Anatomic and Molecular MR Image Synthesis Using Confidence Guided CNNs.
Anatomic and Molecular MR Image Synthesis Using Confidence Guided CNNs.
复制标题
DOI：
10.1109/tmi.2020.3046460
复制
发表时间：
2021-10
影响因子：
10.6
通讯作者：
Jiang S
中科院分区：
文献类型：
--
作者：
Guo P;Wang P;Yasarla R;Zhou J;Patel VM;Jiang S
数据驱动的自动方法已经证明了它们在解决神经肿瘤学中各种临床诊断困境方面的巨大潜力，特别是在标准解剖和先进分子MR图像的帮助下。然而，数据的数量和质量仍然是一个关键的决定因素，也是潜在应用的一个重大限制。在我们以前的工作中，我们探索了治疗后恶性胶质瘤患者的解剖和分子MR图像网络（SAMR）的合成。在这项工作中，我们通过一个信心引导SAMR（CG-SAMR），综合数据从病变轮廓信息的多模态MR图像，包括T1加权（T1 w），钆增强T1 w（Gd-T1 w），T2加权（T2 w），液体衰减反转恢复（FLAIR），以及分子酰胺质子转移加权（APTw）序列。我们引入了一个模块，指导合成的基础上的置信度的中间结果。此外，我们扩展了所提出的架构，允许使用未配对的数据进行训练。在真实的临床数据上进行的大量实验表明，该模型的性能优于目前最先进的合成方法。我们的代码可在https://github.com/guopengf/CG-SAMR上获得。
Data-driven automatic approaches have demonstrated their great potential in resolving various clinical diagnostic dilemmas in neuro-oncology, especially with the help of standard anatomic and advanced molecular MR images. However, data quantity and quality remain a key determinant, and a significant limit of the potential applications. In our previous work, we explored the synthesis of anatomic and molecular MR image networks (SAMR) in patients with post-treatment malignant gliomas. In this work, we extend this through a confidence-guided SAMR (CG-SAMR) that synthesizes data from lesion contour information to multi-modal MR images, including T1-weighted (T1w), gadolinium enhanced T1w (Gd-T1w), T2-weighted (T2w), and fluid-attenuated inversion recovery (FLAIR), as well as the molecular amide proton transferweighted (APTw) sequence. We introduce a module that guides the synthesis based on a confidence measure of the intermediate results. Furthermore, we extend the proposed architecture to allow training using unpaired data. Extensive experiments on real clinical data demonstrate that the proposed model can perform better than current the state-of-the-art synthesis methods. Our code is available at https://github.com/guopengf/CG-SAMR.