3D Consistent & Robust Segmentation of Cardiac Images by Deep Learning with Spatial Propagation
This work addresses the problem of inconsistent 3D segmentation in cardiac imaging for medical professionals, offering improved spatial consistency and generalization, though it is incremental as it builds on existing U-net architectures.
The authors tackled cardiac segmentation in MRI image stacks by proposing a deep learning method that enforces 3D consistency through iterative spatial propagation from top to bottom slices, achieving results comparable to or better than state-of-the-art in distance measures on multiple datasets, including UK Biobank and other cohorts.
We propose a method based on deep learning to perform cardiac segmentation on short axis MRI image stacks iteratively from the top slice (around the base) to the bottom slice (around the apex). At each iteration, a novel variant of U-net is applied to propagate the segmentation of a slice to the adjacent slice below it. In other words, the prediction of a segmentation of a slice is dependent upon the already existing segmentation of an adjacent slice. 3D-consistency is hence explicitly enforced. The method is trained on a large database of 3078 cases from UK Biobank. It is then tested on 756 different cases from UK Biobank and three other state-of-the-art cohorts (ACDC with 100 cases, Sunnybrook with 30 cases, RVSC with 16 cases). Results comparable or even better than the state-of-the-art in terms of distance measures are achieved. They also emphasize the assets of our method, namely enhanced spatial consistency (currently neither considered nor achieved by the state-of-the-art), and the generalization ability to unseen cases even from other databases.