Nakamura Yuko, Higaki Toru, Tatsugami Fuminari, Zhou Jian, Yu Zhou, Akino Naruomi, Ito Yuya, Iida Makoto, Awai Kazuo
Department of Diagnostic Radiology, Hiroshima University, 1-2-3 Kasumi, Minami-ku, Hiroshima, Japan 734-8551 (Y.N., T.H., F.T., M.I., K.A.); Canon Medical Research USA, Vernon Hills, Ill (J.Z., Z.Y.); and Canon Medical Systems, Tochigi, Japan (N.A., Y.I.).
Radiol Artif Intell. 2019 Oct 9;1(6):e180011. doi: 10.1148/ryai.2019180011. eCollection 2019 Nov.
To evaluate the effect of a deep learning-based reconstruction (DLR) method on the conspicuity of hypovascular hepatic metastases on abdominal CT images.
This retrospective study with institutional review board approval included 58 patients with hypovascular hepatic metastases. A radiologist recorded the standard deviation of attenuation in the paraspinal muscle as the image noise and the contrast-to-noise ratio (CNR). CNR was calculated as region of interest ([ROI] - ROI)/N, where ROI is the mean liver parenchyma attenuation, ROI, the mean tumor attenuation, and N, the noise. Two other radiologists graded the conspicuity of the liver lesion on a five-point scale where 1 is unidentifiable and 5 is detected without diagnostic compromise. Only the smallest liver lesion in each patient, classified as smaller or larger than 10 mm, was evaluated. The difference between hybrid iterative reconstruction (IR) and DLR images was determined by using a two-sided Wilcoxon signed-rank test.
The image noise was significantly lower, and the CNR was significantly higher on DLR images than hybrid IR images (median image noise: 19.2 vs 12.8 HU, < .001; median CNR: tumors < 10 mm: 1.9 vs 2.5; tumors > 10 mm: 1.7 vs 2.2, both < .001). The scores for liver lesions were significantly higher for DLR images than hybrid IR images ( < .01 for both in tumors smaller or larger than 10 mm).
DLR improved the quality of abdominal CT images for the evaluation of hypovascular hepatic metastases.© RSNA, 2019
评估基于深度学习的重建（DLR）方法对腹部CT图像上乏血供肝转移瘤的显示效果。
本回顾性研究经机构审查委员会批准，纳入了58例乏血供肝转移瘤患者。一名放射科医生记录椎旁肌衰减的标准差作为图像噪声和对比噪声比（CNR）。CNR计算公式为感兴趣区（[ROI] - ROI）/N，其中ROI为肝脏实质平均衰减值，ROI为肿瘤平均衰减值，N为噪声。另外两名放射科医生对肝脏病变的显示清晰度进行五分制评分，1分为无法识别，5分为能清晰显示且不影响诊断。仅评估每位患者最小的肝脏病变，分为小于或大于10 mm。采用双侧Wilcoxon符号秩检验确定混合迭代重建（IR）图像与DLR图像之间的差异。
DLR图像的图像噪声显著更低，CNR显著更高（图像噪声中位数：19.2 vs 12.8 HU，P <.001；CNR中位数：肿瘤<10 mm：1.9 vs 2.5；肿瘤>10 mm：1.7 vs 2.2，均P <.001）。DLR图像上肝脏病变的评分显著高于混合IR图像（肿瘤小于或大于10 mm时均P <.01）。
DLR提高了腹部CT图像对乏血供肝转移瘤的评估质量。©RSNA，2019
