In echocardiographic view classification, accurately detecting out-of-distribution (OOD) data is essential but challenging, especially given the subtle differences between in-distribution and OOD data. While conventional OOD detection methods, such as Mahalanobis distance (MD) are effective in far-OOD scenarios with clear distinctions between distributions, they struggle to discern the less obvious variations characteristic of echocardiographic data. In this study, we introduce a novel use of label smoothing to enhance semantic feature representation in echocardiographic images, demonstrating that these enriched semantic features are key for significantly improving near-OOD instance detection. By combining label smoothing with MD-based OOD detection, we establish a new benchmark for accuracy in echocardiographic OOD detection.
@article{arxiv.2308.16483,
title = {Improving Out-of-Distribution Detection in Echocardiographic View Classication through Enhancing Semantic Features},
author = {Jaeik Jeon and Seongmin Ha and Yeonggul Jang and Yeonyee E. Yoon and Jiyeon Kim and Hyunseok Jeong and Dawun Jeong and Youngtaek Hong and Seung-Ah Lee Hyuk-Jae Chang},
journal= {arXiv preprint arXiv:2308.16483},
year = {2023}
}