Evaluation of Learning-based Methods for Multimodal Biomedical Image Registration
Multimodal registration of biomedical images, where two or more images are to bemapped into a common coordinate system in order to combine complementaryinformation, is often a highly beneficial yet challenging task. In recent years, the deeplearning renaissance has reactivated the image registration...
Main Author: | |
---|---|
Format: | Others |
Language: | English |
Published: |
Uppsala universitet, Institutionen för informationsteknologi
2020
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-455890 |
id |
ndltd-UPSALLA1-oai-DiVA.org-uu-455890 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-UPSALLA1-oai-DiVA.org-uu-4558902021-10-13T05:36:35ZEvaluation of Learning-based Methods for Multimodal Biomedical Image RegistrationengLu, JiahaoUppsala universitet, Institutionen för informationsteknologi2020Engineering and TechnologyTeknik och teknologierMultimodal registration of biomedical images, where two or more images are to bemapped into a common coordinate system in order to combine complementaryinformation, is often a highly beneficial yet challenging task. In recent years, the deeplearning renaissance has reactivated the image registration field by showing impressiveperformance in various applications. However, there is still a lack of empiricalevaluations of learning-based methods for registration of multimodal biomedical datain the literature. This study aims to reduce this deficiency by evaluating several promising, whilemethodologically different learning-based registration methods on a dataset consistingof multimodal microscopy images. Selected methods include GAN-basedcross-modality mapping combined with feature- or intensity-based registration, andsupervised or unsupervised end-to-end transformation predictions. Classic iterativemutual information (MI) maximisation and a state-of-the-art framework tunedspecifically to the dataset are used as baselines. Both registration quality andprocessing speed are assessed. In our experiments, none of the learning-based methods surpasses MI maximisation inquality. Nevertheless, GANs are demonstrated useful in extending the ability ofmonomodal registration methods towards multimodal tasks. The outstanding speed ofend-to-end transformation prediction methods in both training and inference stagesmotivates their further exploration. Multi-resolution strategy might be a key toimprove both above-mentioned approaches. The empirical evaluations in this thesisprovide an insight into the challenge in multimodal registration of biomedical images.It not only lays a groundwork that can be used by future research as a reference, butalso points out some promising modifications to be studied further. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-455890IT ; 20074application/pdfinfo:eu-repo/semantics/openAccess |
collection |
NDLTD |
language |
English |
format |
Others
|
sources |
NDLTD |
topic |
Engineering and Technology Teknik och teknologier |
spellingShingle |
Engineering and Technology Teknik och teknologier Lu, Jiahao Evaluation of Learning-based Methods for Multimodal Biomedical Image Registration |
description |
Multimodal registration of biomedical images, where two or more images are to bemapped into a common coordinate system in order to combine complementaryinformation, is often a highly beneficial yet challenging task. In recent years, the deeplearning renaissance has reactivated the image registration field by showing impressiveperformance in various applications. However, there is still a lack of empiricalevaluations of learning-based methods for registration of multimodal biomedical datain the literature. This study aims to reduce this deficiency by evaluating several promising, whilemethodologically different learning-based registration methods on a dataset consistingof multimodal microscopy images. Selected methods include GAN-basedcross-modality mapping combined with feature- or intensity-based registration, andsupervised or unsupervised end-to-end transformation predictions. Classic iterativemutual information (MI) maximisation and a state-of-the-art framework tunedspecifically to the dataset are used as baselines. Both registration quality andprocessing speed are assessed. In our experiments, none of the learning-based methods surpasses MI maximisation inquality. Nevertheless, GANs are demonstrated useful in extending the ability ofmonomodal registration methods towards multimodal tasks. The outstanding speed ofend-to-end transformation prediction methods in both training and inference stagesmotivates their further exploration. Multi-resolution strategy might be a key toimprove both above-mentioned approaches. The empirical evaluations in this thesisprovide an insight into the challenge in multimodal registration of biomedical images.It not only lays a groundwork that can be used by future research as a reference, butalso points out some promising modifications to be studied further. |
author |
Lu, Jiahao |
author_facet |
Lu, Jiahao |
author_sort |
Lu, Jiahao |
title |
Evaluation of Learning-based Methods for Multimodal Biomedical Image Registration |
title_short |
Evaluation of Learning-based Methods for Multimodal Biomedical Image Registration |
title_full |
Evaluation of Learning-based Methods for Multimodal Biomedical Image Registration |
title_fullStr |
Evaluation of Learning-based Methods for Multimodal Biomedical Image Registration |
title_full_unstemmed |
Evaluation of Learning-based Methods for Multimodal Biomedical Image Registration |
title_sort |
evaluation of learning-based methods for multimodal biomedical image registration |
publisher |
Uppsala universitet, Institutionen för informationsteknologi |
publishDate |
2020 |
url |
http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-455890 |
work_keys_str_mv |
AT lujiahao evaluationoflearningbasedmethodsformultimodalbiomedicalimageregistration |
_version_ |
1719489618177425408 |