Scalable High Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning

By Guorong Wu, Minjeong Kim, Qian Wang, Brent C. Munsell, Dinggang Shen. 2015

274 citations recorded by the source corpus.

Feature selection is a critical step in deformable image registration. In particular, selecting the most discriminative features that accurately and concisely describe complex morphological patterns in image patches improves correspondence detection, which in turn improves image registration accuracy. Furthermore, since more and more imaging modalities are being invented to better identify morphological changes in medical imaging data, the development of deformable image registration method that scales well to new image modalities or new image applications with little to no human intervention would have a significant impact on the medical image analysis community. To address these concerns, a learning-based image registration framework is proposed that uses deep learning to discover compact and highly discriminative features upon observed imaging data. Specifically, the proposed feature selection method uses a convolutional stacked autoencoder to identify intrinsic deep feature representations in image patches. Since deep learning is an unsupervised learning method, no ground truth label knowledge is required. This makes the proposed feature selection method more flexible to new imaging modalities since feature representations can be directly learned from the observed imaging data in a very short amount of time. Using the LONI and ADNI imaging datasets, image registration performance was compared to two existing state-of-the-art deformable image registration methods that use handcrafted features. To demonstrate the scalability of the proposed image registration framework, image registration experiments were conducted on 7.0-T brain MR images. In all experiments, the results showed that the new image registration framework consistently demonstrated more accurate registration results when compared to state of the art.

Subfields: Computer Vision and Pattern Recognition, Neurology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Neurology

Citations in the corpus

An overview of deep learning in medical imaging focusing on MRI (2018, methodology): “For example: deformable image registration [97,239]; model-to-image registration [240,241]; MRI-based attenuation correction for PET [242,243]; PET/MRI dose calculation [244]; unsupervised end-to-end learning for deformable registration of 2D CT/MR images [245]; an unsupervised learning model for de”
Understanding and Interpreting Machine Learning in Medical Image Computing Applications (2018, background): “This setting leverages on kernel approximation through sampling of basis functions in the spectral domain [14].”
An unsupervised convolutional neural network-based algorithm for deformable image registration (2018, methodology): “Previous models utilizing auto-encoders have shown promise when registering mono-modality brain MRI images (Wu et al 2016).”
Deep learning in medical image registration: a review (2019, background): “[164] has demonstrated that deep similarity network could be trained in an unsupervised manner, they only tested on unimodal image registration.”
An Artificial Agent for Robust Image Registration (2016, methodology): “Unsupervised learning using CNN was proposed in (Wu et al. 2015) to extract features for deformable registration.”
Deep learning in medical imaging and radiation therapy. (2018, methodology): “250 A deep encoder – decoder network was used for predictions for the large deformation diffeomorphic metric mapping model by Yang et al. 251 for fast deformable image registration.”
Recent advances and clinical applications of deep learning in medical image analysis (2021, background): “As one of the early works related to unsupervised registration, Wu et al. (2016) argued that supervised based registration methods do not generalize well on new data; they employed a convolutional stacked autoencoder (Lee et al., 2011) to extract features from fixed and moving images to improve…”
Deep Learning in Medical Image Analysis (2017, methodology): “However, networks with vectorized inputs were also successfully applied to different medical applications (47, 25, 27, 29, 48, 24, 49, 50).”
A Gentle Introduction to Deep Learning in Medical Image Processing (2018, background): “propose to do so using autoencoders to mine good features in an unsupervised way [81].”
Real-time Deep Pose Estimation with Geodesic Loss for Image-to-Template Rigid Registration (2018, background): “learn metrics to guide local deformations for multi-modal inter-subject registration [11], [12].”
CT Super-Resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE) (2018, background): “Hierarchical features and representations derived from a convolutional neural network (CNN) are leveraged to enhance discriminative capacity of visual quality, thus people have started developing SR models for natural images [29]–[34].”