Math, Science, and Technology Center, Lexington, KY 40513, United States of America.
Department of Radiology, University of Kentucky College of Medicine, Lexington, KY 40536 United States of America.
Phys Med Biol. 2022 Jul 8;67(14). doi: 10.1088/1361-6560/ac7999.
While simulated low-dose CT images and phantom studies cannot fully approximate subjective and objective effects of deep learning (DL) denoising on image quality, live animal models may afford this assessment. This study is to investigate the potential of DL in CT dose reduction on image quality compared to iterative reconstruction (IR).The upper abdomen of a live 4 year old sheep was scanned on a CT scanner at different exposure levels. Images were reconstructed using FBP and ADMIRE with 5 strengths. A modularized DL network with 5 modules was used for image reconstruction via progressive denoising. Radiomic features were extracted from a region over the liver. Concordance correlation coefficient (CCC) was applied to quantify agreement between any two sets of radiomic features. Coefficient of variation was calculated to measure variation in a radiomic feature series. Structural similarity index (SSIM) was used to measure the similarity between any two images. Diagnostic quality, low-contrast detectability, and image texture were qualitatively evaluated by two radiologists. Pearson correlation coefficient was computed across all dose-reconstruction/denoising combinations.A total of 66 image sets, with 405 radiomic features extracted from each, are analyzed. IR and DL can improve diagnostic quality and low-contrast detectability and similarly modulate image texture features. In terms of SSIM, DL has higher potential in preserving image structure. There is strong correlation between SSIM and radiologists' evaluations for diagnostic quality (0.559) and low-contrast detectability (0.635) but moderate correlation for texture (0.313). There is moderate correlation between CCC of radiomic features and radiologists' evaluation for diagnostic quality (0.397), low-contrast detectability (0.417), and texture (0.326), implying that improvement of image features may not relate to improvement of diagnostic quality.DL shows potential to further reduce radiation dose while preserving structural similarity, while IR is favored by radiologists and more predictably alters radiomic features.
虽然模拟低剂量 CT 图像和体模研究不能完全近似深度学习（DL）降噪对图像质量的主观和客观影响，但活体动物模型可能可以进行这种评估。本研究旨在比较深度学习与迭代重建（IR）在 CT 剂量降低对图像质量的影响。使用 CT 扫描仪对一只 4 岁绵羊的上腹部进行不同曝光水平的扫描。使用 FBP 和 ADMIRE 以 5 种强度进行图像重建。使用具有 5 个模块的模块化 DL 网络通过逐步降噪进行图像重建。从肝脏上方的一个区域提取放射组学特征。应用一致性相关系数（CCC）来量化任何两组放射组学特征之间的一致性。变异系数用于测量放射组学特征系列的变化。结构相似性指数（SSIM）用于衡量任意两幅图像之间的相似性。两位放射科医生对诊断质量、低对比度检测能力和图像纹理进行定性评估。计算了所有剂量重建/降噪组合的 Pearson 相关系数。共分析了 66 个图像集，每个图像集提取了 405 个放射组学特征。IR 和 DL 可以提高诊断质量和低对比度检测能力，并相似地调节图像纹理特征。就 SSIM 而言，DL 具有更高的保持图像结构的潜力。SSIM 与放射科医生对诊断质量（0.559）和低对比度检测能力（0.635）的评估之间存在很强的相关性，但与纹理（0.313）之间存在中度相关性。放射组学特征的 CCC 与放射科医生对诊断质量（0.397）、低对比度检测能力（0.417）和纹理（0.326）的评估之间存在中度相关性，这表明图像特征的改善可能与诊断质量的改善无关。DL 具有进一步降低辐射剂量同时保持结构相似性的潜力，而 IR 则受到放射科医生的青睐，并且更可预测地改变放射组学特征。
