100(P<0.001)和设置B的57/100(P<0.001);设置C病灶强化平均降低-0.50±0.55,小于设置A的-1.10±0.98和设置B的-0.91±0.67(均P<0.001);设置A-C病灶符合度平均评分分别为1.75±1.07、2.19±1.04和2.48±0.91,所有设置间差异显著(均P<0.001)。

临床应用与阅片要点

  • 原文未据此给出推荐。

局限性

  • 该剂量下仍有相当比例图像与参考图像的互换性不足。

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: Reducing gadolinium-based contrast agents to lower costs, the environmental impact of gadolinium-containing wastewater, and patient exposure is still an unresolved issue. Published methods have never been compared. The purpose of this study was to compare the performance of 2 reimplemented state-of-the-art deep learning methods (settings A and B) and a proposed method for contrast signal extraction (setting C) to synthesize artificial T1-weighted full-dose images from corresponding noncontrast and low-dose images.

MATERIALS AND METHODS: In this prospective study, 213 participants received magnetic resonance imaging of the brain between August and October 2021 including low-dose (0.02 mmol/kg) and full-dose images (0.1 mmol/kg). Fifty participants were randomly set aside as test set before training (mean age ± SD, 52.6 ± 15.3 years; 30 men). Artificial and true full-dose images were compared using a reader-based study. Two readers noted all false-positive lesions and scored the overall interchangeability in regard to the clinical conclusion. Using a 5-point Likert scale (0 being the worst), they scored the contrast enhancement of each lesion and its conformity to the respective reference in the true image.

RESULTS: The average counts of false-positives per participant were 0.33 ± 0.93, 0.07 ± 0.33, and 0.05 ± 0.22 for settings A-C, respectively. Setting C showed a significantly higher proportion of scans scored as fully or mostly interchangeable (70/100) than settings A (40/100, P < 0.001) and B (57/100, P < 0.001), and generated the smallest mean enhancement reduction of scored lesions (-0.50 ± 0.55) compared with the true images (setting A: -1.10 ± 0.98; setting B: -0.91 ± 0.67, both P < 0.001). The average scores of conformity of the lesion were 1.75 ± 1.07, 2.19 ± 1.04, and 2.48 ± 0.91 for settings A-C, respectively, with significant differences among all settings (all P < 0.001).

CONCLUSIONS: The proposed method for contrast signal extraction showed significant improvements in synthesizing postcontrast images. A relevant proportion of images showing inadequate interchangeability with the reference remains at this dosage.

来源:Invest Radiol,查看原文。版权归原作者所有。

引用

  1. Haase R, Pinetz T, Kobler E, et al. Artificial T1-Weighted Postcontrast Brain MRI: A Deep Learning Method for Contrast Signal Extraction. Invest Radiol. 2024. PMID: 39074258. doi:10.1097/RLI.0000000000001107

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。