arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.04059cs.CV
收藏

面向医学图像分类的通用半监督学习

Universal Semi-Supervised Learning for Medical Image Classification

Monash-Airdoc Research(莫纳什-鹰瞳研究中心);Monash University(莫纳什大学);eResearch Centre(电子研究中心);Monash Medical AI Group(莫纳什医学人工智能团队);Faculty of Information Technology(信息技术学院);Harbin Engineering University(哈尔滨工程大学);Centre for Eye Research Australia(澳大利亚眼科研究中心);Melbourne University(墨尔本大学)

Lie Ju, Yicheng Wu, Wei Feng, Zhen Yu, Lin Wang, Zhuoting Zhu, Zongyuan Ge

AI总结:

本文提出统一的开放场景半监督医学图像分类框架,通过双路径异常值估计识别未见类别、VAE预训练提取未见域并进行域适应,在皮肤科和眼科任务上取得优异性能。

摘要:

半监督学习(SSL)因其能够降低收集充足且标注良好的训练数据所需的高昂成本而备受关注,尤其对于深度学习方法而言。然而,传统SSL建立在一个假设之上,即有标签数据和无标签数据应来自相同分布,例如相同的类别和域。但在实际场景中,无标签数据可能来自未见类别或未见域,如何利用这些数据对现有SSL方法而言仍具挑战性。因此,本文提出一个统一框架,以利用这些未见的无标签数据进行开放场景下的半监督医学图像分类。我们首先设计一种名为双路径异常值估计的新颖评分机制,用于识别来自未见类别的样本。同时,为提取未见域样本,我们随后采用有效的变分自编码器(VAE)预训练。之后,我们执行域适应,以充分挖掘所检测到的未见域样本的价值,从而促进半监督训练。我们在皮肤科和眼科任务上评估了所提出的框架。大量实验表明,我们的模型能够在多种医学SSL场景中取得优异的分类性能。代码实现可在 https://github.com/PyJulie/USSL4MIC 获取。

英文摘要:

Semi-supervised learning (SSL) has attracted much attention since it reduces the expensive costs of collecting adequate well-labeled training data, especially for deep learning methods. However, traditional SSL is built upon an assumption that labeled and unlabeled data should be from the same distribution \textit{e.g.,} classes and domains. However, in practical scenarios, unlabeled data would be from unseen classes or unseen domains, and it is still challenging to exploit them by existing SSL methods. Therefore, in this paper, we proposed a unified framework to leverage these unseen unlabeled data for open-scenario semi-supervised medical image classification. We first design a novel scoring mechanism, called dual-path outliers estimation, to identify samples from unseen classes. Meanwhile, to extract unseen-domain samples, we then apply an effective variational autoencoder (VAE) pre-training. After that, we conduct domain adaptation to fully exploit the value of the detected unseen-domain samples to boost semi-supervised training. We evaluated our proposed framework on dermatology and ophthalmology tasks. Extensive experiments demonstrate our model can achieve superior classification performance in various medical SSL scenarios. The code implementations are accessible at: https://github.com/PyJulie/USSL4MIC.

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。

↑