1. Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data
- Author
-
Jennifer Keegan, Raad Mohiaddin, David N. Firmin, Heye Zhang, Jun Chen, Tom Wong, Guang Yang, British Heart Foundation, European Research Council Horizon 2020, Commission of the European Communities, Innovative Medicines Initiative, and Medical Research Council (MRC)
- Subjects
FOS: Computer and information sciences ,Technology ,Computer Science - Machine Learning ,Generative adversarial networks ,Computer science ,Computer Vision and Pattern Recognition (cs.CV) ,cs.LG ,Computer Science - Computer Vision and Pattern Recognition ,Contrast Media ,Inference ,Gadolinium ,02 engineering and technology ,01 natural sciences ,09 Engineering ,Machine Learning (cs.LG) ,Predictive models ,Engineering ,cross-domain study ,0202 electrical engineering, electronic engineering, information engineering ,Segmentation ,ADAPTATION ,cs.CV ,Image segmentation ,Radiological and Ultrasound Technology ,Data domain ,Radiology, Nuclear Medicine & Medical Imaging ,LATE GADOLINIUM ENHANCEMENT ,Image and Video Processing (eess.IV) ,Data models ,Computer Science Applications ,Nuclear Medicine & Medical Imaging ,Computer Science, Interdisciplinary Applications ,FIBRILLATION ,Supervised Machine Learning ,Life Sciences & Biomedicine ,MEDICAL IMAGE SEGMENTATION ,Domain (software engineering) ,Consistency (database systems) ,Deep Learning ,bidirectional adversarial inference ,Robustness (computer science) ,FOS: Electrical engineering, electronic engineering, information engineering ,Heart Atria ,Electrical and Electronic Engineering ,Imaging Science & Photographic Technology ,hierarchical dual consistency ,Engineering, Biomedical ,Science & Technology ,business.industry ,010401 analytical chemistry ,Adaptation models ,Engineering, Electrical & Electronic ,020206 networking & telecommunications ,Pattern recognition ,Electrical Engineering and Systems Science - Image and Video Processing ,DUAL (cognitive architecture) ,Generators ,0104 chemical sciences ,Constraint (information theory) ,WHOLE HEART SEGMENTATION ,Computer Science ,Semi-supervised learning ,eess.IV ,Semisupervised learning ,08 Information and Computing Sciences ,Artificial intelligence ,business ,Software - Abstract
Semi-supervised learning provides great significance in left atrium (LA) segmentation model learning with insufficient labelled data. Generalising semi supervised learning to cross-domain data is of high importance to further improve model robustness. However, the widely existing distribution difference and sample mismatch between different data domains hinder the generalisation of semi-supervised learning. In this study, we alleviate these problems by proposing an Adaptive Hier10 archical Dual Consistency (AHDC) for the semi-supervised LA segmentation on cross-domain data. The AHDC mainly consists of a Bidirectional Adversarial Inference module (BAI) and a Hierarchical Dual Consistency learning module (HDC). The BAI overcomes the difference of distributions and the sample mismatch between two different domains. It mainly learns two mapping networks adversarially to obtain two matched domains through mutual adaptation. The HDC investigates a hierarchical dual learning paradigm for cross-domain semi-supervised segmentation based on the obtained matched domains. It mainly builds two dual modelling networks for mining the complementary information in both intra-domain and inter-domain. For the intra domain learning, a consistency constraint is applied to the dual-modelling targets to exploit the complementary modelling information. For the inter-domain learning, a consistency constraint is applied to the LAs modelled by two dual modelling networks to exploit the complementary knowl28 edge among different data domains. We demonstrated the performance of our proposed AHDC on four 3D late gadolinium enhancement cardiac MR (LGE-CMR) datasets from different centres and a 3D CT dataset. Compared to other state-of-the-art methods, our proposed AHDC achieved higher segmentation accuracy, which indicated its capability in the cross-domain semi-supervised LA segmentation.
- Published
- 2022