深度学习算法再训练对非门控胸部CT中符合指南的主动脉直径测量的影响
本研究纳入995例非心电图门控胸部CT(增强392例、平扫603例)被初版深度学习工具判为胸主动脉扩张的患者,评估再训练版深度学习工具对主动脉直径测量的影响。再训练版正确完成8539/8948(95.5%)测量,其中4456/8948(49.8%)仅再训练版测量正确,以主动脉根部改善最明显(主动脉窦564/995,57%;窦管交界697/995,70%)。作者认为再训练版深度学习工具可用于非门控胸部CT(含增强与平扫)。
要点
- 再训练版深度学习工具在非门控胸部CT中正确完成95.5%(8539/8948)的主动脉直径测量。
- 初版与再训练版均正确的测量仅占42.1%(3765/8948),主动脉窦最差(221/995,22%)。
- 错误测量中倾斜平面占2.5%(228例),过度/不足分割占2.0%(181例),均以主动脉窦为主。
核心结论
- 再训练深度学习工具改善了主动脉直径评估,总正确测量率达95.5%;作者认为该再训练版工具甚至可用于非心电图门控胸部CT,包括增强与平扫检查。
研究设计与样本
- 研究纳入995例(68±12岁)胸部CT患者,其中增强392例、平扫603例,均为初版深度学习工具判为胸主动脉扩张者;再训练版工具改进了中心线拟合与横断面平面放置的稳健性,所有病例经再训练版处理,由放射科医生评估平面放置与直径测量,测量分为各位置正确测量与高估/低估的错误测量。
关键影像表现/征象
- 共评估995例检查中的8948个测量,再训练版正确完成8539/8948(95.5%)。
- 两版均正确的测量为3765/8948(42.1%),最佳为远端主动脉弓655/995(66%),最差为主动脉窦221/995(22%)。
- 仅再训练版正确的测量为4456/8948(49.8%),主动脉根部改善明显:主动脉窦564/995(57%),窦管交界697/995(70%)。
- 再训练版还完成318个(3.6%)此前无法获得的测量。
- 错误测量中,倾斜平面致228例(2.5%),过度/不足分割致181例(2.0%),均集中于主动脉窦(分别为137例(14%)与73例(7%))。
临床应用与阅片要点
- 作者认为再训练版深度学习工具可用于非心电图门控胸部CT(包括增强与平扫)的主动脉直径测量。
- 阅片时需注意主动脉窦处倾斜平面与过度/不足分割所致的高估或低估。
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
PURPOSE/OBJECTIVE: Reliable detection of thoracic aortic dilatation (TAD) is mandatory in clinical routine. For ECG-gated CT angiography, automated deep learning (DL) algorithms are established for diameter measurements according to current guidelines. For non-ECG gated CT (contrast enhanced (CE) and non-CE), however, only a few reports are available. In these reports, classification as TAD is frequently unreliable with variable result quality depending on anatomic location with the aortic root presenting with the worst results. Therefore, this study aimed to explore the impact of re-training on a previously evaluated DL tool for aortic measurements in a cohort of non-ECG gated exams.
METHODS & MATERIALS: A cohort of 995 patients (68 ± 12 years) with CE (n = 392) and non-CE (n = 603) chest CT exams was selected which were classified as TAD by the initial DL tool. The re-trained version featured improved robustness of centerline fitting and cross-sectional plane placement. All cases were processed by the re-trained DL tool version. DL results were evaluated by a radiologist regarding plane placement and diameter measurements. Measurements were classified as correctly measured diameters at each location whereas false measurements consisted of over-/under-estimation of diameters.
RESULTS: We evaluated 8948 measurements in 995 exams. The re-trained version performed 8539/8948 (95.5%) of diameter measurements correctly. 3765/8948 (42.1%) of measurements were correct in both versions, initial and re-trained DL tool (best: distal arch 655/995 (66%), worst: Aortic sinus (AS) 221/995 (22%)). In contrast, 4456/8948 (49.8%) measurements were correctly measured only by the re-trained version, in particular at the aortic root (AS: 564/995 (57%), sinotubular junction: 697/995 (70%)). In addition, the re-trained version performed 318 (3.6%) measurements which were not available previously. A total of 228 (2.5%) cases showed false measurements because of tilted planes and 181 (2.0%) over-/under-segmentations with a focus at AS (n = 137 (14%) and n = 73 (7%), respectively).
CONCLUSION: Re-training of the DL tool improved diameter assessment, resulting in a total of 95.5% correct measurements. Our data suggests that the re-trained DL tool can be applied even in non-ECG-gated chest CT including both, CE and non-CE exams.
引用
- Lo Piccolo F, Hinck D, Segeroth M, et al. Impact of retraining a deep learning algorithm for improving guideline-compliant aortic diameter measurements on non-gated chest CT. Eur J Radiol. 2023. PMID: 37716024. doi:10.1016/j.ejrad.2023.111093
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。