Automatic vertebrae localization and segmentation in CT with a two-stage Dense-U-Net

Abstract Automatic vertebrae localization and segmentation in computed tomography (CT) are fundamental for spinal image analysis and spine surgery with computer-assisted surgery systems. But they remain challenging due to high variation in spinal anatomy among patients. In this paper, we proposed a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Pengfei Cheng, Yusheng Yang, Huiqiang Yu, Yongyi He
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/53177cabd4274d82a20674d5c723e44c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:53177cabd4274d82a20674d5c723e44c
record_format	dspace
spelling	oai:doaj.org-article:53177cabd4274d82a20674d5c723e44c2021-11-14T12:20:19ZAutomatic vertebrae localization and segmentation in CT with a two-stage Dense-U-Net10.1038/s41598-021-01296-12045-2322https://doaj.org/article/53177cabd4274d82a20674d5c723e44c2021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-01296-1https://doaj.org/toc/2045-2322Abstract Automatic vertebrae localization and segmentation in computed tomography (CT) are fundamental for spinal image analysis and spine surgery with computer-assisted surgery systems. But they remain challenging due to high variation in spinal anatomy among patients. In this paper, we proposed a deep-learning approach for automatic CT vertebrae localization and segmentation with a two-stage Dense-U-Net. The first stage used a 2D-Dense-U-Net to localize vertebrae by detecting the vertebrae centroids with dense labels and 2D slices. The second stage segmented the specific vertebra within a region-of-interest identified based on the centroid using 3D-Dense-U-Net. Finally, each segmented vertebra was merged into a complete spine and resampled to original resolution. We evaluated our method on the dataset from the CSI 2014 Workshop with 6 metrics: location error (1.69 ± 0.78 mm), detection rate (100%) for vertebrae localization; the dice coefficient (0.953 ± 0.014), intersection over union (0.911 ± 0.025), Hausdorff distance (4.013 ± 2.128 mm), pixel accuracy (0.998 ± 0.001) for vertebrae segmentation. The experimental results demonstrated the efficiency of the proposed method. Furthermore, evaluation on the dataset from the xVertSeg challenge with location error (4.12 ± 2.31), detection rate (100%), dice coefficient (0.877 ± 0.035) shows the generalizability of our method. In summary, our solution localized the vertebrae successfully by detecting the centroids of vertebrae and implemented instance segmentation of vertebrae in the whole spine.Pengfei ChengYusheng YangHuiqiang YuYongyi HeNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Pengfei Cheng Yusheng Yang Huiqiang Yu Yongyi He Automatic vertebrae localization and segmentation in CT with a two-stage Dense-U-Net
description	Abstract Automatic vertebrae localization and segmentation in computed tomography (CT) are fundamental for spinal image analysis and spine surgery with computer-assisted surgery systems. But they remain challenging due to high variation in spinal anatomy among patients. In this paper, we proposed a deep-learning approach for automatic CT vertebrae localization and segmentation with a two-stage Dense-U-Net. The first stage used a 2D-Dense-U-Net to localize vertebrae by detecting the vertebrae centroids with dense labels and 2D slices. The second stage segmented the specific vertebra within a region-of-interest identified based on the centroid using 3D-Dense-U-Net. Finally, each segmented vertebra was merged into a complete spine and resampled to original resolution. We evaluated our method on the dataset from the CSI 2014 Workshop with 6 metrics: location error (1.69 ± 0.78 mm), detection rate (100%) for vertebrae localization; the dice coefficient (0.953 ± 0.014), intersection over union (0.911 ± 0.025), Hausdorff distance (4.013 ± 2.128 mm), pixel accuracy (0.998 ± 0.001) for vertebrae segmentation. The experimental results demonstrated the efficiency of the proposed method. Furthermore, evaluation on the dataset from the xVertSeg challenge with location error (4.12 ± 2.31), detection rate (100%), dice coefficient (0.877 ± 0.035) shows the generalizability of our method. In summary, our solution localized the vertebrae successfully by detecting the centroids of vertebrae and implemented instance segmentation of vertebrae in the whole spine.
format	article
author	Pengfei Cheng Yusheng Yang Huiqiang Yu Yongyi He
author_facet	Pengfei Cheng Yusheng Yang Huiqiang Yu Yongyi He
author_sort	Pengfei Cheng
title	Automatic vertebrae localization and segmentation in CT with a two-stage Dense-U-Net
title_short	Automatic vertebrae localization and segmentation in CT with a two-stage Dense-U-Net
title_full	Automatic vertebrae localization and segmentation in CT with a two-stage Dense-U-Net
title_fullStr	Automatic vertebrae localization and segmentation in CT with a two-stage Dense-U-Net
title_full_unstemmed	Automatic vertebrae localization and segmentation in CT with a two-stage Dense-U-Net
title_sort	automatic vertebrae localization and segmentation in ct with a two-stage dense-u-net
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/53177cabd4274d82a20674d5c723e44c
work_keys_str_mv	AT pengfeicheng automaticvertebraelocalizationandsegmentationinctwithatwostagedenseunet AT yushengyang automaticvertebraelocalizationandsegmentationinctwithatwostagedenseunet AT huiqiangyu automaticvertebraelocalizationandsegmentationinctwithatwostagedenseunet AT yongyihe automaticvertebraelocalizationandsegmentationinctwithatwostagedenseunet
_version_	1718429286747078656

Automatic vertebrae localization and segmentation in CT with a two-stage Dense-U-Net

Ejemplares similares