Huang Qi, Tang Haoteng, Wang Keyan, Li Ran, Eldeniz Cihat, Nguyen Natalie, Schindler Thomas H, Peterson Linda R, Yang Yang, Yan Yan, Cheng Jingliang, Woodard Pamela K, Zheng Jie
Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, Missouri, USA.
Department of Computer Science, University of Texas Rio Grande Valley, Edinburg, Texas, USA.
Magn Reson Med. 2025 Oct;94(4):1793-1803. doi: 10.1002/mrm.30555. Epub 2025 May 1.
To develop a model-driven, self-supervised deep learning network for end-to-end simultaneous mapping of myocardial oxygen extraction fraction (mOEF) and myocardial blood volume (MBV).
An asymmetrical spin echo-prepared sequence was used to acquire mOEF and MBV images. By integrating a physical model into the training process, a self-supervised learning (SSL) pattern can be regulated. A loss function consisted of the mean squared error, plus cosine similarity was used to improve the performance of network predictions for estimating mOEF and MBV simultaneously. The SSL network was trained and evaluated using simulated data with ground truths and human data in vivo from 10 healthy subjects and 10 patients with myocardial infarction.
In the simulation study, the SSL method demonstrated the ability of generating relatively accurate mOEF, MBV, and ΔB maps simultaneously. In the in vivo study, healthy volunteers had an average mOEF of 0.6-0.7 and MBV of 0.11-0.13, comparable to literature-reported values. In the myocardial infarction regions, the average mOEF and MBV in 5 tested patients reduced to 0.45 ± 0.09 and 0.09 ± 0.02, which were significantly lower (p < 0.001) than those in normal regions (0.67 ± 0.04 and 0.13 ± 0.01, respectively).
This work has demonstrated the initial feasibility of generating mOEF and MBV maps simultaneously by a model-driven, self-supervised learning method.
开发一种模型驱动的自监督深度学习网络，用于心肌氧摄取分数（mOEF）和心肌血容量（MBV）的端到端同步映射。
使用非对称自旋回波准备序列获取mOEF和MBV图像。通过将物理模型集成到训练过程中，可以调节自监督学习（SSL）模式。使用均方误差加余弦相似度组成的损失函数来提高网络同时估计mOEF和MBV预测的性能。使用具有真实值的模拟数据以及来自10名健康受试者和10名心肌梗死患者的体内人体数据对SSL网络进行训练和评估。
在模拟研究中，SSL方法展示了同时生成相对准确的mOEF、MBV和ΔB图的能力。在体内研究中，健康志愿者的平均mOEF为0.6 - 0.7，MBV为0.11 - 0.13，与文献报道值相当。在心肌梗死区域，5名受试患者的平均mOEF和MBV分别降至0.45±0.09和0.09±0.02，显著低于正常区域（分别为0.67±0.04和0.13±0.01，p < 0.001）。
这项工作证明了通过模型驱动的自监督学习方法同时生成mOEF和MBV图的初步可行性。
