Mid-level image representations for real-time heart view plane classification of echocardiograms. (1st November 2015)

• Record Type: Journal Article
• Authors: Penatti, Otávio A.B.; Werneck, Rafael de O.; de Almeida, Waldir R.; Stein, Bernardo V.; Pazinato, Daniel V.; Mendes Júnior, Pedro R.; Torres, Ricardo da S.; Rocha, Anderson
• Is Part Of: Computers in biology and medicine. Volume 66(2015)
• Page Start: 66
• Page End: 81
• Publication Date: 2015-11-01
• Subjects: Echocardiography -- Feature extraction -- Real-time systems -- Image classification -- Pattern analysis; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2015.08.004
• Languages: English
• ISSNs: 0010-4825

Abstract

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 problem, 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. Abstract : Highlights: Proposal of new mid-level representations for real-time heart view plane classification of 2D echocardiograms. Approach relies on bags of visual words with image sampling using large regions. Extensive set of experiments comparing the proposed method with existing descriptors. Evaluation considering real-time constraints, noise filtering, and different machine learning classifiers. Proposed approach is very fast to compute and consistently achieves accuracy above 90%.