A cascade approach for automatic segmentation of cardiac structures in short-axis cine-MR images using deep neural networks. (1st July 2022)

• Record Type: Journal Article
• Authors: da Silva, Italo Francyles Santos; Silva, Aristófanes Corrêa; de Paiva, Anselmo Cardoso; Gattass, Marcelo
• Is Part Of: Expert systems with applications. Volume 197(2022)
• Publication Date: 2022-07-01
• Subjects: Cardiac structures segmentation -- Fully convolutional networks -- Cine-MRI -- ACDC dataset; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.116704
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: Cardiovascular diseases are responsible for millions of deaths every year. In this scenario, non-invasive exams such as cine-magnetic resonance imaging (cine-MRI) have favored a better understanding of these pathologies, helping early diagnosis and previous treatments essential to improve the quality of life of individuals. Through this exam, specialists can obtain more accurate information about cardiac structures, including the myocardium, the left ventricular cavity, and the right ventricle. Given this context, this work presents an automatic method for the segmentation of these cardiac structures in short-axis cine-MRI images. The proposed method uses a cascade approach and is therefore divided into three main steps. The first step consists of extracting a region of interest to reduce the scope of processing. The second applies a fully convolutional network proposed to generate the initial segmentations of the myocardium, left ventricular cavity, and right ventricle. These initial segmentations are passed on to the third step, called refinement, in which a mask reconstruction module based on U-Net is used to restore the generated segmentations. In addition, in this step some specific post-processing techniques are also applied for each structure of interest. The proposed method achieves promising results in tests with the ACDC challenge dataset, both at the local level, and in the evaluation made by the challenge's own platform, in which the proposed method proves to be competitive with the best approaches. Highlights: A computational method for automatic segmentation of cardiac structures is presented. Our method uses a cascaded approach combining FCNs and image processing techniques. The proposed method is validated with cine-MR images from ACDC dataset. The method achieves promising results, being competitive in the ACDC challenge.