文献速递胸部CT

深度学习技术用于超低剂量胸部CT的图像质量:厂商无关后处理可能优于厂商特定技术

Image quality of ultralow-dose chest CT using deep learning techniques: potential superiority of vendor-agnostic post-processing over vendor-specific techniques.
PubMed 文献 · Eur Radiol · 2021-01-07

本研究纳入100例连续超低剂量非增强胸部CT(CTDIvol均值0.33±0.056 mGy),用五种算法重建,由三名胸部放射科医师盲法评估主观噪声、空间分辨率、失真伪影和整体图像质量。结果显示DLM-stnd整体图像质量最佳(均值3.89±0.19),三名阅片者中两人偏好DLM-stnd;DLIR定量噪声最低但主观空间分辨率较差、边缘上升距离更高、失真伪影更频繁且偏度偏离。

要点

  • 超低剂量胸部CT中,厂商无关深度学习后处理DLM-stnd整体图像质量评分最佳,三名阅片者中两人偏好。
  • DLIR定量噪声最低,但肺窗主观空间分辨率低于DLM-stnd,边缘上升距离更高,失真伪影更频繁。
  • DLM-stnd整体图像质量均值3.89±0.19,DLM-shrp为3.68±0.24,DLIR为3.53±0.33(ps<.001)。

核心结论

  • DLIR定量噪声最低,但DLM-stnd整体图像质量最佳、伪影更少,且被三名阅片者中的两人偏好。

研究设计与样本

  • 研究纳入100例连续超低剂量非增强胸部CT扫描,CTDIvol均值0.33±0.056 mGy。
  • 采用五种重建算法:DLM-stnd(标准核)、DLM-shrp(锐利核)、DLIR(高水平)、ASiR-stnd(70%)、ASiR-shrp。
  • 由三名胸部放射科医师在不知重建算法的条件下评估五组各100幅图像的主观噪声、空间分辨率、失真伪影和整体图像质量,并为每例选择最偏好的算法。
  • 测量图像噪声和信噪比;在肺血管处测量边缘上升距离(衰减为最大血管内强度10%和90%两点之间的距离);在均匀区域计算衰减偏度。

关键影像表现/征象

  • DLM-stnd在肺窗和纵隔窗的主观噪声最佳,其次为DLIR(ps<.0001)。
  • DLIR定量噪声最低(ps<.0001),但肺窗主观空间分辨率低于DLM-stnd,边缘上升距离更高(ps<.0001)。
  • DLIR失真伪影最频繁,衰减偏度偏离最明显(ps<.0001)。

诊断标准与关键数值

  • 整体图像质量均值:DLM-stnd 3.89±0.19、DLM-shrp 3.68±0.24、DLIR 3.53±0.33(ps<.001)。
  • 主观噪声最佳为DLM-stnd,其次DLIR(ps<.0001);定量噪声最低为DLIR(ps<.0001)。
  • 肺窗主观空间分辨率DLIR低于DLM-stnd,DLIR边缘上升距离高于DLM-stnd(ps<.0001)。
  • DLIR失真伪影最频繁、衰减偏度偏离最明显(ps<.0001)。

临床应用与阅片要点

  • 在超低剂量胸部CT(CTDIvol均值0.33±0.056 mGy)重建中,DLM-stnd整体图像质量最佳且伪影较少,被三名阅片者中的两人偏好。
  • DLIR虽定量噪声最低,但肺窗主观空间分辨率较低、边缘上升距离更高、失真伪影更频繁且偏度偏离,阅片时需注意这些伪影表现。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVE: To compare the image quality between the vendor-agnostic and vendor-specific algorithms on ultralow-dose chest CT.

METHODS: Vendor-agnostic deep learning post-processing model (DLM), vendor-specific deep learning image reconstruction (DLIR, high level), and adaptive statistical iterative reconstruction (ASiR, 70%) algorithms were employed. One hundred consecutive ultralow-dose noncontrast CT scans (CTDIvol; mean, 0.33 ± 0.056 mGy) were reconstructed with five algorithms: DLM-stnd (standard kernel), DLM-shrp (sharp kernel), DLIR, ASiR-stnd, and ASiR-shrp. Three thoracic radiologists blinded to the reconstruction algorithms reviewed five sets of 100 images and assessed subjective noise, spatial resolution, distortion artifact, and overall image quality. They selected the most preferred algorithm among five image sets for each case. Image noise and signal-to-noise ratio were measured. Edge-rise-distance was measured at a pulmonary vessel, i.e., the distance between two points where attenuation was 10% and 90% of maximal intravascular intensity. The skewness of attenuation was calculated in homogeneous areas.

RESULTS: DLM-stnd, followed by DLIR, showed the best subjective noise on both lung and mediastinal windows, while DLIR yielded the least measured noise (ps < .0001). Compared to DLM-stnd, DLIR showed inferior subjective spatial resolution on lung window and higher edge-rise-distance (ps < .0001). Additionally, DLIR showed the most frequent distortion artifacts and deviated skewness (ps < .0001). DLM-stnd scored the best overall image quality, followed by DLM-shrp and DLIR (mean score 3.89 ± 0.19, 3.68 ± 0.24, and 3.53 ± 0.33; ps < .001). Two among three readers preferred DLM-stnd on both windows.

CONCLUSION: Although DLIR provided the best quantitative noise profile, DLM-stnd showed the best overall image quality with fewer artifacts and was preferred by two among three readers.

KEY POINTS: • A vendor-agnostic deep learning post-processing algorithm applied to ultralow-dose chest CT exhibited the best image quality compared to vendor-specific deep learning algorithm and ASiR techniques. • Two out of three readers preferred a vendor-agnostic deep learning post-processing algorithm in comparison to vendor-specific deep learning algorithm and ASiR techniques. • A vendor-specific deep learning reconstruction algorithm yielded the least image noise, but showed significantly more frequent specific distortion artifacts and increased skewness of attenuation compared to a vendor-agnostic algorithm.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Nam JG, Ahn C, Choi H, et al. Image quality of ultralow-dose chest CT using deep learning techniques: potential superiority of vendor-agnostic post-processing over vendor-specific techniques. Eur Radiol. 2021. PMID: 33415436. doi:10.1007/s00330-020-07537-7

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。