Open Set Recognition for Endoscopic Image Classification: A Deep Learning Approach on the Kvasir Dataset

TL;DR

This paper evaluates the effectiveness of open set recognition techniques on endoscopic image classification using the Kvasir dataset, highlighting the importance of OSR for reliable AI deployment in clinical settings.

Contribution

It introduces the first application of open set recognition to the Kvasir dataset and benchmarks deep learning models' ability to identify unseen classes in medical images.

Findings

ResNet-50, Swin Transformer, and hybrid models show varying OSR capabilities.

OpenMax baseline provides a reference for distinguishing known and unknown classes.

Results emphasize the need for OSR in safe clinical AI applications.

Abstract

Endoscopic image classification plays a pivotal role in medical diagnostics by identifying anatomical landmarks and pathological findings. However, conventional closed-set classification frameworks are inherently limited in open-world clinical settings, where previously unseen conditions can arise andcompromise model reliability. To address this, we explore the application of Open Set Recognition (OSR) techniques on the Kvasir dataset, a publicly available and diverse endoscopic image collection. In this study, we evaluate and compare the OSR capabilities of several representative deep learning architectures, including ResNet-50, Swin Transformer, and a hybrid ResNet-Transformer model, under both closed-set and open-set conditions. OpenMax is adopted as a baseline OSR method to assess the ability of these models to distinguish known classes from previously unseen categories. This work represents one of the first efforts to apply open set recognition to the Kvasir dataset and provides a foundational benchmark for evaluating OSR performance in medical image analysis. Our results offer practical insights into model behavior in clinically realistic settings and highlight the importance of OSR techniques for the safe deployment of AI systems in endoscopy.