Generative adversarial network-based super-resolution of diffusion-weighted imaging: Application to tumour radiomics in breast cancer.,NMR in Biomedicine

当前位置： X-MOL 学术 › NMR Biomed. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Generative adversarial network-based super-resolution of diffusion-weighted imaging: Application to tumour radiomics in breast cancer.
NMR in Biomedicine ( IF 2.7 ) Pub Date : 2020-06-10 , DOI: 10.1002/nbm.4345
Ming Fan ₁ , Zuhui Liu ₁ , Maosheng Xu ₂ , Shiwei Wang ₂ , Tieyong Zeng ₃ , Xin Gao ₄ , Lihua Li ₁

Affiliation

Diffusion‐weighted imaging (DWI) is increasingly used to guide the clinical management of patients with breast tumours. However, accurate tumour characterization with DWI and the corresponding apparent diffusion coefficient (ADC) maps are challenging due to their limited resolution. This study aimed to produce super‐resolution (SR) ADC images and to assess the clinical utility of these SR images by performing a radiomic analysis for predicting the histologic grade and Ki‐67 expression status of breast cancer. To this end, 322 samples of dynamic enhanced magnetic resonance imaging (DCE‐MRI) and the corresponding DWI data were collected. A SR generative adversarial (SRGAN) and an enhanced deep SR (EDSR) network along with the bicubic interpolation were utilized to generate SR‐ADC images from which radiomic features were extracted. The dataset was randomly separated into a development dataset (n = 222) to establish a deep SR model using DCE‐MRI and a validation dataset (n = 100) to improve the resolution of ADC images. This random separation of datasets was performed 10 times, and the results were averaged. The EDSR method was significantly better than the SRGAN and bicubic methods in terms of objective quality criteria. Univariate and multivariate predictive models of radiomic features were established to determine the area under the receiver operating characteristic curve (AUC). Individual features from the tumour SR‐ADC images showed a higher performance with the EDSR and SRGAN methods than with the bicubic method and the original images. Multivariate analysis of the collective radiomics showed that the EDSR‐ and SRGAN‐based SR‐ADC images performed better than the bicubic method and original images in predicting either Ki‐67 expression levels (AUCs of 0.818 and 0.801, respectively) or the tumour grade (AUCs of 0.826 and 0.828, respectively). This work demonstrates that in addition to improving the resolution of ADC images, deep SR networks can also improve tumour image‐based diagnosis in breast cancer.

中文翻译：

基于生成对抗网络的扩散加权成像超分辨率：在乳腺癌肿瘤放射组学中的应用。

弥散加权成像（DWI）越来越多地用于指导乳腺肿瘤患者的临床管理。然而，由于分辨率有限，使用 DWI 和相应的表观扩散系数 (ADC) 图准确表征肿瘤具有挑战性。本研究旨在生成超分辨率 (SR) ADC 图像，并通过进行放射组学分析来预测这些 SR 图像的临床效用，以预测乳腺癌的组织学分级和 Ki-67 表达状态。为此，收集了 322 个动态增强磁共振成像 (DCE-MRI) 样本和相应的 DWI 数据。利用 SR 生成对抗 (SRGAN) 和增强型深度 SR (EDSR) 网络以及双三次插值生成 SR-ADC 图像，从中提取放射学特征。n = 222) 使用 DCE-MRI 和验证数据集 ( n= 100) 以提高 ADC 图像的分辨率。数据集的这种随机分离进行了 10 次，并对结果进行了平均。在客观质量标准方面，EDSR 方法明显优于 SRGAN 和双三次方法。建立了放射组学特征的单变量和多变量预测模型，以确定接受者操作特征曲线（AUC）下的面积。与双三次方法和原始图像相比，来自肿瘤 SR-ADC 图像的单个特征使用 EDSR 和 SRGAN 方法显示出更高的性能。对集体放射组学的多变量分析表明，基于 EDSR 和 SRGAN 的 SR-ADC 图像在预测 Ki-67 表达水平（AUC 为 0.818 和 0.801，分别）或肿瘤等级（AUC 分别为 0.826 和 0.828）。这项工作表明，除了提高 ADC 图像的分辨率外，深度 SR 网络还可以改进基于肿瘤图像的乳腺癌诊断。

更新日期：2020-07-08

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11