Morikawa Tomoro, Tanabe Yuki, Suekuni Hiroshi, Fukuyama Naoki, Toshimori Wataru, Toritani Hidetaka, Sawada Shun, Matsuda Takuya, Nakano Shota, Kido Teruhito
Department of Radiology, Ehime University Graduate School of Medicine, Toon, Japan.
Canon Medical Systems Corporation, Otawara, Japan.
Eur Radiol. 2025 Mar 20. doi: 10.1007/s00330-025-11506-3.
To evaluate the impact of deep learning-based super-resolution reconstruction (DLSRR) on image quality and Agatston score.
Consecutive patients who underwent cardiac CT, including unenhanced CT for Agatston scoring, were enrolled. Four types of non-contrast CT images were reconstructed using filtered back projection (FBP) and three strengths of DLSRR. Image quality was assessed by measuring image noise, signal-to-noise ratio (SNR) of the aorta, contrast-to-noise ratio (CNR), and edge rise slope (ERS) of coronary artery calcium (CAC). Agatston score and CAC volume were also measured. These results were compared among the four CT datasets. Patients were categorized into four risk levels based on the Coronary Artery Calcium Data and Reporting System (CAC-DRS), and the concordance rate between FBP and DLSRR classifications was evaluated.
For the 111 patients enrolled, DLSRR significantly reduced image noise (p < 0.001) and improved SNR and CNR (p < 0.001), with stronger effects at higher DLSRR strengths (p < 0.01). ERS was significantly enhanced using DLSRR compared with FBP (p < 0.001), whereas there was no significant difference among the three strengths of DLSRR (p = 0.90-0.98). Agatston score and CAC volume were not significantly affected by DLSRR (p = 0.952 and 0.901, respectively). The concordance rate of CAC-DRS classification between FBP and DLSRR was 93%.
DLSRR significantly improves image quality by reducing noise and enhancing sharpness without significantly altering Agatston scores or CAC volumes. The concordance rate of CAC-DRS classification with FBP was high, although some reclassifications were observed.
Question The utility of deep learning-based super-resolution reconstruction (DLSRR) in coronary CT angiography is well known, but its impact on the Agatston score remains unclear. Findings DLSRR significantly improved image quality without altering the Agatston scores, but some reclassifications of Coronary Artery Calcium Data and Reporting System (CAC-DRS) were observed. Clinical relevance DLSRR should be cautiously used in clinical settings owing to the occurrence of some cases of CAC-DRS reclassification.
评估基于深度学习的超分辨率重建（DLSRR）对图像质量和阿加斯顿评分的影响。
纳入连续接受心脏CT检查的患者，包括用于阿加斯顿评分的平扫CT。使用滤波反投影（FBP）和三种强度的DLSRR重建四种类型的非增强CT图像。通过测量图像噪声、主动脉的信噪比（SNR）、对比噪声比（CNR）以及冠状动脉钙化（CAC）的边缘上升斜率（ERS）来评估图像质量。还测量了阿加斯顿评分和CAC体积。对这四个CT数据集的结果进行比较。根据冠状动脉钙化数据和报告系统（CAC-DRS）将患者分为四个风险级别，并评估FBP和DLSRR分类之间的一致性率。
对于纳入的111例患者，DLSRR显著降低了图像噪声（p < 0.001），并改善了SNR和CNR（p < 0.001），在较高的DLSRR强度下效果更强（p < 0.01）。与FBP相比，使用DLSRR时ERS显著增强（p < 0.001），而DLSRR的三种强度之间没有显著差异（p = 0.90 - 0.98）。DLSRR对阿加斯顿评分和CAC体积没有显著影响（分别为p = 0.952和0.901）。FBP和DLSRR之间的CAC-DRS分类一致性率为93%。
DLSRR通过降低噪声和增强锐度显著提高了图像质量，而不会显著改变阿加斯顿评分或CAC体积。尽管观察到一些重新分类，但CAC-DRS分类与FBP的一致性率较高。
问题基于深度学习的超分辨率重建（DLSRR）在冠状动脉CT血管造影中的效用是众所周知的，但其对阿加斯顿评分的影响仍不清楚。发现DLSRR显著改善了图像质量而未改变阿加斯顿评分，但观察到冠状动脉钙化数据和报告系统（CAC-DRS）的一些重新分类。临床意义由于发生了一些CAC-DRS重新分类的情况，DLSRR在临床环境中应谨慎使用。
