Universal Semi-Supervised Learning for Medical Image Classification

TL;DR

This paper introduces a unified semi-supervised learning framework for medical image classification that effectively utilizes unseen classes and domains, improving performance in practical scenarios with limited labeled data.

Contribution

It proposes a novel approach combining outlier detection, VAE pre-training, and domain adaptation to leverage unseen unlabeled data in medical SSL tasks.

Findings

Achieves superior classification accuracy on dermatology and ophthalmology datasets.

Effectively identifies unseen classes and domains in semi-supervised settings.

Demonstrates robustness across various medical SSL scenarios.

Abstract

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.