Automatic Whole Heart Segmentation Using Deep Learning and Shape Context

• Published in: Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges Vol. 10663; pp. 242 - 249
• Main Authors: Wang, Chunliang, Smedby, Örjan
• Format: Book Chapter Conference Proceeding
• Language: English
• Published: Switzerland Springer International Publishing AG 2018; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Deep learning; Fully convolutional network; Heart segmentation; Shape context; Statistic shape model
• ISBN: 9783319755403; 3319755404
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-75541-0_26

To assist 3D cardiac image analysis, we propose an automatic whole heart segmentation using a deep learning framework combined with shape context information that is encoded in volumetric shape models. The proposed processing pipeline consists of three major steps: scout segmentation with orthogonal 2D U-nets, shape context estimation and refining segmentation with U-net and shape context. The proposed method was evaluated using the MMWHS challenge data. Two sets of networks were trained separately for contrast-enhanced CT and MRI. On the 20 training datasets, using 5-fold cross-validation, the average Dice coefficients for the left ventricle, the right ventricle, the left atrium, the right atrium and the myocardium of the left ventricle were 0.895, 0.795, 0.847, 0.821, 0.807 for MRI and 0.935, 0.825, 0.908, 0.881, 0.879 for CT, respectively. Further improvement may be possible given more training data or advanced data augmentation strategy.