Open-Set Semi-Supervised Learning for Long-Tailed Medical Datasets

TL;DR

This paper introduces an open-set semi-supervised learning method tailored for imbalanced medical image datasets, improving recognition of rare and unseen classes through feature regularization and classifier normalization.

Contribution

The authors propose a novel open-set semi-supervised learning approach that addresses class imbalance and unseen classes in medical imaging, with specific regularization and normalization techniques.

Findings

Significant improvement in open-set accuracy across datasets

Enhanced performance on highly imbalanced data

Effective handling of unseen classes in medical image recognition

Abstract

Many practical medical imaging scenarios include categories that are under-represented but still crucial. The relevance of image recognition models to real-world applications lies in their ability to generalize to these rare classes as well as unseen classes. Real-world generalization requires taking into account the various complexities that can be encountered in the real-world. First, training data is highly imbalanced, which may lead to model exhibiting bias toward the more frequently represented classes. Moreover, real-world data may contain unseen classes that need to be identified, and model performance is affected by the data scarcity. While medical image recognition has been extensively addressed in the literature, current methods do not take into account all the intricacies in the real-world scenarios. To this end, we propose an open-set learning method for highly imbalanced medical datasets using a semi-supervised approach. Understanding the adverse impact of long-tail distribution at the inherent model characteristics, we implement a regularization strategy at the feature level complemented by a classifier normalization technique. We conduct extensive experiments on the publicly available datasets, ISIC2018, ISIC2019, and TissueMNIST with various numbers of labelled samples. Our analysis shows that addressing the impact of long-tail data in classification significantly improves the overall performance of the network in terms of closed-set and open-set accuracies on all datasets. Our code and trained models will be made publicly available at https://github.com/Daniyanaj/OpenLTR.