Faster dense deformable image registration by utilizing both CPU and GPU

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Search: WFRF:(Ahlström Håkan) > (2020-2021) > Faster dense deform...

Details
MARC

Ekström, Simon,1991-Uppsala universitet,Radiologi,Antaros Medical AB (Sweden) (author)

Faster dense deformable image registration by utilizing both CPU and GPU

Article/chapterEnglish2021

Publisher, publication year, extent ...

2021
electronicrdacarrier

Numbers

LIBRIS-ID:oai:DiVA.org:uu-437222
https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-437222URI
https://doi.org/10.1117/1.JMI.8.1.014002DOI

Supplementary language notes

Language:English
Summary in:English

Part of subdatabase

SwePubSwePub

Classification

Subject category:ref swepub-contenttype
Subject category:art swepub-publicationtype

Notes

Purpose: Image registration is an important aspect of medical image analysis and a key component in many analysis concepts. Applications include fusion of multimodal images, multi-atlas segmentation, and whole-body analysis. Deformable image registration is often computationally expensive, and the need for efficient registration methods is highlighted by the emergence of large-scale image databases, e.g., the UK Biobank, providing imaging from 100,000 participants. Approach: We present a heterogeneous computing approach, utilizing both the CPU and the graphics processing unit (GPU), to accelerate a previously proposed image registration method. The parallelizable task of computing the matching criterion is offloaded to the GPU, where it can be computed efficiently, while the more complex optimization task is performed on the CPU. To lessen the impact of data synchronization between the CPU and GPU, we propose a pipeline model, effectively overlapping computational tasks with data synchronization. The performance is evaluated on a brain labeling task and compared with a CPU implementation of the same method and the popular advanced normalization tools (ANTs) software. Results: The proposed method presents a speed-up by factors of 4 and 8 against the CPU implementation and the ANTs software, respectively. A significant improvement in labeling quality was also observed, with measured mean Dice overlaps of 0.712 and 0.701 for our method and ANTs, respectively. Conclusions: We showed that the proposed method compares favorably to the ANTs software yielding both a significant speed-up and an improvement in labeling quality. The registration method together with the proposed parallelization strategy is implemented as an open-source software package, deform.

Subject headings and genre

TEKNIK OCH TEKNOLOGIER Medicinteknik Medicinsk bildbehandling hsv//swe
ENGINEERING AND TECHNOLOGY Medical Engineering Medical Image Processing hsv//eng
Atlas-based segmentation
brain MRI
deformable image registration
graphics processing unit

Added entries (persons, corporate bodies, meetings, titles ...)

Pilia, MartinoUppsala universitet,Radiologi (author)
Kullberg, Joel,1979-Uppsala universitet,Radiologi,Antaros Medical AB (Sweden)(Swepub:uu)jokul377 (author)
Ahlström, Håkan,1953-Uppsala universitet,Radiologi,Antaros Medical AB (Sweden)(Swepub:uu)hakanahl (author)
Strand, Robin,1978-Uppsala universitet,Radiologi,Institutionen för informationsteknologi(Swepub:uu)rostr275 (author)
Malmberg, Filip,1980-Uppsala universitet,Radiologi(Swepub:uu)filma606 (author)
Uppsala universitetRadiologi (creator_code:org_t)

Related titles

In:Journal of Medical Imaging8:12329-43022329-4310

Internet link

Find in a library

Journal of Medical Imaging (Search for host publication in LIBRIS)

To the university's database

Find more in SwePub

By the author/editor: Ekström, Simon, ...; Pilia, Martino; Kullberg, Joel, ...; Ahlström, Håkan, ...; Strand, Robin, 1 ...; Malmberg, Filip, ...

About the subject

ENGINEERING AND TECHNOLOGY: ENGINEERING AND ...; and Medical Engineer ...; and Medical Image Pr ...

Articles in the publication: Journal of Medic ...

By the university: Uppsala University

Search outside SwePub

Extend your search to:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se