Zhang Kun, Shi Xiang, Xie Shuang-Shuang, Sun Ji-Hang, Liu Zhuo-Heng, Zhang Shuai, Song Jia-Yang, Shen Wen
Department of Radiology, Tianjin First Central Hospital, Tianjin Institute of Imaging Medicine, School of Medicine, Nankai University, Tianjin, China.
First Central Clinical College, Tianjin Medical University, Tianjin, China.
Quant Imaging Med Surg. 2022 Jun;12(6):3238-3250. doi: 10.21037/qims-21-936.
Studies on the application of deep learning image reconstruction (DLIR) in pediatric computed tomography (CT) are limited and have so far been mostly based on phantom. The purpose of this study was to compare the image quality and radiation dose of DLIR with that of adaptive statistical iterative reconstruction-Veo (ASiR-V) during abdominal and chest CT for the pediatric population.
A pediatric phantom was used for the pilot study, and 20 children were recruited for clinical verification. The preset scan parameter noise index (NI) was 5, 8, 11, 13, 15, and 18 for the phantom study, and 8 and 13 for the clinical pediatric study. We reconstructed CT images with ASiR-V 30%, ASiR-V 70%, DLIR-M (medium) and DLIR-H (high). The regions of interest (ROI) were marked on the organs of the abdomen (liver, kidney, and subcutaneous fat) and the chest (lung, mediastinum, and spine). The CT dose index volume (CTDI), CT value, image noise (N), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were measured and calculated. The subjective image quality was assessed by 3 radiologists blindly using a 5-point scale. The dose reduction efficiency of DLIR was estimated.
In the phantom study, the interobserver assessment of the data measurement demonstrated good agreement [intraclass correlation coefficient (ICC) =0.814 for abdomen, 0.801 for chest]. Within the same dose level, the N, SNR, and CNR were statistically different among reconstructions, while the CT value remained the same. The N increased and SNR decreased as the radiation dose decreased. The DLIR-H performed better than ASiR-V when the radiation dose was reduced, without sacrificing image quality. In the patient study, the interobserver assessment of the data measurement demonstrated good agreement (ICC =0.774 for abdomen, 0.751 for chest). DLIR-H had the highest subjective and objective scores in the abdomen.
Application of DLIR could help to reduce radiation dose without sacrificing the image quality of pediatric CT scans. Further clinical validation is required.
深度学习图像重建（DLIR）在儿科计算机断层扫描（CT）中的应用研究有限，目前大多基于体模。本研究的目的是比较DLIR与自适应统计迭代重建-Veo（ASiR-V）在儿科人群腹部和胸部CT检查中的图像质量和辐射剂量。
使用儿科体模进行初步研究，并招募20名儿童进行临床验证。体模研究中预设扫描参数噪声指数（NI）为5、8、11、13、15和18，临床儿科研究中为8和13。我们用ASiR-V 30%、ASiR-V 70%、DLIR-M（中等）和DLIR-H（高）重建CT图像。在腹部（肝脏、肾脏和皮下脂肪）和胸部（肺、纵隔和脊柱）的器官上标记感兴趣区域（ROI）。测量并计算CT剂量指数体积（CTDI）、CT值、图像噪声（N）、信噪比（SNR）和对比噪声比（CNR）。由3名放射科医生采用5分制对主观图像质量进行盲法评估。估计DLIR的剂量降低效率。
在体模研究中，观察者间对数据测量的评估显示出良好的一致性[腹部组内相关系数（ICC）=0.814，胸部ICC=0.801]。在相同剂量水平下，不同重建方法之间的N、SNR和CNR存在统计学差异，而CT值保持不变。随着辐射剂量降低，N增加，SNR降低。当降低辐射剂量时，DLIR-H在不牺牲图像质量的情况下表现优于ASiR-V。在患者研究中，观察者间对数据测量的评估显示出良好的一致性（腹部ICC=0.774，胸部ICC=0.751）。DLIR-H在腹部的主观和客观评分最高。
DLIR的应用有助于在不牺牲儿科CT扫描图像质量的情况下降低辐射剂量。需要进一步的临床验证。
