3D brain tumor segmentation using a two-stage optimal mass transport algorithm

Abstract Optimal mass transport (OMT) theory, the goal of which is to move any irregular 3D object (i.e., the brain) without causing significant distortion, is used to preprocess brain tumor datasets for the first time in this paper. The first stage of a two-stage OMT (TSOMT) procedure transforms th...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wen-Wei Lin, Cheng Juang, Mei-Heng Yueh, Tsung-Ming Huang, Tiexiang Li, Sheng Wang, Shing-Tung Yau
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/a87e7ba877574d96b7c8a879d68a9c85
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a87e7ba877574d96b7c8a879d68a9c85
record_format	dspace
spelling	oai:doaj.org-article:a87e7ba877574d96b7c8a879d68a9c852021-12-02T15:07:55Z3D brain tumor segmentation using a two-stage optimal mass transport algorithm10.1038/s41598-021-94071-12045-2322https://doaj.org/article/a87e7ba877574d96b7c8a879d68a9c852021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-94071-1https://doaj.org/toc/2045-2322Abstract Optimal mass transport (OMT) theory, the goal of which is to move any irregular 3D object (i.e., the brain) without causing significant distortion, is used to preprocess brain tumor datasets for the first time in this paper. The first stage of a two-stage OMT (TSOMT) procedure transforms the brain into a unit solid ball. The second stage transforms the unit ball into a cube, as it is easier to apply a 3D convolutional neural network to rectangular coordinates. Small variations in the local mass-measure stretch ratio among all the brain tumor datasets confirm the robustness of the transform. Additionally, the distortion is kept at a minimum with a reasonable transport cost. The original $$240 \times 240 \times 155 \times 4$$ 240 × 240 × 155 × 4 dataset is thus reduced to a cube of $$128 \times 128 \times 128 \times 4$$ 128 × 128 × 128 × 4 , which is a 76.6% reduction in the total number of voxels, without losing much detail. Three typical U-Nets are trained separately to predict the whole tumor (WT), tumor core (TC), and enhanced tumor (ET) from the cube. An impressive training accuracy of 0.9822 in the WT cube is achieved at 400 epochs. An inverse TSOMT method is applied to the predicted cube to obtain the brain results. The conversion loss from the TSOMT method to the inverse TSOMT method is found to be less than one percent. For training, good Dice scores (0.9781 for the WT, 0.9637 for the TC, and 0.9305 for the ET) can be obtained. Significant improvements in brain tumor detection and the segmentation accuracy are achieved. For testing, postprocessing (rotation) is added to the TSOMT, U-Net prediction, and inverse TSOMT methods for an accuracy improvement of one to two percent. It takes 200 seconds to complete the whole segmentation process on each new brain tumor dataset.Wen-Wei LinCheng JuangMei-Heng YuehTsung-Ming HuangTiexiang LiSheng WangShing-Tung YauNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-19 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Wen-Wei Lin Cheng Juang Mei-Heng Yueh Tsung-Ming Huang Tiexiang Li Sheng Wang Shing-Tung Yau 3D brain tumor segmentation using a two-stage optimal mass transport algorithm
description	Abstract Optimal mass transport (OMT) theory, the goal of which is to move any irregular 3D object (i.e., the brain) without causing significant distortion, is used to preprocess brain tumor datasets for the first time in this paper. The first stage of a two-stage OMT (TSOMT) procedure transforms the brain into a unit solid ball. The second stage transforms the unit ball into a cube, as it is easier to apply a 3D convolutional neural network to rectangular coordinates. Small variations in the local mass-measure stretch ratio among all the brain tumor datasets confirm the robustness of the transform. Additionally, the distortion is kept at a minimum with a reasonable transport cost. The original $$240 \times 240 \times 155 \times 4$$ 240 × 240 × 155 × 4 dataset is thus reduced to a cube of $$128 \times 128 \times 128 \times 4$$ 128 × 128 × 128 × 4 , which is a 76.6% reduction in the total number of voxels, without losing much detail. Three typical U-Nets are trained separately to predict the whole tumor (WT), tumor core (TC), and enhanced tumor (ET) from the cube. An impressive training accuracy of 0.9822 in the WT cube is achieved at 400 epochs. An inverse TSOMT method is applied to the predicted cube to obtain the brain results. The conversion loss from the TSOMT method to the inverse TSOMT method is found to be less than one percent. For training, good Dice scores (0.9781 for the WT, 0.9637 for the TC, and 0.9305 for the ET) can be obtained. Significant improvements in brain tumor detection and the segmentation accuracy are achieved. For testing, postprocessing (rotation) is added to the TSOMT, U-Net prediction, and inverse TSOMT methods for an accuracy improvement of one to two percent. It takes 200 seconds to complete the whole segmentation process on each new brain tumor dataset.
format	article
author	Wen-Wei Lin Cheng Juang Mei-Heng Yueh Tsung-Ming Huang Tiexiang Li Sheng Wang Shing-Tung Yau
author_facet	Wen-Wei Lin Cheng Juang Mei-Heng Yueh Tsung-Ming Huang Tiexiang Li Sheng Wang Shing-Tung Yau
author_sort	Wen-Wei Lin
title	3D brain tumor segmentation using a two-stage optimal mass transport algorithm
title_short	3D brain tumor segmentation using a two-stage optimal mass transport algorithm
title_full	3D brain tumor segmentation using a two-stage optimal mass transport algorithm
title_fullStr	3D brain tumor segmentation using a two-stage optimal mass transport algorithm
title_full_unstemmed	3D brain tumor segmentation using a two-stage optimal mass transport algorithm
title_sort	3d brain tumor segmentation using a two-stage optimal mass transport algorithm
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/a87e7ba877574d96b7c8a879d68a9c85
work_keys_str_mv	AT wenweilin 3dbraintumorsegmentationusingatwostageoptimalmasstransportalgorithm AT chengjuang 3dbraintumorsegmentationusingatwostageoptimalmasstransportalgorithm AT meihengyueh 3dbraintumorsegmentationusingatwostageoptimalmasstransportalgorithm AT tsungminghuang 3dbraintumorsegmentationusingatwostageoptimalmasstransportalgorithm AT tiexiangli 3dbraintumorsegmentationusingatwostageoptimalmasstransportalgorithm AT shengwang 3dbraintumorsegmentationusingatwostageoptimalmasstransportalgorithm AT shingtungyau 3dbraintumorsegmentationusingatwostageoptimalmasstransportalgorithm
_version_	1718388337951113216

3D brain tumor segmentation using a two-stage optimal mass transport algorithm

Ejemplares similares