用深度学习把实时2D心脏影像拼成高清3D动态图，1分钟完成分析。
High Resolution Isotropic 3D Cine imaging with Automated Segmentation using Concatenated 2D Real-time Imaging and Deep Learning
- 用四类深度学习模型逐层修正2D影像的对比度、呼吸运动和分辨率，并分割心腔与血管。
- 生成的3D电影在心室容积和血管直径测量上与传统方法基本一致，仅右肺动脉略高估。
- 适合临床快速评估儿童先天性心脏病，总耗时不到2分钟。
背景：传统儿科及先天性心脏病心血管磁共振（CMR）采用2D屏气平衡稳态自由进动（bSSFP）电影评估功能，以及心脏门控、呼吸导航的静态3D bSSFP全心成像进行解剖评估。本研究旨在将多层2D自由呼吸实时电影串联，并利用深度学习（DL）重建出各向同性的完整分割3D电影数据。方法：基于开源数据训练四种深度学习模型，分别实现：a) 层间对比度校正；b) 层间呼吸运动校正；c) 超分辨率（层面方向）；d) 右/左心房与心室（RA, LA, RV, LV）、胸主动脉（Ao）及肺动脉（PA）的分割。在10例接受常规心血管检查的患者中，对前瞻性采集的矢状位实时电影堆栈进行验证。定量指标（心室容积与血管直径）及3D电影图像质量与传统屏气电影和全心成像对比。结果：所有实时数据均成功转换为3D电影，每例后处理时间均小于1分钟。所有左右心室指标无显著偏倚，一致性限度合理，相关性良好；所有血管直径也具合理一致性，但右肺动脉直径存在轻微但显著的高估。结论：本研究证明了利用一系列深度学习模型从串联2D实时电影生成3D电影的可行性。该方法具有短采集与重建时间，2分钟内即可获得完整分割数据。与传统方法的良好一致性表明，该方法有望显著提升临床实践中的CMR效率。
原文摘要 · Abstract (English)
Background: Conventional cardiovascular magnetic resonance (CMR) in paediatric and congenital heart disease uses 2D, breath-hold, balanced steady state free precession (bSSFP) cine imaging for assessment of function and cardiac-gated, respiratory-navigated, static 3D bSSFP whole-heart imaging for anatomical assessment. Our aim is to concatenate a stack 2D free-breathing real-time cines and use Deep Learning (DL) to create an isotropic a fully segmented 3D cine dataset from these images. Methods: Four DL models were trained on open-source data that performed: a) Interslice contrast correction; b) Interslice respiratory motion correction; c) Super-resolution (slice direction); and d) Segmentation of right and left atria and ventricles (RA, LA, RV, and LV), thoracic aorta (Ao) and pulmonary arteries (PA). In 10 patients undergoing routine cardiovascular examination, our method was validated on prospectively acquired sagittal stacks of real-time cine images. Quantitative metrics (ventricular volumes and vessel diameters) and image quality of the 3D cines were compared to conventional breath hold cine and whole heart imaging. Results: All real-time data were successfully transformed into 3D cines with a total post-processing time of <1 min in all cases. There were no significant biases in any LV or RV metrics with reasonable limits of agreement and correlation. There is also reasonable agreement for all vessel diameters, although there was a small but significant overestimation of RPA diameter. Conclusion: We have demonstrated the potential of creating a 3D-cine data from concatenated 2D real-time cine images using a series of DL models. Our method has short acquisition and reconstruction times with fully segmented data being available within 2 minutes. The good agreement with conventional imaging suggests that our method could help to significantly speed up CMR in clinical practice.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。