AI自动分割心脏核磁心梗区域，准确度媲美专家
Deep Learning Pipeline for Fully Automated Myocardial Infarct Segmentation from Clinical Cardiac MR Scans
- 用2D与3D卷积网络构建级联模型，直接从LGE图像识别心梗疤痕
- 自动分割与人工测量的梗死体积相关性达0.9，专家更认可AI结果
- 无需预处理即可快速完成，适合临床高效应用
目的：开发并评估一种基于深度学习的全自动心肌梗死分割方法。材料与方法：本回顾性研究采用两级级联框架，结合二维与三维卷积神经网络（CNN），在包含144例检查的自建训练数据集上训练，用于识别延迟钆增强（LGE）心脏磁共振（CMR）图像中的缺血性心肌瘢痕。在同机构独立测试数据集（2021–2023年采集的152例）上，对人工智能（AI）分割与人工分割进行定量比较，并由两位CMR专家在盲法下评估分割准确性。结果：人工与自动计算的梗死体积具有优异一致性（ρ_c = 0.9）。定性评估显示，相较于人工测量，专家更常认为AI分割能更好反映实际梗死范围（AI 33.4% vs 人类 25.1%，相等 41.5%；p < 0.001）。而对于微血管阻塞（MVO）分割，人工测量仍更受青睐（人工 55.6%，AI 11.3%，相等 33.1%）。结论：该全自动分割流程可在极短时间内完成心梗体积计算，无需输入图像预处理，且分割质量可媲美受训人类观察者。在盲法实验中，专家更倾向于选择自动分割结果，为临床应用铺平道路。
原文摘要 · Abstract (English)
Purpose: To develop and evaluate a deep learning-based method that allows to perform myocardial infarct segmentation in a fully-automated way. Materials and Methods: For this retrospective study, a cascaded framework of two and three-dimensional convolutional neural networks (CNNs), specialized on identifying ischemic myocardial scars on late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) images, was trained on an in-house training dataset consisting of 144 examinations. On a separate test dataset from the same institution, including images from 152 examinations obtained between 2021 and 2023, a quantitative comparison between artificial intelligence (AI)-based segmentations and manual segmentations was performed. Further, qualitative assessment of segmentation accuracy was evaluated for both human and AI-generated contours by two CMR experts in a blinded experiment. Results: Excellent agreement could be found between manually and automatically calculated infarct volumes ($ρ_c$ = 0.9). The qualitative evaluation showed that compared to human-based measurements, the experts rated the AI-based segmentations to better represent the actual extent of infarction significantly (p < 0.001) more often (33.4% AI, 25.1% human, 41.5% equal). On the contrary, for segmentation of microvascular obstruction (MVO), manual measurements were still preferred (11.3% AI, 55.6% human, 33.1% equal). Conclusion: This fully-automated segmentation pipeline enables CMR infarct size to be calculated in a very short time and without requiring any pre-processing of the input images while matching the segmentation quality of trained human observers. In a blinded experiment, experts preferred automated infarct segmentations more often than manual segmentations, paving the way for a potential clinical application.
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。