Deep learning based registration using spatial gradients and noisy segmentation labels

Abstract

Image registration is one of the most challenging problems in medical image analysis. In the recent years, deep learning based approaches became quite popular, providing fast and performing registration strategies. In this short paper, we summarise our work presented on Learn2Reg challenge 2020. The main contributions of our work rely on (i) a symmetric formulation, predicting the transformations from source to target and from target to source simultaneously, enforcing the trained representations to be similar and (ii) integration of variety of publicly available datasets used both for pretraining and for augmenting segmentation labels. Our method reports a mean dice of $0.64$ for task 3 and $0.85$ for task 4 on the test sets, taking third place on the challenge. Our code and models are publicly available at https://github.com/TheoEst/abdominal_registration and \https://github.com/TheoEst/hippocampus_registration.

6 pages, 3 figures. Updated version after review modifications. Published to Segmentation, Classification, and Registration of Multi-modality Medical Imaging Data. MICCAI 2020. Lecture Notes in Computer Science, vol 12587

References in corpus (8)

• A Deep Learning Framework for Unsupervised Affine and Deformable Image Registration
• A large annotated medical image dataset for the development and evaluation of segmentation algorithms
• Deep Learning in Medical Image Registration: A Survey
• Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration
• The KiTS19 Challenge Data: 300 Kidney Tumor Cases with Clinical Context, CT Semantic Segmentations, and Surgical Outcomes
• Learning a Probabilistic Model for Diffeomorphic Registration
• Deep convolutional networks for pancreas segmentation in CT imaging
• Linear and Deformable Image Registration with 3D Convolutional Neural Networks