From the Department of Radiology, Seoul National University Hospital.
CONNECT-AI R&D Center, Yonsei University College of Medicine.
Invest Radiol. 2022 May 1;57(5):308-317. doi: 10.1097/RLI.0000000000000839.
This study aimed to evaluate the usefulness of deep learning-based image conversion to improve the reproducibility of computed tomography (CT) radiomics features.
This study was conducted using an abdominal phantom with liver nodules. We developed an image conversion algorithm using a residual feature aggregation network to reproduce radiomics features with CT images under various CT protocols and reconstruction kernels. External validation was performed using images from different scanners, consisting of 8 different protocols. To evaluate the variability of radiomics features, regions of interest (ROIs) were drawn by targeting the liver parenchyma, vessels, paraspinal area, and liver nodules. We extracted 18 first-order, 68 second-order, and 688 wavelet radiomics features. Measurement variability was assessed using the concordance correlation coefficient (CCC), compared with the ground-truth image.
In the ROI-based analysis, there was an 83.3% improvement of CCC (80/96; 4 ROIs with 3 categories of radiomics features and 8 protocols) in synthetic images compared with the original images. Among them, the 56 CCC pairs showed a significant increase after image synthesis. In the radiomics feature-based analysis, 62.0% (3838 of 6192; 774 radiomics features with 8 protocols) features showed increased CCC after image synthesis, and a significant increase was noted in 26.9% (1663 of 6192) features. In particular, the first-order feature (79.9%, 115/144) showed better improvement in terms of the reproducibility of radiomics feature than the second-order (59.9%, 326/544) or wavelet feature (61.7%, 3397/5504).
Our study demonstrated that a deep learning model for image conversion can improve the reproducibility of radiomics features across various CT protocols, reconstruction kernels, and CT scanners.
本研究旨在评估基于深度学习的图像转换在提高 CT 放射组学特征可重复性方面的作用。
本研究使用具有肝脏结节的腹部体模进行。我们开发了一种使用残差特征聚合网络的图像转换算法，以在不同 CT 协议和重建核下复制 CT 图像的放射组学特征。使用来自不同扫描仪的图像进行外部验证，这些图像由 8 种不同的协议组成。为了评估放射组学特征的可变性，在肝脏实质、血管、脊柱旁区域和肝脏结节处绘制感兴趣区（ROI）。我们提取了 18 个一阶、68 个二阶和 688 个小波放射组学特征。使用一致性相关系数（CCC）评估测量变异性，并与真实图像进行比较。
在基于 ROI 的分析中，与原始图像相比，合成图像的 CCC（4 个 ROI，3 种类别的放射组学特征和 8 个协议）提高了 83.3%（80/96）。其中，56 对 CCC 在图像合成后显著增加。在放射组学特征分析中，62.0%（774 个特征，8 个协议）的特征在图像合成后 CCC 增加，26.9%（1663 个特征）的特征明显增加。特别是，一阶特征（79.9%，115/144）在放射组学特征的可重复性方面的改善优于二阶特征（59.9%，326/544）或小波特征（61.7%，3397/5504）。
本研究表明，图像转换的深度学习模型可以提高不同 CT 协议、重建核和 CT 扫描仪之间的放射组学特征的可重复性。
