UCDSC: Open Set UnCertainty aware Deep Simplex Classifier for Medical Image Datasets

TL;DR

This paper introduces UCDSC, a deep simplex classifier with an open set recognition capability that effectively identifies unknown medical image samples, addressing data scarcity and class ambiguity in real-world medical diagnosis scenarios.

Contribution

It proposes a novel loss function that enhances open set recognition in deep classifiers by penalizing open space regions, improving detection of unknown classes in medical imaging.

Findings

Achieves significant performance improvements on four MedMNIST datasets.

Outperforms state-of-the-art open set recognition methods.

Effectively rejects unknown samples in medical image classification.

Abstract

Driven by advancements in deep learning, computer-aided diagnoses have made remarkable progress. However, outside controlled laboratory settings, algorithms may encounter several challenges. In the medical domain, these difficulties often stem from limited data availability due to ethical and legal restrictions, as well as the high cost and time required for expert annotations-especially in the face of emerging or rare diseases. In this context, open-set recognition plays a vital role by identifying whether a sample belongs to one of the known classes seen during training or should be rejected as an unknown. Recent studies have shown that features learned in the later stages of deep neural networks are observed to cluster around their class means, which themselves are arranged as individual vertices of a regular simplex [32]. The proposed method introduces a loss function designed to reject samples of unknown classes effectively by penalizing open space regions using auxiliary datasets. This approach achieves significant performance gain across four MedMNIST datasets-BloodMNIST, OCTMNIST, DermaMNIST, TissueMNIST and a publicly available skin dataset [29] outperforming state-of-the-art techniques.