Learning deep abdominal CT registration through adaptive loss weighting and synthetic data generation
Perez de Frutos, Javier; Pedersen, Andre; Pelanis, Egidijus; Bouget, David Nicolas Jean-Mar; Survarachakan, Shanmugapriya; Langø, Thomas; Elle, Ole Jakob; Lindseth, Frank
Peer reviewed, Journal article
Published version

View/ Open
Date
2023Metadata
Show full item recordCollections
Original version
10.1371/journal.pone.0282110Abstract
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. Learning deep abdominal CT registration through adaptive loss weighting and synthetic data generation