Subtle Medical Inc., Menlo Park, CA, USA.
Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA.
Magn Reson Med. 2021 Sep;86(3):1687-1700. doi: 10.1002/mrm.28808. Epub 2021 Apr 29.
With rising safety concerns over the use of gadolinium-based contrast agents (GBCAs) in contrast-enhanced MRI, there is a need for dose reduction while maintaining diagnostic capability. This work proposes comprehensive technical solutions for a deep learning (DL) model that predicts contrast-enhanced images of the brain with approximately 10% of the standard dose, across different sites and scanners.
The proposed DL model consists of a set of methods that improve the model robustness and generalizability. The steps include multi-planar reconstruction, 2.5D model, enhancement-weighted L1, perceptual, and adversarial losses. The proposed model predicts contrast-enhanced images from corresponding pre-contrast and low-dose images. With IRB approval and informed consent, 640 heterogeneous patient scans (56 train, 13 validation, and 571 test) from 3 institutions consisting of 3D T1-weighted brain images were used. Quantitative metrics were computed and 50 randomly sampled test cases were evaluated by 2 board-certified radiologists. Quantitative tumor segmentation was performed on cases with abnormal enhancements. Ablation study was performed for systematic evaluation of proposed technical solutions.
The average peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) between full-dose and model prediction were dB and , respectively. Radiologists found the same enhancing pattern in 45/50 (90%) cases; discrepancies were minor differences in contrast intensity and artifacts, with no effect on diagnosis. The average segmentation Dice score between full-dose and synthesized images was (median = 0.91).
We have proposed a DL model with technical solutions for low-dose contrast-enhanced brain MRI with potential generalizability under diverse clinical settings.
随着对比增强磁共振成像中使用钆基造影剂（GBCA）的安全性担忧不断增加，需要在保持诊断能力的同时降低剂量。本研究提出了一种深度学习（DL）模型的综合技术解决方案，该模型可以预测不同部位和扫描仪的大脑对比增强图像，剂量约为标准剂量的 10%。
所提出的 DL 模型由一组提高模型稳健性和通用性的方法组成。这些步骤包括多平面重建、2.5D 模型、增强加权 L1、感知和对抗性损失。该模型从相应的预对比和低剂量图像预测对比增强图像。本研究获得了 3 个机构的 640 例异质患者扫描（56 例训练、13 例验证和 571 例测试），包括 3D T1 加权脑图像。计算了定量指标，并由 2 名具有董事会认证的放射科医生评估了 50 例随机抽样的测试病例。对异常增强的病例进行了定量肿瘤分割。进行了消融研究以系统评估所提出的技术解决方案。
全剂量和模型预测之间的平均峰值信噪比（PSNR）和结构相似性指数度量（SSIM）分别为 dB 和 。放射科医生在 45/50 例（90%）病例中发现了相同的增强模式；差异仅为对比度强度和伪影的细微差异，不影响诊断。全剂量和合成图像之间的平均分割 Dice 评分分别为 （中位数=0.91）。
我们提出了一种具有技术解决方案的深度学习模型，用于低剂量对比增强脑 MRI，具有在不同临床环境下潜在的通用性。
