深度学习图像转换对薄层、锐核、非门控、低剂量胸部CT全自动冠状动脉钙化评分的影响:多中心研究
多中心回顾性研究纳入225对低剂量胸部CT与钙化评分CT图像,用深度学习软件将薄层锐核低剂量图像转换为模拟常规钙化评分CT。转换后自动Agatston评分与参考标准的偏差从206.7降至-3.45,一致性相关系数从0.269升至0.881,风险分级加权kappa从0.115升至0.792。
要点
- 转换后自动钙化评分偏差明显减小,与手动参考标准的一致性提高。
- 转换后风险分级与参考标准达到良好一致(加权kappa=0.792)。
- 未转换的薄层锐核低剂量CT自动评分一致性差,风险分级一致性差。
核心结论
- 基于深度学习的图像转换可提高薄层锐核低剂量胸部CT自动冠状动脉钙化评分测量的准确性。
研究设计与样本
- 多中心回顾性研究,纳入4家机构225对低剂量胸部CT与钙化评分CT图像(120 kVp,同一患者6个月内),以钙化评分CT手动评分为参考标准。
关键影像表现/征象
- 图像转换包括深度学习核转换(低剂量高频锐核模拟标准剂量低频核)和厚度转换(raysum法将1 mm或1.25 mm转为3 mm)。
- 转换后自动评分(LDCT-CONVauto)与参考标准的偏差为-3.45,未转换自动评分(LDCT-Orgauto)偏差为206.7。
诊断标准与关键数值
- LDCT-CONVauto与CSCTmanual的CCC为0.881(95%CI 0.750-0.960),LDCT-Orgauto为0.269(95%CI 0.129-0.430)。
- LDCT-CONVauto风险分级加权kappa为0.792(95%CI 0.731-0.847),LDCT-Orgauto为0.115(95%CI 0.082-0.154)。
临床应用与阅片要点
- 对薄层锐核非门控低剂量胸部CT,经深度学习转换后自动钙化评分与参考标准一致性提高。
- 未转换图像自动评分偏差大、风险分级一致性差。
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 evaluate the impact of deep learning-based image conversion on the accuracy of automated coronary artery calcium quantification using thin-slice, sharp-kernel, non-gated, low-dose chest computed tomography (LDCT) images collected from multiple institutions.
MATERIALS AND METHODS: A total of 225 pairs of LDCT and calcium scoring CT (CSCT) images scanned at 120 kVp and acquired from the same patient within a 6-month interval were retrospectively collected from four institutions. Image conversion was performed for LDCT images using proprietary software programs to simulate conventional CSCT. This process included 1) deep learning-based kernel conversion of low-dose, high-frequency, sharp kernels to simulate standard-dose, low-frequency kernels, and 2) thickness conversion using the raysum method to convert 1-mm or 1.25-mm thickness images to 3-mm thickness. Automated Agaston scoring was conducted on the LDCT scans before (LDCT-Orgauto) and after the image conversion (LDCT-CONVauto). Manual scoring was performed on the CSCT images (CSCTmanual) and used as a reference standard. The accuracy of automated Agaston scores and risk severity categorization based on the automated scoring on LDCT scans was analyzed compared to the reference standard, using the Bland-Altman analysis, concordance correlation coefficient (CCC), and weighted kappa (κ) statistic.
RESULTS: LDCT-CONVauto demonstrated a reduced bias for Agaston score, compared with CSCTmanual, than LDCT-Orgauto did (-3.45 vs. 206.7). LDCT-CONVauto showed a higher CCC than LDCT-Orgauto did (0.881 [95% confidence interval {CI}, 0.750-0.960] vs. 0.269 [95% CI, 0.129-0.430]). In terms of risk category assignment, LDCT-Orgauto exhibited poor agreement with CSCTmanual (weighted κ = 0.115 [95% CI, 0.082-0.154]), whereas LDCT-CONVauto achieved good agreement (weighted κ = 0.792 [95% CI, 0.731-0.847]).
CONCLUSION: Deep learning-based conversion of LDCT images originally obtained with thin slices and a sharp kernel can enhance the accuracy of automated coronary artery calcium score measurement using the images.
引用
- Kim C, Hong S, Choi H, et al. Impact of Deep Learning-Based Image Conversion on Fully Automated Coronary Artery Calcium Scoring Using Thin-Slice, Sharp-Kernel, Non-Gated, Low-Dose Chest CT Scans: A Multi-Center Study. Korean J Radiol. 2025. PMID: 40527737. doi:10.3348/kjr.2025.0177
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。