General Purpose Image Encoder DINOv2 for Medical Image Registration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Song, Xinrui, Xu, Xuanang, Yan, Pingkun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929256261484544
author Song, Xinrui
Xu, Xuanang
Yan, Pingkun
author_facet Song, Xinrui
Xu, Xuanang
Yan, Pingkun
contents Existing medical image registration algorithms rely on either dataset specific training or local texture-based features to align images. The former cannot be reliably implemented without large modality-specific training datasets, while the latter lacks global semantics thus could be easily trapped at local minima. In this paper, we present a training-free deformable image registration method, DINO-Reg, leveraging a general purpose image encoder DINOv2 for image feature extraction. The DINOv2 encoder was trained using the ImageNet data containing natural images. We used the pretrained DINOv2 without any finetuning. Our method feeds the DINOv2 encoded features into a discrete optimizer to find the optimal deformable registration field. We conducted a series of experiments to understand the behavior and role of such a general purpose image encoder in the application of image registration. Combined with handcrafted features, our method won the first place in the recent OncoReg Challenge. To our knowledge, this is the first application of general vision foundation models in medical image registration.
format Preprint
id arxiv_https___arxiv_org_abs_2402_15687
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle General Purpose Image Encoder DINOv2 for Medical Image Registration
Song, Xinrui
Xu, Xuanang
Yan, Pingkun
Computer Vision and Pattern Recognition
Artificial Intelligence
Existing medical image registration algorithms rely on either dataset specific training or local texture-based features to align images. The former cannot be reliably implemented without large modality-specific training datasets, while the latter lacks global semantics thus could be easily trapped at local minima. In this paper, we present a training-free deformable image registration method, DINO-Reg, leveraging a general purpose image encoder DINOv2 for image feature extraction. The DINOv2 encoder was trained using the ImageNet data containing natural images. We used the pretrained DINOv2 without any finetuning. Our method feeds the DINOv2 encoded features into a discrete optimizer to find the optimal deformable registration field. We conducted a series of experiments to understand the behavior and role of such a general purpose image encoder in the application of image registration. Combined with handcrafted features, our method won the first place in the recent OncoReg Challenge. To our knowledge, this is the first application of general vision foundation models in medical image registration.
title General Purpose Image Encoder DINOv2 for Medical Image Registration
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2402.15687