Anatomy-specific acquisition-agnostic affine registration learned from fictitious images

Malte Hoffmann; Andrew Hoopes; Bruce Fischl; Adrian V. Dalca

doi:10.1117/12.2653251

3 April 2023 Anatomy-specific acquisition-agnostic affine registration learned from fictitious images

Malte Hoffmann, Andrew Hoopes, Bruce Fischl, Adrian V. Dalca

Proceedings Volume 12464, Medical Imaging 2023: Image Processing; 1246402 (2023) https://doi.org/10.1117/12.2653251
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Abstract

Affine image registration is a cornerstone of medical image processing backed by decades of development. While classical algorithms can achieve excellent accuracy, they solve a time-consuming optimization for every new image pair. In contrast, deep-learning (DL) methods learn a function that maps an image pair to an output transform. Evaluating the function is fast, but these methods tend to be susceptible to domain shift. A network trained on a specific image type may perform poorly if an image characteristic changes at test time, such as the imaging contrast or resolution. Secondly, many classical and DL registration algorithms cannot distinguish between relevant and irrelevant anatomy: the global nature of the linear registration problem means that accuracy will suffer if parts of the image deform independently. This is why neuroimage processing, for example, often starts with brain extraction, to enhance the accuracy of brain-specific registration. We address these shortcomings of linear registration by training deep neural networks using a generative strategy that synthesizes wildly varying images from label maps. Optimizing label overlap decouples the loss from the image appearance, encouraging network invariance to acquisition specifics. It also enables the registration model to distinguish between anatomy of interest and irrelevant structures, which alleviates the need for segmenting images prior to registration to remove distracting content. We test brain-specific registration across a variety of magnetic resonance imaging protocols that approximate the diversity of real-world data, demonstrating consistent and improved accuracy relative to state-of-the-art baselines. We freely distribute our easy-to-use tool at https://w3id.org/synthmorph.

Conference Presentation

Citation Download Citation

Malte Hoffmann, Andrew Hoopes, Bruce Fischl, and Adrian V. Dalca "Anatomy-specific acquisition-agnostic affine registration learned from fictitious images", Proc. SPIE 12464, Medical Imaging 2023: Image Processing, 1246402 (3 April 2023); https://doi.org/10.1117/12.2653251

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available