arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.05798cs.CV
收藏

基于自监督学习的三维神经网络任务知识嵌入

Embedding Task Knowledge into 3D Neural Networks via Self-supervised Learning

Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Tencent Jarvis Lab(腾讯Jarvis实验室)

Jiuwen Zhu, Yuexiang Li, Yifan Hu, S. Kevin Zhou

摘要:

深度学习高度依赖于注释数据的数量。然而,注释医学图像是极其费力和昂贵的。为此,自监督学习(SSL),作为一个潜在的解决方案,缺乏注释的数据,吸引了越来越多的关注,从社区。然而,SSL方法通常设计一个不一定与目标任务相关的代理任务。在本文中,我们提出了一种新的SSL方法的三维医学图像分类,即任务相关的对比预测编码(TCPC),它嵌入到训练三维神经网络的任务知识。建议TCPC首先定位初始候选病变通过超体素估计使用简单的线性迭代聚类。然后,我们从潜在的病变区域周围裁剪的子体积中提取特征,并构建一个校准的对比预测编码方案用于自监督学习。在公共和私人数据集上进行了广泛的实验。实验结果表明,将病变相关先验知识嵌入到神经网络中用于三维医学图像分类是有效的。

英文摘要:

Deep learning highly relies on the amount of annotated data. However, annotating medical images is extremely laborious and expensive. To this end, self-supervised learning (SSL), as a potential solution for deficient annotated data, attracts increasing attentions from the community. However, SSL approaches often design a proxy task that is not necessarily related to target task. In this paper, we propose a novel SSL approach for 3D medical image classification, namely Task-related Contrastive Prediction Coding (TCPC), which embeds task knowledge into training 3D neural networks. The proposed TCPC first locates the initial candidate lesions via supervoxel estimation using simple linear iterative clustering. Then, we extract features from the sub-volume cropped around potential lesion areas, and construct a calibrated contrastive predictive coding scheme for self-supervised learning. Extensive experiments are conducted on public and private datasets. The experimental results demonstrate the effectiveness of embedding lesion-related prior-knowledge into neural networks for 3D medical image classification.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