mlsanityData to 7 Oct 2026

Learning deep abdominal CT registration through adaptive loss weighting and synthetic data generation

arXiv 2211.15717 ↗First posted 28 Nov 2022eess.IV cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Purpose: This study aims to explore training strategies to improve convolutional neural network-based image-to-image deformable registration for abdominal imaging. Methods: Different training strategies, loss functions, and transfer learning schemes were considered. Furthermore, an augmentation layer which generates artificial training image pairs on-the-fly was proposed, in addition to a loss layer that enables dynamic loss weighting. Results: Guiding registration using segmentations in the training step proved beneficial for deep-learning-based image registration. Finetuning the pretrained model from the brain MRI dataset to the abdominal CT dataset further improved performance on the latter application, removing the need for a large dataset to yield satisfactory performance. Dynamic loss weighting also marginally improved performance, all without impacting inference runtime. Conclusion: Using simple concepts, we improved the performance of a commonly used deep image registration architecture, VoxelMorph. In future work, our framework, DDMR, should be validated on different datasets to further assess its value.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 16 of its 42 references that are in the map. First posted on arXiv 28 Nov 2022.

Builds on

16 of 42 references.

References · 16

  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. 2015Spatial Transformer Networkscited by 1,423
  5. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  6. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
  7. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 657
  8. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 221
  9. 2020Large Deformation Diffeomorphic Image Registration with Laplacian Pyramid Networkscited by 136
  10. 2021Learn2Reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learningcited by 125
  11. 2017Quicksilver: Fast Predictive Image Registration - a Deep Learning Approachcited by 113
  12. 2018Weakly-Supervised Convolutional Neural Networks for Multimodal Image Registrationcited by 90
4 more
  1. 2022U-Net vs Transformer: Is U-Net Outdated in Medical Image Registration?cited by 40
  2. 2018Non-Rigid Image Registration Using Self-Supervised Fully Convolutional Networks without Training Datacited by 24
  3. 2020Medical image reconstruction with image-adaptive priors learned by use of generative adversarial networkscited by 11
  4. 2017MRI-PET Registration with Automated Algorithm in Pre-clinical Studiescited by 1

Built on by

Cited by year

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

4 papers.

  1. 2024Deep Learning in Medical Image Registration: Magic or Mirage?cited by 20
  2. 2024Deep Implicit Optimization enables Robust Learnable Features for Deformable Image Registrationcited by 5
  3. 2024NCA-Morph: Medical Image Registration with Neural Cellular Automatacited by 4
  4. 2023TRUSTED: The Paired 3D Transabdominal Ultrasound and CT Human Data for Kidney Segmentation and Registration Researchcited by 3