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

ABSTRACT:

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 perfo

SUBMITTER: Perez de Frutos J 

PROVIDER: S-EPMC9956065 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature