Department of Radiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Avenue, MLC 5031, Cincinnati, OH, 45229, USA.
Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, OH, USA.
Abdom Radiol (NY). 2022 Jan;47(1):265-271. doi: 10.1007/s00261-021-03274-7. Epub 2021 Oct 4.
Deep learning Computed Tomography (CT) reconstruction (DLR) algorithms promise to improve image quality but the impact on clinical diagnostic performance remains to be demonstrated. We aimed to compare DLR to standard iterative reconstruction for detection of urolithiasis by unenhanced CT in children and young adults.
This was an IRB approved retrospective study involving post-hoc reconstruction of clinically acquired unenhanced abdomen/pelvis CT scans. Images were reconstructed with six different manufacturer-standard DLR algorithms and reformatted in 3 planes (axial, sagittal, and coronal) at 3 mm intervals. De-identified reconstructions were loaded as independent examinations for review by 3 blinded radiologists (R1, R2, R3) tasked with identifying and measuring all stones. Results were compared to the clinical iterative reconstruction images as a reference standard. IntraClass correlation coefficients and kappa (k) statistics were used to quantify agreement.
CT data for 14 patients (mean age: 17.3 ± 3.4 years, 5 males and 9 females, weight class: 31-70 kg (n = 6), 71-100 kg (n = 7), > 100 kg (n = 1)) were reconstructed into 84 total exams. 7 patients had urinary tract calculi. Interobserver agreement on the presence of any urinary tract calculus was substantial to almost perfect (k = 0.71-1) for all DLR algorithms. Agreement with the reference standard on number of calculi was excellent (ICC = 0.78-0.96) and agreement on the size of the largest calculus was fair to excellent (ICC = 0.51-0.97) depending on reviewer and DLR algorithm.
Deep learning reconstruction of unenhanced CT images allows similar renal stone detectability compared to iterative reconstruction.
深度学习计算机断层扫描（CT）重建（DLR）算法有望提高图像质量，但仍需证明其对临床诊断性能的影响。我们旨在比较 DLR 与标准迭代重建在儿童和年轻成人中对未增强 CT 尿路结石检测的影响。
这是一项经 IRB 批准的回顾性研究，涉及对临床获得的未增强腹部/骨盆 CT 扫描进行后处理重建。使用 6 种不同制造商标准的 DLR 算法对图像进行重建，并以 3 毫米的间隔在 3 个平面（轴位、矢状位和冠状位）进行重组。将去识别的重建作为独立的检查加载，由 3 名盲法放射科医生（R1、R2、R3）进行审查，负责识别和测量所有结石。结果与临床迭代重建图像作为参考标准进行比较。使用组内相关系数和 kappa（k）统计量来量化一致性。
14 名患者（平均年龄：17.3±3.4 岁，5 名男性和 9 名女性，体重等级：31-70kg（n=6），71-100kg（n=7），>100kg（n=1））的 CT 数据被重建为 84 个总检查。7 名患者有尿路结石。所有 DLR 算法对任何尿路结石存在的观察者间一致性均为中等至几乎完美（k=0.71-1）。与参考标准相比，结石数量的一致性为极好（ICC=0.78-0.96），最大结石大小的一致性为良好至极好（ICC=0.51-0.97），具体取决于审阅者和 DLR 算法。
与迭代重建相比，未增强 CT 图像的深度学习重建可以实现类似的肾结石检测能力。
Zotero 插件