计算机科学
人工智能
加权
深度学习
样品(材料)
机器学习
特征学习
学习迁移
特征(语言学)
特征提取
元学习(计算机科学)
一般化
分割
模式识别(心理学)
医学影像学
管理
化学
任务(项目管理)
哲学
经济
数学分析
放射科
医学
色谱法
语言学
数学
作者
Yixiong Chen,Chunhui Zhang,Chris Ding,Li Liu
出处
期刊:IEEE Transactions on Medical Imaging
[Institute of Electrical and Electronics Engineers]
日期:2023-05-01
卷期号:42 (5): 1388-1400
被引量:3
标识
DOI:10.1109/tmi.2022.3228254
摘要
Well-annotated medical datasets enable deep neural networks (DNNs) to gain strong power in extracting lesion-related features. Building such large and well-designed medical datasets is costly due to the need for high-level expertise. Model pre-training based on ImageNet is a common practice to gain better generalization when the data amount is limited. However, it suffers from the domain gap between natural and medical images. In this work, we pre-train DNNs on ultrasound (US) domains instead of ImageNet to reduce the domain gap in medical US applications. To learn US image representations based on unlabeled US videos, we propose a novel meta-learning-based contrastive learning method, namely Meta Ultrasound Contrastive Learning (Meta-USCL). To tackle the key challenge of obtaining semantically consistent sample pairs for contrastive learning, we present a positive pair generation module along with an automatic sample weighting module based on meta-learning. Experimental results on multiple computer-aided diagnosis (CAD) problems, including pneumonia detection, breast cancer classification, and breast tumor segmentation, show that the proposed self-supervised method reaches state-of-the-art (SOTA). The codes are available at https://github.com/Schuture/Meta-USCL.
科研通智能强力驱动
Strongly Powered by AbleSci AI