Combining Deep Learning and Shape Priors for Bi-Ventricular Segmentation of Volumetric Cardiac Magnetic Resonance Images

Duan, Jinming; Schlemper, Jo; Bai, Wenjia; Dawes, Timothy J W; Bello, Ghalib; Biffi, Carlo; Doumou, Georgia; Marvao, Antonio de; O’Regan, Declan P.; Rueckert, Daniel

doi:10.1007/978-3-030-04747-4_24

Cited by 4 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This poses difficulty for existing image registration algorithms due to their non-convex nature. For this, the landmarks detected from SSLLN-HR and -LR were used to initialise the subsequent non-rigid algorithm between target and each atlas, which is similar to [27], [28]. An affine transformation with 12 degrees of freedom was first computed between the target landmarks (predicted by SSLLN-LR) and the atlas landmarks (predicted by SSLLN-HR).…”

Section: Introducing Anatomical Shape Prior Knowledgementioning

confidence: 99%

Automatic 3D Bi-Ventricular Segmentation of Cardiac Images by a Shape-Refined Multi- Task Deep Learning Approach

Duan

Bello

Schlemper

et al. 2019

IEEE Trans. Med. Imaging

Self Cite

188

109

View full text Add to dashboard Cite

Deep learning approaches have achieved state-of-the-art performance in cardiac magnetic resonance (CMR) image segmentation. However, most approaches have focused on learning image intensity features for segmentation, whereas the incorporation of anatomical shape priors has received less attention. In this paper, we combine a multi-task deep learning approach with atlas propagation to develop a shape-refined bi-ventricular segmentation pipeline for short-axis CMR volumetric images. The pipeline first employs a fully convolutional network (FCN) that learns segmentation and landmark localisation tasks simultaneously. The architecture of the proposed FCN uses a 2.5D representation, thus combining the computational advantage of 2D FCNs networks and the capability of addressing 3D spatial consistency without compromising segmentation accuracy. Moreover, a refinement step is designed to explicitly impose shape prior knowledge and improve segmentation quality. This step is effective for overcoming image artefacts (e.g. due to different breath-hold positions and large slice thickness), which preclude the creation of anatomically meaningful 3D cardiac shapes. The pipeline is fully automated, due to network’s ability to infer landmarks, which are then used downstream in the pipeline to initialise atlas propagation. We validate the pipeline on 1831 healthy subjects and 649 subjects with pulmonary hypertension. Extensive numerical experiments on the two datasets demonstrate that our proposed method is robust and capable of producing accurate, high-resolution and anatomically smooth bi-ventricular 3D models, despite the presence of artefacts in input CMR volumes.

show abstract

Section: Introducing Anatomical Shape Prior Knowledgementioning

confidence: 99%