Contrastive Learning for View Classification of Echocardiograms

Autor:	Chartsias, Agisilaos, Gao, Shan, Mumith, Angela, Oliveira, Jorge, Bhatia, Kanwal, Kainz, Bernhard, Beqiri, Arian
Rok vydání:	2021
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	Analysis of cardiac ultrasound images is commonly performed in routine clinical practice for quantification of cardiac function. Its increasing automation frequently employs deep learning networks that are trained to predict disease or detect image features. However, such models are extremely data-hungry and training requires labelling of many thousands of images by experienced clinicians. Here we propose the use of contrastive learning to mitigate the labelling bottleneck. We train view classification models for imbalanced cardiac ultrasound datasets and show improved performance for views/classes for which minimal labelled data is available. Compared to a naive baseline model, we achieve an improvement in F1 score of up to 26% in those views while maintaining state-of-the-art performance for the views with sufficiently many labelled training observations. Comment: Accepted in ASMUS workshop of MICCAI 2021
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2108.03124 Zobrazit plný text záznamu View this record from Arxiv