在非对比心脏CT中,冠状动脉细分使用了基于解剖学的对比学习和合成数据
Jinkui Hao1, Xiaoyi He2, Gorkem Durak3
1Northwestern University, 737 N Michigan Avenue, Chicago, Illinois, 60611, UNITED STATES.
Physics in medicine and biology
|January 14, 2026
概括
一种新的深度学习方法,SynCAS,只使用合成数据,从非对比心脏CT (NCCT) 中准确分段冠状动脉. 这种方法克服了可见性差和注释稀缺性,使得大规模的心血管风险查能够在没有对比剂的情况下进行.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 心血管疾病研究研究
背景情况:
- 非对比心脏CT (NCCT) 是一种低剂量,具有成本效益的工具,用于冠状动脉疾病查.
- 在NCCT中,冠状动脉的自动细分是具有挑战性的,因为血管的可见性差,注释数据有限.
研究的目的:
- 开发一种深度学习方法,从NCCT图像中准确地对冠状动脉进行细分,而无需手动注释.
- 为了克服NCCT分析中船舶可见度差和数据稀缺的局限性.
主要方法:
- 提出了SynCAS (合成数据驱动的冠状动脉细分),这是一个完全基于合成数据进行训练的深度学习框架.
- 开发了一个合成的NCCT数据集生成管道,具有完美的地面真相.
- 引入了基于解剖学的对比学习策略,使用voxel级伪负样本来改善血管分化.
主要成果:
- 在公共和内部数据集上,SynCAS与最先进的无监督和域调整方法相比,表现优越.
- 该模型在不同数据集中显示出强大的概括能力,尽管仅在合成数据上进行训练.
- 从背景结构中有效区分冠状动脉,减少错误阳性.
结论:
- 在非对比成像中,SynCAS为冠状动脉分析提供了强大的解决方案.
- 促进了回顾性分析和大规模的心血管风险查,避免了与CCTA相关的风险.
- 介绍了一种新的方法来克服医学图像细分中的注释依赖.
相关概念视频
Imaging Studies for Cardiovascular System V: CT
284
Cardiac computed tomography (CT) scanning is an advanced cardiac imaging technique that utilizes CT technology, with or without intravenous (IV) contrast, to produce accurate cross-sectional virtual slices of specific areas of the heart, coronary circulation, and major blood vessels such as the aorta, pulmonary veins, and arteries. The computer processes these slices to generate three-dimensional images. Multidetector CT (MDCT) is a rapid form of CT scanning that captures multiple slices...
284
Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
395
Calcium-Scoring CT ScanA calcium-scoring CT scan, also known as coronary artery calcium (CAC) scan, detects calcium deposits in the coronary arteries. This test assesses the risk of coronary artery disease (CAD), which can lead to cardiovascular events such as angina, heart failure, and sudden cardiac arrest.A calcium-scoring CT scan is generally recommended for individuals at intermediate risk of CAD without symptoms. It includes:Men aged 40-75 and women aged 50-75: Especially those with a...
395


