Generalizable Framework for Atrial Volume Estimation for Cardiac CT Images Using Deep Learning With Quality Control Assessment.
Generalizable Framework for Atrial Volume Estimation for Cardiac CT Images Using Deep Learning With Quality Control Assessment.
复制标题
使用深度学习和质量控制评估的深度学习对心脏CT图像进行心房体积估算的可通用框架。
DOI：
10.3389/fcvm.2022.822269
复制
发表时间：
2022
影响因子：
3.6
通讯作者：
Petersen SE
中科院分区：
文献类型：
--
作者：
Abdulkareem M;Brahier MS;Zou F;Taylor A;Thomaides A;Bergquist PJ;Srichai MB;Lee AM;Vargas JD;Petersen SE
心脏计算机断层扫描（CCT）是一种常见的术前成像方式，用于评价接受导管消融（CA）治疗房颤（AF）的患者的肺静脉解剖结构和左心耳血栓。这些图像还允许完整的左心房（LA）体积测量用于复发风险分层，因为较大的LA体积（LAV）与较高的复发率相关。我们的目标是应用深度学习（DL）技术来完全自动化LAV的计算，并评估计算出的LAV值的质量。使用来自337名患者的85，477个CCT图像的数据集，我们提出了一个框架，该框架由执行任务组合的几个过程组成，包括使用ResNet50分类模型从所有其他图像中选择具有LA的图像，使用UNet图像分割模型分割具有LA的图像，评估图像分割任务的质量，估计LAV，质量控制（QC）评估。总体而言，所提出的LAV估计框架在图像分类任务中实现了98%的准确率（精确度，召回率和F1得分指标），在图像分割任务中实现了88.5%的准确率（平均骰子得分），在分割质量预测任务中实现了82%的准确率（平均骰子得分），在体积估计任务中实现了0.968的R2（确定系数）值。它正确地识别了来自总共337名患者的10个不良LAV估计中的9个为质量差的估计。我们提出了一个可推广的框架，包括DL模型和LAV估计的计算方法。该框架为基于DL的图像分割和体积估计任务的准确性的QC评估提供了一种有效且稳健的策略，从而可以高通量提取可再现的LAV测量值。
Cardiac computed tomography (CCT) is a common pre-operative imaging modality to evaluate pulmonary vein anatomy and left atrial appendage thrombus in patients undergoing catheter ablation (CA) for atrial fibrillation (AF). These images also allow for full volumetric left atrium (LA) measurement for recurrence risk stratification, as larger LA volume (LAV) is associated with higher recurrence rates. Our objective is to apply deep learning (DL) techniques to fully automate the computation of LAV and assess the quality of the computed LAV values. Using a dataset of 85,477 CCT images from 337 patients, we proposed a framework that consists of several processes that perform a combination of tasks including the selection of images with LA from all other images using a ResNet50 classification model, the segmentation of images with LA using a UNet image segmentation model, the assessment of the quality of the image segmentation task, the estimation of LAV, and quality control (QC) assessment. Overall, the proposed LAV estimation framework achieved accuracies of 98% (precision, recall, and F1 score metrics) in the image classification task, 88.5% (mean dice score) in the image segmentation task, 82% (mean dice score) in the segmentation quality prediction task, and R2 (the coefficient of determination) value of 0.968 in the volume estimation task. It correctly identified 9 out of 10 poor LAV estimations from a total of 337 patients as poor-quality estimates. We proposed a generalizable framework that consists of DL models and computational methods for LAV estimation. The framework provides an efficient and robust strategy for QC assessment of the accuracy for DL-based image segmentation and volume estimation tasks, allowing high-throughput extraction of reproducible LAV measurements to be possible.