.png){kind=icon}
.png){kind=icon}
Return
Meta-Learning Initializations for Interactive Medical Image Registration
.png){kind=icon}
OA
AI
DOI：10.1109/TMI.2022.3218147.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We present a meta-learning framework for interactive medical image registration. Our proposed framework comprises three components: a learning-based medical image registration algorithm, a form of user interaction that refines registration at inference, and a meta-learning protocol that learns a rapidly adaptable network initialization. This paper describes a specific algorithm that implements the registration, interaction and meta-learning protocol for our exemplar clinical application: registration of magnetic resonance (MR) imaging to interactively acquired, sparsely-sampled transrectal ultrasound (TRUS) images. Our approach obtains comparable registration error (4.26 mm) to the best-performing non-interactive learning-based 3D-to-3D method (3.97 mm) while requiring only a fraction of the data, and occurring in real-time during acquisition. Applying sparsely sampled data to non-interactive methods yields higher registration errors (6.26 mm), demonstrating the effectiveness of interactive MR-TRUS registration, which may be applied intraoperatively given the real-time nature of the adaptation process.
Keywords:
Image registration
Biomedical imaging
Training
Annotations
Image segmentation
Ultrasonic imaging
Task analysis
Medical image registration
meta-learning
interactive machine learning
prostate cancer
Journal
IF:
9.8
Papers:
6.2K
Citations:
3.7W