Multi-view convolutional neural networks for automated ocular structure and tumor segmentation in retinoblastoma

Abstract In retinoblastoma, accurate segmentation of ocular structure and tumor tissue is important when working towards personalized treatment. This retrospective study serves to evaluate the performance of multi-view convolutional neural networks (MV-CNNs) for automated eye and tumor segmentation...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Victor I. J. Strijbis, Christiaan M. de Bloeme, Robin W. Jansen, Hamza Kebiri, Huu-Giao Nguyen, Marcus C. de Jong, Annette C. Moll, Merixtell Bach-Cuadra, Pim de Graaf, Martijn D. Steenwijk
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/64b6ff5d7bb04de6a7e9bf1f87dd6bd2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:64b6ff5d7bb04de6a7e9bf1f87dd6bd2
record_format	dspace
spelling	oai:doaj.org-article:64b6ff5d7bb04de6a7e9bf1f87dd6bd22021-12-02T15:33:01ZMulti-view convolutional neural networks for automated ocular structure and tumor segmentation in retinoblastoma10.1038/s41598-021-93905-22045-2322https://doaj.org/article/64b6ff5d7bb04de6a7e9bf1f87dd6bd22021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-93905-2https://doaj.org/toc/2045-2322Abstract In retinoblastoma, accurate segmentation of ocular structure and tumor tissue is important when working towards personalized treatment. This retrospective study serves to evaluate the performance of multi-view convolutional neural networks (MV-CNNs) for automated eye and tumor segmentation on MRI in retinoblastoma patients. Forty retinoblastoma and 20 healthy-eyes from 30 patients were included in a train/test (N = 29 retinoblastoma-, 17 healthy-eyes) and independent validation (N = 11 retinoblastoma-, 3 healthy-eyes) set. Imaging was done using 3.0 T Fast Imaging Employing Steady-state Acquisition (FIESTA), T2-weighted and contrast-enhanced T1-weighted sequences. Sclera, vitreous humour, lens, retinal detachment and tumor were manually delineated on FIESTA images to serve as a reference standard. Volumetric and spatial performance were assessed by calculating intra-class correlation (ICC) and dice similarity coefficient (DSC). Additionally, the effects of multi-scale, sequences and data augmentation were explored. Optimal performance was obtained by using a three-level pyramid MV-CNN with FIESTA, T2 and T1c sequences and data augmentation. Eye and tumor volumetric ICC were 0.997 and 0.996, respectively. Median [Interquartile range] DSC for eye, sclera, vitreous, lens, retinal detachment and tumor were 0.965 [0.950–0.975], 0.847 [0.782–0.893], 0.975 [0.930–0.986], 0.909 [0.847–0.951], 0.828 [0.458–0.962] and 0.914 [0.852–0.958], respectively. MV-CNN can be used to obtain accurate ocular structure and tumor segmentations in retinoblastoma.Victor I. J. StrijbisChristiaan M. de BloemeRobin W. JansenHamza KebiriHuu-Giao NguyenMarcus C. de JongAnnette C. MollMerixtell Bach-CuadraPim de GraafMartijn D. SteenwijkNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Victor I. J. Strijbis Christiaan M. de Bloeme Robin W. Jansen Hamza Kebiri Huu-Giao Nguyen Marcus C. de Jong Annette C. Moll Merixtell Bach-Cuadra Pim de Graaf Martijn D. Steenwijk Multi-view convolutional neural networks for automated ocular structure and tumor segmentation in retinoblastoma
