Please use this identifier to cite or link to this item:
Type: Artigo de periódico
Title: Mid-level Image Representations For Real-time Heart View Plane Classification Of Echocardiograms
Author: Penatti
Otavio A. B.; Werneck
Rafael de O.; de Almeida
Waldir R.; Stein
Bernardo V.; Pazinato
Daniel V.; Mendes Junior
Pedro R.; Torres
Ricardo da S.; Rocha
Abstract: In this paper, we explore mid-level image representations for real-time heart view plane classification of 2D echocardiogram ultrasound images. The proposed representations rely on bags of visual words, successfully used by the computer vision community in visual recognition problems. An important element of the proposed representations is the image sampling with large regions, drastically reducing the execution time of the image characterization procedure. Throughout an extensive set of experiments, we evaluate the proposed approach against different image descriptors for classifying four heart view planes. The results show that our approach is effective and efficient for the target problelm, making it suitable for use in real-time setups. The proposed representations are also robust to different image transformations, e.g., downsampling, noise filtering, and different machine learning classifiers, keeping classification accuracy above 90%. Feature extraction can be performed in 30 fps or 60 fps in some cases. This paper also includes an in-depth review of the literature in the area of automatic echocardiogram view classification giving the reader a through comprehension of this field of study. (C) 2015 Elsevier Ltd. All rights reserved.
Subject: Texture
Country: OXFORD
Citation: Mid-level Image Representations For Real-time Heart View Plane Classification Of Echocardiograms. Pergamon-elsevier Science Ltd, v. 66, p. 66-81 Nov-2015.
Rights: embargo
Identifier DOI: 10.1016/j.compbiomed.2015.08.004
Date Issue: 2015
Appears in Collections:Unicamp - Artigos e Outros Documentos

Files in This Item:
File SizeFormat 
wos_000365367400007.pdf1.8 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.