Few-Shot Learning by a Cascaded Framework With Shape-Constrained Pseudo Label Assessment for Whole Heart Segmentation
- 20 January 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 40 (10), 2629-2641
- https://doi.org/10.1109/tmi.2021.3053008
Abstract
Automatic and accurate 3D cardiac image segmentation plays a crucial role in cardiac disease diagnosis and treatment. Even though CNN based techniques have achieved great success in medical image segmentation, the expensive annotation, large memory consumption, and insufficient generalization ability still pose challenges to their application in clinical practice, especially in the case of 3D segmentation from high-resolution and large-dimension volumetric imaging. In this paper, we propose a few-shot learning framework by combining ideas of semi-supervised learning and self-training for whole heart segmentation and achieve promising accuracy with a Dice score of 0.890 and a Hausdorff distance of 18.539 mm with only four labeled data for training. When more labeled data provided, the model can generalize better across institutions. The key to success lies in the selection and evolution of high-quality pseudo labels in cascaded learning. A shape-constrained network is built to assess the quality of pseudo labels, and the self-training stages with alternative global-local perspectives are employed to improve the pseudo labels. We evaluate our method on the CTA dataset of the MM-WHS 2017 Challenge and a larger multi-center dataset. In the experiments, our method outperforms the state-of-the-art methods significantly and has great generalization ability on the unseen data. We also demonstrate, by a study of two 4D (3D+T) CTA data, the potential of our method to be applied in clinical practice.Keywords
Funding Information
- Beijing Nova Program (Z201100006820064)
- National Key Research and Development Project of China (2020YFC2004800)
- STCSMunder (19511121400)
- Beijing Postdoctoral Research Foundation
This publication has 42 references indexed in Scilit:
- V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Multi-scale patch and multi-modality atlases for whole heart segmentation of MRIMedical Image Analysis, 2016
- A homotopy-based sparse representation for fast and accurate shape prior modeling in liver surgical planningMedical Image Analysis, 2014
- Challenges and Methodologies of Fully Automatic Whole Heart Segmentation: A ReviewJournal of Healthcare Engineering, 2013
- Deformable segmentation via sparse representation and dictionary learningMedical Image Analysis, 2012
- Towards robust and effective shape modeling: Sparse shape compositionMedical Image Analysis, 2012
- Heart chambers and whole heart segmentation techniques: reviewJournal of Electronic Imaging, 2012
- Cardiac CT and CT coronary angiography: technology and applicationHeart, 2008
- Hierarchical active shape models, using the wavelet transformIEEE Transactions on Medical Imaging, 2003
- Active Shape Models-Their Training and ApplicationComputer Vision and Image Understanding, 1995