mlsanityData to 7 Oct 2026

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

arXiv 2206.06341 ↗First posted 13 Jun 2022eess.IV cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Subject motion in whole-body dynamic PET introduces inter-frame mismatch and seriously impacts parametric imaging. Traditional non-rigid registration methods are generally computationally intense and time-consuming. Deep learning approaches are promising in achieving high accuracy with fast speed, but have yet been investigated with consideration for tracer distribution changes or in the whole-body scope. In this work, we developed an unsupervised automatic deep learning-based framework to correct inter-frame body motion. The motion estimation network is a convolutional neural network with a combined convolutional long short-term memory layer, fully utilizing dynamic temporal features and spatial information. Our dataset contains 27 subjects each under a 90-min FDG whole-body dynamic PET scan. With 9-fold cross-validation, compared with both traditional and deep learning baselines, we demonstrated that the proposed network obtained superior performance in enhanced qualitative and quantitative spatial alignment between parametric Ki and Vb images and in significantly reduced parametric fitting error. We also showed the potential of the proposed motion correction method for impacting downstream analysis of the estimated parametric images, improving the ability to distinguish malignant from benign hypermetabolic regions of interest. Once trained, the motion estimation inference time of our proposed network was around 460 times faster than the conventional registration baseline, showing its potential to be easily applied in clinical settings.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 15 of its 57 references that are in the map. First posted on arXiv 13 Jun 2022.

Builds on

15 of 57 references.

References · 15

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  4. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  5. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  6. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  7. 2018Image Transformercited by 770
  8. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 657
  9. 2017Regularizing and Optimizing LSTM Language Modelscited by 205
  10. 2017Quicksilver: Fast Predictive Image Registration - a Deep Learning Approachcited by 113
  11. 2019Bi-Directional ConvLSTM U-Net with Densley Connected Convolutionscited by 82
  12. 2016Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentationcited by 25
3 more
  1. 2018Microscopy Cell Segmentation via Convolutional LSTM Networkscited by 17
  2. 2017Temporal HeartNet: Towards Human-Level Automatic Analysis of Fetal Cardiac Screening Videocited by 10
  3. 2018A multi-level convolutional LSTM model for the segmentation of left ventricle myocardium in infarcted porcine cine MR imagescited by 3

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 1.

4 papers.

  1. 2023Fast-MC-PET: A Novel Deep Learning-aided Motion Correction and Reconstruction Framework for Accelerated PETcited by 5
  2. 2024TAI-GAN: A Temporally and Anatomically Informed Generative Adversarial Network for early-to-late frame conversion in dynamic cardiac PET inter-frame motion correctioncited by 2
  3. 2023Whole-body PET image denoising for reduced acquisition timecited by 1
  4. 2023TAI-GAN: Temporally and Anatomically Informed GAN for early-to-late frame conversion in dynamic cardiac PET motion correctioncited by 1