From the Department of Radiology, University of Washington School of Medicine, Seattle, Wash (A.M.); Department of Radiology, Mayo Clinic, Rochester, Minn (L.Y.); Department of Radiology, New York University Grossman School of Medicine, NYU Langone Health, New York, NY (J.W.R.); Departments of Radiation Oncology (S.K.) and Abdominal Imaging (M.A.S., J.J.I.R., V.K.W., K.M.E., C.T.J.), The University of Texas MD Anderson Cancer Center, 1400 Pressler St, Unit 1473, Houston, TX 77030-4009; Department of Radiology, Texas Children's Hospital, Houston, Tex (A.M.R.C.); and Department of Radiology, Seoul National University College of Medicine, Seoul, South Korea (J.M.L.).
Radiographics. 2024 Dec;44(12):e240095. doi: 10.1148/rg.240095.
The implementation of deep neural networks has spurred the creation of deep learning reconstruction (DLR) CT algorithms. DLR CT techniques encompass a spectrum of deep learning-based methodologies that operate during the different steps of the image creation, prior to or after the traditional image formation process (eg, filtered backprojection [FBP] or iterative reconstruction [IR]), or alternatively by fully replacing FBP or IR techniques. DLR algorithms effectively facilitate the reduction of image noise associated with low photon counts from reduced radiation dose protocols. DLR methods have emerged as an effective solution to ameliorate limitations observed with prior CT image reconstruction algorithms, including FBP and IR algorithms, which are not able to preserve image texture and diagnostic performance at low radiation dose levels. An additional advantage of DLR algorithms is their high reconstruction speed, hence targeting the ideal triad of features for a CT image reconstruction (ie, the ability to consistently provide diagnostic-quality images and achieve radiation dose imaging levels as low as reasonably possible, with high reconstruction speed). An accumulated body of evidence supports the clinical use of DLR algorithms in abdominal imaging across multiple CT imaging tasks. The authors explore the technical aspects of DLR CT algorithms and examine various approaches to image synthesis in DLR creation. The clinical applications of DLR algorithms are highlighted across various abdominal CT imaging domains, with emphasis on the supporting evidence for diverse clinical tasks. An overview of the current limitations of and outlook for DLR algorithms for CT is provided. RSNA, 2024.
深度学习网络的实现推动了深度学习重建 (DLR) CT 算法的创建。DLR CT 技术涵盖了一系列基于深度学习的方法，这些方法在图像创建的不同步骤中运行，在传统图像形成过程之前或之后（例如滤波反投影 [FBP] 或迭代重建 [IR]），或者通过完全替代 FBP 或 IR 技术。DLR 算法有效地促进了降低与低光子计数相关的图像噪声，这些低光子计数来自于降低的辐射剂量方案。DLR 方法已成为改善先前 CT 图像重建算法（包括 FBP 和 IR 算法）所观察到的局限性的有效解决方案，这些算法无法在低辐射剂量水平下保留图像纹理和诊断性能。DLR 算法的另一个优点是其高重建速度，因此针对 CT 图像重建的理想三重特征（即，能够始终如一地提供诊断质量的图像，并实现尽可能低的辐射剂量成像水平，同时具有高重建速度）。越来越多的证据支持 DLR 算法在腹部成像中的临床应用，涵盖了多种 CT 成像任务。作者探讨了 DLR CT 算法的技术方面，并研究了 DLR 创建中图像合成的各种方法。强调了 DLR 算法在各种腹部 CT 成像领域的临床应用，重点介绍了支持各种临床任务的证据。概述了当前 DLR 算法在 CT 中的局限性和展望。RSNA，2024 年。
