DenseNet用于改善CT冠状动脉钙化检测的可行性研究
本研究探讨使用密集连接卷积网络(DenseNet)降低薄层(<3 mm)冠状动脉钙化(CAC)扫描图像噪声的可行性。体模实验显示,在1.5 mm层厚下,去噪后图像与常规3 mm层厚图像在钙化CT值上无显著差异,且患者数据中去噪图像能检测到更多钙化像素,使钙化更清晰。结论提示该方法可在不引起明显纹理改变或CT值变异的情况下降低1.5 mm层厚图像的统计噪声,有助于检测3 mm图像上难以识别的小和软钙化。
要点
- DenseNet去噪可用于1.5 mm层厚CAC扫描,降低噪声且不显著改变CT值。
- 去噪后1.5 mm图像较3 mm图像显示更多钙化像素,小钙化更清晰。
- 200-HA钙化在0.5和1.0 mm层厚去噪后CT值与3 mm图像仍有显著差异。
核心结论
- 基于CNN的去噪方法可降低1.5 mm层厚CAC扫描的统计噪声,不引起显著纹理改变或CT值变异。
- 该方法通过检测3 mm层厚图像上难以识别的小和软钙化,可能改善心血管风险预测。
研究设计与样本
- 体模研究使用QRM和CIRS体模进行模型训练和测试,DenseNet为针对超分辨率恢复设计的卷积神经网络。
- 患者数据评估中,CNN输入图像为0.5、1.0和1.5 mm层厚CAC扫描,标签图像为3 mm层厚重构图像(IMG3mm)。
- 对IMG3mm、输入图像和CNN输出图像进行感兴趣区(ROI)分析,采用双样本t检验比较ROI内CT值差异。
关键影像表现/征象
- QRM体模中,400-和800-HA钙化在3 mm图像与0.5、1.0或1.5 mm层厚去噪图像的CT值无统计学显著差异。
- QRM体模中,200-HA钙化在3 mm图像与0.5和1.0 mm层厚去噪图像的CT值有统计学显著差异,而与1.5 mm层厚去噪图像无显著差异。
- CIRS体模中模拟9种人体组织类型的棒插入物,3 mm图像与1.5 mm层厚去噪图像间无统计学显著差异,所有P值均大于0.10。
- 患者研究中,1.5 mm层厚去噪图像(IMGoutput)检测到的钙化像素多于3 mm图像(IMG3mm),钙化在去噪图像上更清晰。
临床应用与阅片要点
- 在CAC扫描采用1.5 mm层厚时,可考虑DenseNet去噪以降低噪声并保持CT值稳定性。
- 去噪后1.5 mm图像有助于识别3 mm常规图像上难以分辨的小和软钙化。
- 需注意0.5和1.0 mm层厚去噪图像对200-HA钙化的CT值仍与3 mm图像有显著差异,解读时需谨慎。
局限性
- 原文未明确报告研究局限性。
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
OBJECTIVES: Interscan reproducibility of coronary artery calcium (CAC) scoring can be improved by using a smaller slice thickness but at the cost of higher image noise. This study aimed to investigate the feasibility of using densely connected convolutional network (DenseNet) to reduce the image noise in CAC scans reconstructed with slice thickness < 3 mm for improving coronary calcification detection in CT.
METHODS: Phantom data acquired with QRM and CIRS phantoms were used for model training and testing, where the DenseNet model adopted in this work was a convolutional neural network (CNN) designed for super resolution recovery. After phantom study, the proposed method was evaluated in terms of its ability to improve calcification detection using patient data. The CNN input images (IMGinput) were CAC scans reconstructed with 0.5-, 1.0- and 1.5-mm slice thickness, while CNN label images were CAC scans reconstructed with 3-mm slice thickness (IMG3mm). Region of interest (ROI) analysis was carried out on IMG3mm, IMGinput and CNN output images (IMGoutput). Two-sample t test was used to compare the difference in Hounsfield Unit (HU) values within ROI between IMG3mm and IMGoutput.
RESULTS: For the calcifications in QRM phantoms, no statistically significant difference was found when comparing the HU values of 400- and 800-HA calcifications identified on IMG3mm to those on IMGoutput with slice thickness of 0.5, 1.0 or 1.5 mm. On the other hand, statistically significant difference was found when comparing the HU values of 200-HA calcifications identified on IMG3mm to those on IMGoutput with a slice thickness of 0.5 and 1.0 mm. Meanwhile, no statistically significant difference was found when comparing the HU values of 200-HA calcifications identified on IMG3mm to those on IMGoutput with a slice thickness of 1.5 mm. As for the rod inserts in CIRS phantoms simulating 9 different tissue types in human body, there was no statistically significant difference between IMG3mm and IMGoutput with slice thickness of 1.5 mm, and all the p values were larger than 0.10. With regards to patient study, more calcification pixels were detected on IMGoutput with a slice thickness of 1.5 mm than on IMG3mm, so calcifications were more clear on the denoised images.
CONCLUSION: According to our results, the CNN-based denoising method could reduce statistical noise in IMGinput with a slice thickness of 1.5 mm without causing significant texture change or variation in HU values. The proposed method could improve cardiovascular risk prediction by detecting small and soft calcifications that are barely identified on 3-mm slice images used in conventional CAC scans.
引用
- Hou, Yang. Investigating the Feasibility of Using DenseNet to Improve Coronary Calcification Detection in CT. Acad Radiol. 2022. PMID: 36396585. doi:10.1016/j.acra.2022.10.018
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。