DeepAI AI Chat
Log In Sign Up

Train smarter, not harder: learning deep abdominal CT registration on scarce data

by   Javier Pérez de Frutos, et al.

Purpose: This study aims to explore training strategies to improve convolutional neural network-based image-to-image 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.


Exploring Intensity Invariance in Deep Neural Networks for Brain Image Registration

Image registration is a widely-used technique in analysing large scale d...

A Meta-Learning Approach for Medical Image Registration

Non-rigid registration is a necessary but challenging task in medical im...

Recurrence With Correlation Network for Medical Image Registration

We present Recurrence with Correlation Network (RWCNet), a medical image...

Performance of Image Registration Tools on High-Resolution 3D Brain Images

Recent progress in tissue clearing has allowed for the imaging of entire...

Recurrent Image Registration using Mutual Attention based Network

Image registration is an important task in medical imaging which estimat...

Deep Image Prior using Stein's Unbiased Risk Estimator: SURE-DIP

Deep learning algorithms that rely on extensive training data are revolu...

Code Repositories


Deep learning powered image to image registration, based on VoxelMorph

view repo