Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, No. 119, the West Southern 4th Ring Road, Fengtai District, Beijing, 100070, China.
Subtle Medical Inc., Menlo Park, CA, USA.
Eur Radiol. 2021 Sep;31(9):6419-6428. doi: 10.1007/s00330-021-07848-3. Epub 2021 Mar 18.
To evaluate the clinical performance of a deep learning (DL)-based method for brain MRI exams with reduced gadolinium-based contrast agent (GBCA) dose to provide better understanding of the readiness and limitations of this method.
Eighty-three consecutive patients (from March 2019 to August 2019) who underwent brain contrast-enhanced (CE) MRI were included. Three 3D T1-weighted images with zero-dose, low-dose (10%), and full-dose (100%) GBCA were collected. The first 30 cases were used to train a DL model to synthesize the full-dose GBCA images from the zero-dose and low-dose image pairs. The remaining 53 cases were used for testing. The enhancement pattern, number, and location of enhancing lesions were recorded. Overall image quality, image signal noise ratio (SNR), lesion conspicuity, and lesion enhancement were assessed.
Lesion detection from the DL-synthesized CE-MRI image accurately matched those from the true full-dose CE-MRI images in 48 of 53 cases (90.6%). The DL method identified the lesions in 34 of 36 cases (94.4%) with a single enhanced lesion and all lesions in 3 of 6 cases (50.0%) in cases with multiple enhancing lesions. The agreement between synthesized and true full-dose CE-MRI images were 0.73, 0.63, 0.89, and 0.87 for image quality, image SNR, lesion conspicuity, and lesion enhancement, respectively.
The proposed DL method is a feasible way to minimize the dosage of GBCAs in brain MRI without sacrificing the diagnostic information. Missing enhancement of small lesions in patients with multiple lesions was observed, requiring improvements in algorithms or dosage design.
• This study evaluated the clinical performance of a DL-based reconstruction method for significant dose reduction in GBCA contrast-enhanced MRI exams. • The proposed DL method has the potential to satisfy the routine radiological diagnosis needs in certain clinical applications.
评估一种基于深度学习（DL）的方法在脑 MRI 检查中减少钆基对比剂（GBCA）剂量的临床性能，以更好地了解该方法的准备情况和局限性。
纳入 2019 年 3 月至 8 月期间连续 83 例进行脑对比增强（CE）MRI 的患者。采集 3 个零剂量、低剂量（10%）和全剂量（100%）GBCA 的 3D T1 加权图像。前 30 例用于训练 DL 模型，从零剂量和低剂量图像对合成全剂量 GBCA 图像。其余 53 例用于测试。记录增强病变的增强模式、数量和位置。评估整体图像质量、图像信噪比（SNR）、病变显著性和病变增强。
从 DL 合成的 CE-MRI 图像中检测到的病变与 53 例中的 48 例（90.6%）真实全剂量 CE-MRI 图像准确匹配。DL 方法在 36 例中有 34 例（94.4%）单发性增强病变和 6 例中有 3 例（50.0%）多发性增强病变中识别出病变。合成图像与真实全剂量 CE-MRI 图像的图像质量、图像 SNR、病变显著性和病变增强的一致性分别为 0.73、0.63、0.89 和 0.87。
所提出的 DL 方法是一种可行的方法，可以在不牺牲诊断信息的情况下减少脑 MRI 中 GBCA 的剂量。在多发性病变患者中观察到小病变的增强缺失，需要改进算法或剂量设计。
本研究评估了一种基于深度学习（DL）的重建方法在 GBCA 对比增强 MRI 检查中显著减少剂量的临床性能。
所提出的 DL 方法有可能在某些临床应用中满足常规放射诊断需求。
