AUTHOR=Wang Yu , Zhang Wanjun 

TITLE=A Dense RNN for Sequential Four-Chamber View Left Ventricle Wall Segmentation and Cardiac State Estimation

JOURNAL=Frontiers in Bioengineering and Biotechnology

VOLUME=Volume 9 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2021.696227

DOI=10.3389/fbioe.2021.696227

ISSN=2296-4185

ABSTRACT=The segmentation of left ventricle(LV) wall in four-chamber view cardiac sequential image is significant for cardiac disease diagnosis and cardiac mechanisms study. However, there is no success reported work on sequential four-chamber view LV wall segmentation due to the complex four-chamber structure and diversity of wall motion. In this paper, we propose a dense Recurrent Neural Network(RNN) algorithm to achieve accurately LV wall segmentation in four-chamber view magnetic resonance imaging (MRI) time sequence. In cardiac sequential LV wall process, not only the sequential accuracy but also the accuracy of each image matters. Thus, we propose a dense RNN to provide compensation for the first long short term memory(LSTM) cell. Two RNNs are combined in our work, the first one aims at providing information for the first image and the second RNN generate segmentation result. In this way, the proposed dense RNN improves the accuracy of the first frame image. What's more, it improves the effectiveness of information flow between LSTM cell. Obtaining more competent information from the former cell, frame-wise segmentation accuracy is greatly improved. Based on the segmentation result, an algorithm is proposed to estimate cardiac state. This is the first time that deals with both cardiac time sequential LV segmentation problem and robustly estimate cardiac state. Rather than segment each frame separately, utilize cardiac sequence information is more stable. The proposed method ensures an Intersection over Union(IoU) of 92.13%, which outperforms other classical deep learning algorithms.