■心脏结构和功能异常可以通过心脏磁共振成像(CMR)进行非侵入性检查。由于MR设备的发展,诊断扫描可以捕获越来越多关于可能的心脏病的相关信息。T1和T2映射是这样的新技术,提供组织特异性信息,即使没有对比材料的管理。基于深度学习的人工智能解决方案已经在许多应用领域展示了最先进的成果,包括医学成像。更具体地说,在过去的五年中,电影序列中应用的自动化工具彻底改变了CMR报告的容量。将深度学习模型应用于T1和T2映射图像可以类似地提高后处理管道的效率,从而促进诊断过程。
■在本文中,我们引入了一种用于心肌分割的深度学习模型,该模型在来自262名异质性疾病病因受试者的7,000多幅原始CMR图像上进行了训练。数据由三位专家标记。作为评估的一部分,计算专家之间的骰子得分和豪斯多夫距离,并将专家共识与模型的预测进行比较。
■我们的深度学习方法获得了86%的平均骰子得分,而由三位专家提供的相同数据的轮廓显示90%的平均骰子得分。该方法的准确性在心外膜和心内膜轮廓上是一致的,在基础上,脑室中段切片,根尖切片的结果只有5%低,这甚至对专家来说都是具有挑战性的。
■我们在262个异构CMR案例中训练并评估了基于深度学习的分割模型。将深度神经网络应用于T1和T2映射可以类似地改善诊断实践。使用T1和T2映射图像和高质量标签的精细细节,这项研究的目的是通过深度学习来接近人体分割的准确性。
UNASSIGNED: Structural and functional heart abnormalities can be examined non-invasively with cardiac magnetic resonance imaging (CMR). Thanks to the development of MR devices, diagnostic scans can capture more and more relevant information about possible heart diseases. T1 and T2 mapping are such novel technology, providing tissue specific information even without the administration of contrast material. Artificial intelligence solutions based on deep learning have demonstrated state-of-the-art results in many application areas, including medical imaging. More specifically, automated tools applied at cine sequences have revolutionized volumetric CMR reporting in the past five years. Applying deep learning models to T1 and T2 mapping images can similarly improve the efficiency of post-processing pipelines and consequently facilitate diagnostic processes.
UNASSIGNED: In this paper, we introduce a deep learning model for myocardium segmentation trained on over 7,000 raw CMR images from 262 subjects of heterogeneous disease etiology. The data were labeled by three experts. As part of the evaluation, Dice score and Hausdorff distance among experts is calculated, and the expert consensus is compared with the model\'s predictions.
UNASSIGNED: Our deep learning method achieves 86% mean Dice score, while contours provided by three experts on the same data show 90% mean Dice score. The method\'s accuracy is consistent across epicardial and endocardial contours, and on basal, midventricular slices, with only 5% lower results on apical slices, which are often challenging even for experts.
UNASSIGNED: We trained and evaluated a deep learning based segmentation model on 262 heterogeneous CMR cases. Applying deep neural networks to T1 and T2 mapping could similarly improve diagnostic practices. Using the fine details of T1 and T2 mapping images and high-quality labels, the objective of this research is to approach human segmentation accuracy with deep learning.