SAUN: Stack attention U‐Net for left ventricle segmentation from cardiac cine magnetic resonance imaging

Medical Physics, vol. 48, pp. 1750–1763

Abstract

PURPOSE: Quantification of left ventricular (LV) volume, ejection fraction and myocardial mass from multi-slice multi-phase cine MRI requires accurate segmentation of the LV in many images. We propose a stack attention-based convolutional neural network (CNN) approach for fully automatic segmentation from short-axis cine MR images. METHODS: To extract the relevant spatiotemporal image features, we introduce two kinds of stack methods, spatial stack model and temporal stack model, combining the target image with its neighboring images as the input of a CNN. A stack attention mechanism is proposed to weigh neighboring image slices in order to extract the relevant features using the target image as a guide. Based on stack attention and standard U-Net, a novel Stack Attention U-Net (SAUN) is proposed and trained to perform the semantic segmentation task. A loss function combining cross-entropy and Dice is used to train SAUN. The performance of the proposed method was evaluated on an internal and a public dataset using technical metrics including Dice, Hausdorff distance (HD), and mean contour distance (MCD), as well as clinical parameters, including left ventricular ejection fraction (LVEF) and myocardial mass (LVM). In addition, the results of SAUN were compared to previously presented CNN methods, including U-Net and SegNet. RESULTS: The spatial stack attention model resulted in better segmentation results than the temporal stack model. On the internal dataset comprising of 167 post-myocardial infarction patients and 57 healthy volunteers, our method achieved a mean Dice of 0.91, HD of 3.37 mm, and MCD of 1.08 mm. Evaluation on the publicly available ACDC dataset demonstrated good generalization performance, yielding a Dice of 0.92, HD of 9.4 mm, and MCD of 0.74 mm on end-diastolic images, and a Dice of 0.89, HD of 7.1 mm and MCD of 1.03 mm on end-systolic images. The Pearson correlation coefficient of LVEF and LVM between automatically and manually derived results were higher than 0.98 in both datasets. CONCLUSION: We developed a CNN with a stack attention mechanism to automatically segment the LV chamber and myocardium from the multi-slice short-axis cine MRI. The experimental results demonstrate that the proposed approach exceeds existing state-of-the-art segmentation methods and verify its potential clinical applicability.

Authors 4

1. Xiaowu Sun Aachen Division of Image Processing (LKEB) Department of Radiology, Leiden University Medical Center

   Leiden University Medical Center

   Affiliation as printed

   Division of Image Processing Department of Radiology Leiden University Medical Center PO Box 9600 Leiden 2300 RC The Netherlands

   Division of Image Processing, Department of Radiology, Leiden University Medical Center, PO Box 9600, Leiden, 2300 RC The Netherlands

2. Pankaj Garg

   University of Sheffield

   Affiliation as printed

   Department of Infection Immunity & Cardiovascular Disease University of Sheffield Sheffield UK

   Department of Infection, Immunity & Cardiovascular Disease, University of Sheffield, Sheffield, UK

3. Sven Plein

   University of Leeds

   Affiliation as printed

   Department of Biomedical Imaging Science Leeds Institute of Cardiovascular and Metabolic Medicine University of Leeds Leeds UK

   Department of Biomedical Imaging Science, Leeds Institute of Cardiovascular and Metabolic Medicine University of Leeds, Leeds, UK

4. Rob J. van der Geest corresponding Aachen Division of Image Processing (LKEB) Department of Radiology, Leiden University Medical Center

   Leiden University Medical Center

   Affiliation as printed

   Division of Image Processing Department of Radiology Leiden University Medical Center PO Box 9600 Leiden 2300 RC The Netherlands

   Division of Image Processing, Department of Radiology, Leiden University Medical Center, PO Box 9600, Leiden, 2300 RC The Netherlands