Anatomically Constrained Neural Networks (ACNN): application to cardiac image enhancement and segmentation
File(s)
Supporting information
Published version
Author(s)
Type
Journal Article
Abstract
Incorporation of prior knowledge about organ shape and location is key to improve performance of image analysis approaches. In particular, priors can be useful in cases where images are corrupted and contain artefacts due to limitations in image acquisition. The highly constrained nature of anatomical objects can be well captured with learning based techniques. However, in most recent and promising techniques such as CNN based segmentation it is not obvious how to incorporate such prior knowledge. State-of-the-art methods operate as pixel-wise classifiers where the training objectives do not incorporate the structure and inter-dependencies of the output. To overcome this limitation, we propose a generic training strategy that incorporates anatomical prior knowledge into CNNs through a new regularisation model, which is trained end-to-end. The new framework encourages models to follow the global anatomical properties of the underlying anatomy (e.g. shape, label structure) via learnt non-linear representations of the shape. We show that the proposed approach can be easily adapted to different analysis tasks (e.g. image enhancement, segmentation) and improve the prediction accuracy of the state-of-the-art models. The applicability of our approach is shown on multi-modal cardiac datasets and public benchmarks. Additionally, we demonstrate how the learnt deep models of 3D shapes can be interpreted and used as biomarkers for classification of cardiac pathologies.
Date Issued
2018-02-01
Date Acceptance
2017-08-14
Citation
IEEE Transactions on Medical Imaging, 2018, 37 (2), pp.384-395
ISSN
0278-0062
Publisher
IEEE
Start Page
384
End Page
395
Journal / Book Title
IEEE Transactions on Medical Imaging
Volume
37
Issue
2
Copyright Statement
© 2017 IEEE. This work is licensed under a Creative Commons Attribution 3.0 License. For more information, see http://creativecommons.org/licenses/by/3.0/.
License URL
Sponsor
Engineering & Physical Science Research Council (EPSRC)
British Heart Foundation
Imperial College Healthcare NHS Trust- BRC Funding
Grant Number
EP/P001009/1
PG/12/27/29489
RDC04
Subjects
Science & Technology
Technology
Life Sciences & Biomedicine
Computer Science, Interdisciplinary Applications
Engineering, Biomedical
Engineering, Electrical & Electronic
Imaging Science & Photographic Technology
Radiology, Nuclear Medicine & Medical Imaging
Computer Science
Engineering
Shape prior
convolutional neural network
medical image segmentation
image super-resolution
AUTOMATIC SEGMENTATION
SHAPE MODELS
VENTRICLE
Algorithms
Cardiac Imaging Techniques
Cardiomyopathies
Databases, Factual
Heart
Humans
Imaging, Three-Dimensional
Magnetic Resonance Imaging
Neural Networks, Computer
Heart
Humans
Cardiomyopathies
Imaging, Three-Dimensional
Magnetic Resonance Imaging
Algorithms
Databases, Factual
Cardiac Imaging Techniques
Neural Networks, Computer
cs.CV
cs.CV
Nuclear Medicine & Medical Imaging
08 Information and Computing Sciences
09 Engineering
Publication Status
Published
Date Publish Online
2017-09-26