FeaCL:使用特征级和实例级对比度学习的超声波图像对状腺斑块进行分类
Cheng Li1, Kai Wang2, Haitao Gan1
1School of Computer Science, Hubei University of Technology, Wuhan 430068, China.
概括
一种新的自主监督学习方法,FeaCL,改善了从超声波图像的动脉斑块分类. 这种技术提高了诊断准确度,特别是当标记数据稀缺时,有助于评估心血管风险.
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:
- 从超声波图像中准确地分类 carotid 斑块对于预测心血管和脑血管疾病风险至关重要.
- 深度学习模型显示出有希望的结果,但受到有限的标记性带斑块图像数据集的阻碍.
研究的目的:
- 引入一种新型的自我监督学习技术,FeaCL (特征级和实例级对比学习),以提高带斑块分类的准确性.
- 为了应对有限的标记数据在训练深度学习模型进行动脉斑块分析的挑战.
主要方法:
- 在FeaCL中,使用强增强和弱增强的三重网络作为借口任务来学习强大的动脉斑块表示.
- 该方法在同一图像的不同增强视图中促进了功能和实例相似性.
- 从借口任务中预先训练的编码器在标记的超声波图像上进行微调,用于下游分类任务.
主要成果:
- 通过使用仅30%的培训数据,FeaCL实现了83.4%的分类准确度.
- 这与没有自我监督的借口任务训练的模型相比,相当于16.3%的显著改善.
- 该方法表明,即使有有限的标记数据,也能有效地学习状腺斑块特征.
结论:
- 从超声波图像来看,FeaCL显著提高了状腺斑块分类的准确性,特别是在低数据模式下.
- 自主监督方法有效地学习有意义的表示,改善临床医生的诊断能力.
- 这种技术为患有动脉疾病的患者的风险分层和治疗计划提供了宝贵的工具.
相关概念视频
Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
128
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...
128
Imaging Studies for Cardiovascular System V: CT
71
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...
71


