Unsupervised inter-frame motion correction for whole-body dynamic PET using convolutional long short-term memory in a convolutional neural network

  title={Unsupervised inter-frame motion correction for whole-body dynamic PET using convolutional long short-term memory in a convolutional neural network},
  author={Xue-yuan Guo and Bo Zhou and David C. Pigg and Bruce S. Spottiswoode and Michael E. Casey and Chi Liu and Nicha C. Dvornek},
  journal={Medical image analysis},

Figures and Tables from this paper

Motion correction and its impact on quantification in dynamic total-body 18F-fluorodeoxyglucose PET

A correction framework that can effectively reduce the effect of random body movements on dynamic images and their associated quantification is demonstrated and can potentially benefit applications that require total-body assessment, such as imaging the brain-gut axis and systemic diseases.



VoxelMorph: A Learning Framework for Deformable Medical Image Registration

VoxelMorph promises to speed up medical image analysis and processing pipelines while facilitating novel directions in learning-based registration and its applications and demonstrates that the unsupervised model’s accuracy is comparable to the state-of-the-art methods while operating orders of magnitude faster.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

2016. 3d u-net: learning dense volumetric segmentation from sparse annotation, in: International conference on medical image computing and computerassisted intervention

  • 2016

Data-driven voluntary body motion detection and non-rigid event-by-event correction for static and dynamic PET

The proposed COD-based BMC approach successfully detected BMs and yielded superior correction results over conventional FIR approaches, and it is hypothesized that abrupt changes on the COD trace in lateral direction represent BMs.

Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting

This paper proposes the convolutional LSTM (ConvLSTM) and uses it to build an end-to-end trainable model for the precipitation nowcasting problem and shows that it captures spatiotemporal correlations better and consistently outperforms FC-L STM and the state-of-the-art operational ROVER algorithm.

Uformer: A General U-Shaped Transformer for Image Restoration

Uformer is an effective andcient Transformer-based architecture for image restoration, in which a hierarchical encoder-decoder network is built using the Transformer block and a learnable multi-scale restoration modulator in the form of a multi- scale spatial bias to adjust features in multiple layers of the Uformer decoder is proposed.

Automatic Inter-Frame Patient Motion Correction for Dynamic Cardiac PET Using Deep Learning

An automatic deep learning-based motion correction (DeepMC) method for dynamic cardiac PET that is much faster than the registration-based methods and can be easily integrated into the clinical workflow is developed.

A Deep Multitask Learning Framework Coupling Semantic Segmentation and Fully Convolutional LSTM Networks for Urban Change Detection

A UNet-like architecture (LUNet) which models the temporal relationship of spatial feature representations using integrated fully convolutional LSTM blocks on top of every encoding level without the need to downsample or flatten them, forming an end-to-end trainable framework.

MDPET: A Unified Motion Correction and Denoising Adversarial Network for Low-Dose Gated PET

Experimental results on human data demonstrated that the proposed MDPET can generate accurate motion estimation directly from low-dose gated images and produce high-quality motion-compensated low-noise reconstructions.

Real-time liver tracking algorithm based on LSTM and SVR networks for use in surface-guided radiation therapy

The LSTM-based integrated model performs well at predicting liver motion from external respiratory signals with system latencies of up to 450 ms and is necessary to update the external/internal correlation model continuously.