description	Abstract In retinoblastoma, accurate segmentation of ocular structure and tumor tissue is important when working towards personalized treatment. This retrospective study serves to evaluate the performance of multi-view convolutional neural networks (MV-CNNs) for automated eye and tumor segmentation on MRI in retinoblastoma patients. Forty retinoblastoma and 20 healthy-eyes from 30 patients were included in a train/test (N = 29 retinoblastoma-, 17 healthy-eyes) and independent validation (N = 11 retinoblastoma-, 3 healthy-eyes) set. Imaging was done using 3.0 T Fast Imaging Employing Steady-state Acquisition (FIESTA), T2-weighted and contrast-enhanced T1-weighted sequences. Sclera, vitreous humour, lens, retinal detachment and tumor were manually delineated on FIESTA images to serve as a reference standard. Volumetric and spatial performance were assessed by calculating intra-class correlation (ICC) and dice similarity coefficient (DSC). Additionally, the effects of multi-scale, sequences and data augmentation were explored. Optimal performance was obtained by using a three-level pyramid MV-CNN with FIESTA, T2 and T1c sequences and data augmentation. Eye and tumor volumetric ICC were 0.997 and 0.996, respectively. Median [Interquartile range] DSC for eye, sclera, vitreous, lens, retinal detachment and tumor were 0.965 [0.950–0.975], 0.847 [0.782–0.893], 0.975 [0.930–0.986], 0.909 [0.847–0.951], 0.828 [0.458–0.962] and 0.914 [0.852–0.958], respectively. MV-CNN can be used to obtain accurate ocular structure and tumor segmentations in retinoblastoma.
format	article
author	Victor I. J. Strijbis Christiaan M. de Bloeme Robin W. Jansen Hamza Kebiri Huu-Giao Nguyen Marcus C. de Jong Annette C. Moll Merixtell Bach-Cuadra Pim de Graaf Martijn D. Steenwijk
author_facet	Victor I. J. Strijbis Christiaan M. de Bloeme Robin W. Jansen Hamza Kebiri Huu-Giao Nguyen Marcus C. de Jong Annette C. Moll Merixtell Bach-Cuadra Pim de Graaf Martijn D. Steenwijk
author_sort	Victor I. J. Strijbis
title	Multi-view convolutional neural networks for automated ocular structure and tumor segmentation in retinoblastoma
title_short	Multi-view convolutional neural networks for automated ocular structure and tumor segmentation in retinoblastoma
title_full	Multi-view convolutional neural networks for automated ocular structure and tumor segmentation in retinoblastoma
title_fullStr	Multi-view convolutional neural networks for automated ocular structure and tumor segmentation in retinoblastoma
title_full_unstemmed	Multi-view convolutional neural networks for automated ocular structure and tumor segmentation in retinoblastoma
title_sort	multi-view convolutional neural networks for automated ocular structure and tumor segmentation in retinoblastoma
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/64b6ff5d7bb04de6a7e9bf1f87dd6bd2
work_keys_str_mv	AT victorijstrijbis multiviewconvolutionalneuralnetworksforautomatedocularstructureandtumorsegmentationinretinoblastoma AT christiaanmdebloeme multiviewconvolutionalneuralnetworksforautomatedocularstructureandtumorsegmentationinretinoblastoma AT robinwjansen multiviewconvolutionalneuralnetworksforautomatedocularstructureandtumorsegmentationinretinoblastoma AT hamzakebiri multiviewconvolutionalneuralnetworksforautomatedocularstructureandtumorsegmentationinretinoblastoma AT huugiaonguyen multiviewconvolutionalneuralnetworksforautomatedocularstructureandtumorsegmentationinretinoblastoma AT marcuscdejong multiviewconvolutionalneuralnetworksforautomatedocularstructureandtumorsegmentationinretinoblastoma AT annettecmoll multiviewconvolutionalneuralnetworksforautomatedocularstructureandtumorsegmentationinretinoblastoma AT merixtellbachcuadra multiviewconvolutionalneuralnetworksforautomatedocularstructureandtumorsegmentationinretinoblastoma AT pimdegraaf multiviewconvolutionalneuralnetworksforautomatedocularstructureandtumorsegmentationinretinoblastoma AT martijndsteenwijk multiviewconvolutionalneuralnetworksforautomatedocularstructureandtumorsegmentationinretinoblastoma
_version_	1718387144959983616

Multi-view convolutional neural networks for automated ocular structure and tumor segmentation in retinoblastoma

Ejemplares similares