Deep-learning-based deformable image registration of head CT and MRI scans

Author:

Ratke Alexander,Darsht Elena,Heinzelmann Feline,Kröninger Kevin,Timmermann Beate,Bäumer Christian

Abstract

This work is motivated by the lack of publications on the direct application of multimodal image registration with deep-learning techniques for the enhancement of treatment planning in particle therapy. An unsupervised workflow, which seeks to improve image alignment, was developed and evaluated for computed tomography and magnetic resonance imaging scans of the head. The scans of 39 paediatric patients with brain tumours were available. The focus of the two-step workflow, including preprocessing of the scans for normalisation, is deformable image registration (DIR) with a deep neural network, which generates deformation vector fields (DVFs). To obtain a suitable configuration of the network, parameter tuning is performed by varying its parameters, e.g., layer size, regularisation (λ) of the DVF and learning rate (α). Image similarity was determined with the Dice similarity coefficient, mDSC, using segmented images and the mutual-information metric, mMI. The performance of the deep-learning models was assessed with the inverse consistency, mIC, and the Jacobian determinant, mJD. Inverse consistency is obtained for mIC = 0 mm, while the determinant of a deformed image is expected to be unity. The deep-learning models passed both performance checks, indicated by the mean values m̄IC=(0.57±1.00)mm and m̄JD=(1.00±0.07). Models with λ ≥ 1 yielded higher mDSC values than models with lower λ values. A small-architecture model with α = 10–4 was found to be most suitable for DIR, as improvement in image similarity of up to 12% was obtained in terms of mMI. The direct application of deep-learning models produced registered images improving image alignment between scans of different modalities.

Publisher

Frontiers Media SA

Subject

Physical and Theoretical Chemistry,General Physics and Astronomy,Mathematical Physics,Materials Science (miscellaneous),Biophysics

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3