Exponential-Distance Weights for Reducing Grid-like Artifacts in Patch-Based Medical Image Registration

Patch-based medical image registration has been well explored in recent decades. However, the patch fusion process can generate grid-like artifacts along the edge of patches for the following two reasons: firstly, in order to ensure the same size of input and output, zero-padding is used, which caus...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Liang Wu, Shunbo Hu, Changchun Liu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	patch-based registration overlap distance exponential function Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/56b425c8a2fe41db9ecf974c9ba42573
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:56b425c8a2fe41db9ecf974c9ba42573
record_format	dspace
spelling	oai:doaj.org-article:56b425c8a2fe41db9ecf974c9ba425732021-11-11T19:07:12ZExponential-Distance Weights for Reducing Grid-like Artifacts in Patch-Based Medical Image Registration10.3390/s212171121424-8220https://doaj.org/article/56b425c8a2fe41db9ecf974c9ba425732021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7112https://doaj.org/toc/1424-8220Patch-based medical image registration has been well explored in recent decades. However, the patch fusion process can generate grid-like artifacts along the edge of patches for the following two reasons: firstly, in order to ensure the same size of input and output, zero-padding is used, which causes uncertainty in the edges of the output feature map during the feature extraction process; secondly, the sliding window extraction patch with different strides will result in different degrees of grid-like artifacts. In this paper, we propose an exponential-distance-weighted (EDW) method to remove grid-like artifacts. To consider the uncertainty of predictions near patch edges, we used an exponential function to convert the distance from the point in the overlapping regions to the center point of the patch into a weighting coefficient. This gave lower weights to areas near the patch edges, to decrease the uncertainty predictions. Finally, the dense displacement field was obtained by this EDW weighting method. We used the OASIS-3 dataset to evaluate the performance of our method. The experimental results show that the proposed EDW patch fusion method removed grid-like artifacts and improved the dice similarity coefficient superior to those of several state-of-the-art methods. The proposed fusion method can be used together with any patch-based registration model.Liang WuShunbo HuChangchun LiuMDPI AGarticlepatch-basedregistrationoverlapdistanceexponential functionChemical technologyTP1-1185ENSensors, Vol 21, Iss 7112, p 7112 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	patch-based registration overlap distance exponential function Chemical technology TP1-1185
spellingShingle	patch-based registration overlap distance exponential function Chemical technology TP1-1185 Liang Wu Shunbo Hu Changchun Liu Exponential-Distance Weights for Reducing Grid-like Artifacts in Patch-Based Medical Image Registration
description	Patch-based medical image registration has been well explored in recent decades. However, the patch fusion process can generate grid-like artifacts along the edge of patches for the following two reasons: firstly, in order to ensure the same size of input and output, zero-padding is used, which causes uncertainty in the edges of the output feature map during the feature extraction process; secondly, the sliding window extraction patch with different strides will result in different degrees of grid-like artifacts. In this paper, we propose an exponential-distance-weighted (EDW) method to remove grid-like artifacts. To consider the uncertainty of predictions near patch edges, we used an exponential function to convert the distance from the point in the overlapping regions to the center point of the patch into a weighting coefficient. This gave lower weights to areas near the patch edges, to decrease the uncertainty predictions. Finally, the dense displacement field was obtained by this EDW weighting method. We used the OASIS-3 dataset to evaluate the performance of our method. The experimental results show that the proposed EDW patch fusion method removed grid-like artifacts and improved the dice similarity coefficient superior to those of several state-of-the-art methods. The proposed fusion method can be used together with any patch-based registration model.
format	article
author	Liang Wu Shunbo Hu Changchun Liu
author_facet	Liang Wu Shunbo Hu Changchun Liu
author_sort	Liang Wu
title	Exponential-Distance Weights for Reducing Grid-like Artifacts in Patch-Based Medical Image Registration
title_short	Exponential-Distance Weights for Reducing Grid-like Artifacts in Patch-Based Medical Image Registration
title_full	Exponential-Distance Weights for Reducing Grid-like Artifacts in Patch-Based Medical Image Registration
title_fullStr	Exponential-Distance Weights for Reducing Grid-like Artifacts in Patch-Based Medical Image Registration
title_full_unstemmed	Exponential-Distance Weights for Reducing Grid-like Artifacts in Patch-Based Medical Image Registration
title_sort	exponential-distance weights for reducing grid-like artifacts in patch-based medical image registration
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/56b425c8a2fe41db9ecf974c9ba42573
work_keys_str_mv	AT liangwu exponentialdistanceweightsforreducinggridlikeartifactsinpatchbasedmedicalimageregistration AT shunbohu exponentialdistanceweightsforreducinggridlikeartifactsinpatchbasedmedicalimageregistration AT changchunliu exponentialdistanceweightsforreducinggridlikeartifactsinpatchbasedmedicalimageregistration
_version_	1718431585290682368

Exponential-Distance Weights for Reducing Grid-like Artifacts in Patch-Based Medical Image Registration

Ejemplares similares