From the Departments of Abdominal Imaging (C.T.J., S.G., M.M.S., V.K.W., U.S., N.A.W.B.), Physics (X.L.), and Biostatistics (W.Q.), the University of Texas MD Anderson Cancer Center, 1400 Pressler St, Unit 1473, Houston, TX 77030-4009; and Center for Virtual Imaging Trials, Carl E. Ravin Advanced Imaging Laboratories, Clinical Imaging Physics Group, Medical Physics Graduate Program, Departments of Radiology, Physics, Biomedical Engineering, and Electrical and Computer Engineering, Duke University Medical Center, Durham, NC (E.S.).
Radiology. 2022 Apr;303(1):90-98. doi: 10.1148/radiol.211838. Epub 2022 Jan 11.
Background Assessment of liver lesions is constrained as CT radiation doses are lowered; evidence suggests deep learning reconstructions mitigate such effects. Purpose To evaluate liver metastases and image quality between reduced-dose deep learning image reconstruction (DLIR) and standard-dose filtered back projection (FBP) contrast-enhanced abdominal CT. Materials and Methods In this prospective Health Insurance Portability and Accountability Act-compliant study (September 2019 through April 2021), participants with biopsy-proven colorectal cancer and liver metastases at baseline CT underwent standard-dose and reduced-dose portal venous abdominal CT in the same breath hold. Three radiologists detected and characterized lesions at standard-dose FBP and reduced-dose DLIR, reported confidence, and scored image quality. Contrast-to-noise ratios for liver metastases were recorded. Summary statistics were reported, and a generalized linear mixed model was used. Results Fifty-one participants (mean age ± standard deviation, 57 years ± 13; 31 men) were evaluated. The mean volume CT dose index was 65.1% lower with reduced-dose CT (12.2 mGy) than with standard-dose CT (34.9 mGy). A total of 161 lesions (127 metastases, 34 benign lesions) with a mean size of 0.7 cm ± 0.3 were identified. Subjective image quality of reduced-dose DLIR was superior to that of standard-dose FBP ( < .001). The mean contrast-to-noise ratio for liver metastases of reduced-dose DLIR (3.9 ± 1.7) was higher than that of standard-dose FBP (3.5 ± 1.4) ( < .001). Differences in detection were identified only for lesions 0.5 cm or smaller: 63 of 65 lesions detected with standard-dose FBP (96.9%; 95% CI: 89.3, 99.6) and 47 lesions with reduced-dose DLIR (72.3%; 95% CI: 59.8, 82.7). Lesion accuracy with standard-dose FBP and reduced-dose DLIR was 80.1% (95% CI: 73.1, 86.0; 129 of 161 lesions) and 67.1% (95% CI: 59.3, 74.3; 108 of 161 lesions), respectively ( = .01). Lower lesion confidence was reported with a reduced dose ( < .001). Conclusion Deep learning image reconstruction (DLIR) improved CT image quality at 65% radiation dose reduction while preserving detection of liver lesions larger than 0.5 cm. Reduced-dose DLIR demonstrated overall inferior characterization of liver lesions and reader confidence. Clinical trial registration no. NCT03151564 © RSNA, 2022
背景 随着 CT 辐射剂量的降低，对肝脏病变的评估受到限制；有证据表明，深度学习重建可以减轻这种影响。目的 评估降低剂量的深度学习图像重建（DLIR）与标准剂量滤波反投影（FBP）对比增强腹部 CT 之间肝转移瘤和图像质量的差异。 材料与方法 本前瞻性符合《健康保险流通与责任法案》（2019 年 9 月至 2021 年 4 月）的研究纳入基线 CT 检查显示有结直肠癌和肝转移瘤的患者，这些患者在一次屏气过程中接受标准剂量和降低剂量门静脉腹部 CT 检查。3 名放射科医生在标准剂量 FBP 和降低剂量 DLIR 下检测和描述病变，报告信心，并对图像质量进行评分。记录肝脏转移瘤的对比噪声比。报告了统计描述，并使用广义线性混合模型。 结果 51 名参与者（平均年龄±标准差，57 岁±13；31 名男性）接受了评估。降低剂量 CT（12.2 mGy）的容积 CT 剂量指数比标准剂量 CT（34.9 mGy）平均降低 65.1%。共发现 161 个病变（127 个转移瘤，34 个良性病变），平均大小为 0.7 cm±0.3 cm。降低剂量 DLIR 的主观图像质量优于标准剂量 FBP（<.001）。降低剂量 DLIR 肝脏转移瘤的平均对比噪声比（3.9±1.7）高于标准剂量 FBP（3.5±1.4）（<.001）。只有 0.5 cm 或更小的病变存在检测差异：标准剂量 FBP 检出 65 个病变中的 63 个（96.9%；95%CI：89.3，99.6），47 个病变用降低剂量 DLIR 检出（72.3%；95%CI：59.8，82.7）。标准剂量 FBP 和降低剂量 DLIR 的病变准确率分别为 80.1%（95%CI：73.1，86.0；129/161 个病变）和 67.1%（95%CI：59.3，74.3；108/161 个病变）（=.01）。降低剂量时，病变的置信度较低（<.001）。 结论 深度学习图像重建（DLIR）在降低 65%辐射剂量的同时提高了 CT 图像质量，同时保留了对大于 0.5 cm 肝脏病变的检测。降低剂量的 DLIR 显示出肝病变整体特征描述和读者信心的总体下降。 临床试验注册号 NCT03151564 © RSNA，2022
