Accurate pancreas segmentation using multi-level pyramidal pooling residual U-Net with adversarial mechanism

Abstract Background A novel multi-level pyramidal pooling residual U-Net with adversarial mechanism was proposed for organ segmentation from medical imaging, and was conducted on the challenging NIH Pancreas-CT dataset. Methods The 82 pancreatic contrast-enhanced abdominal CT volumes were split via...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Meiyu Li, Fenghui Lian, Chunyu Wang, Shuxu Guo
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Residual learning Multi-level pyramidal pooling module Adversarial mechanism Pancreas segmentation Medical technology R855-855.5
Acceso en línea:	https://doaj.org/article/6172d803667641d1ac167f3267bc6747
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6172d803667641d1ac167f3267bc6747
record_format	dspace
spelling	oai:doaj.org-article:6172d803667641d1ac167f3267bc67472021-11-14T12:33:36ZAccurate pancreas segmentation using multi-level pyramidal pooling residual U-Net with adversarial mechanism10.1186/s12880-021-00694-11471-2342https://doaj.org/article/6172d803667641d1ac167f3267bc67472021-11-01T00:00:00Zhttps://doi.org/10.1186/s12880-021-00694-1https://doaj.org/toc/1471-2342Abstract Background A novel multi-level pyramidal pooling residual U-Net with adversarial mechanism was proposed for organ segmentation from medical imaging, and was conducted on the challenging NIH Pancreas-CT dataset. Methods The 82 pancreatic contrast-enhanced abdominal CT volumes were split via four-fold cross validation to test the model performance. In order to achieve accurate segmentation, we firstly involved residual learning into an adversarial U-Net to achieve a better gradient information flow for improving segmentation performance. Then, we introduced a multi-level pyramidal pooling module (MLPP), where a novel pyramidal pooling was involved to gather contextual information for segmentation, then four groups of structures consisted of a different number of pyramidal pooling blocks were proposed to search for the structure with the optimal performance, and two types of pooling blocks were applied in the experimental section to further assess the robustness of MLPP for pancreas segmentation. For evaluation, Dice similarity coefficient (DSC) and recall were used as the metrics in this work. Results The proposed method preceded the baseline network 5.30% and 6.16% on metrics DSC and recall, and achieved competitive results compared with the-state-of-art methods. Conclusions Our algorithm showed great segmentation performance even on the particularly challenging pancreas dataset, this indicates that the proposed model is a satisfactory and promising segmentor.Meiyu LiFenghui LianChunyu WangShuxu GuoBMCarticleResidual learningMulti-level pyramidal pooling moduleAdversarial mechanismPancreas segmentationMedical technologyR855-855.5ENBMC Medical Imaging, Vol 21, Iss 1, Pp 1-8 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Residual learning Multi-level pyramidal pooling module Adversarial mechanism Pancreas segmentation Medical technology R855-855.5
spellingShingle	Residual learning Multi-level pyramidal pooling module Adversarial mechanism Pancreas segmentation Medical technology R855-855.5 Meiyu Li Fenghui Lian Chunyu Wang Shuxu Guo Accurate pancreas segmentation using multi-level pyramidal pooling residual U-Net with adversarial mechanism
description	Abstract Background A novel multi-level pyramidal pooling residual U-Net with adversarial mechanism was proposed for organ segmentation from medical imaging, and was conducted on the challenging NIH Pancreas-CT dataset. Methods The 82 pancreatic contrast-enhanced abdominal CT volumes were split via four-fold cross validation to test the model performance. In order to achieve accurate segmentation, we firstly involved residual learning into an adversarial U-Net to achieve a better gradient information flow for improving segmentation performance. Then, we introduced a multi-level pyramidal pooling module (MLPP), where a novel pyramidal pooling was involved to gather contextual information for segmentation, then four groups of structures consisted of a different number of pyramidal pooling blocks were proposed to search for the structure with the optimal performance, and two types of pooling blocks were applied in the experimental section to further assess the robustness of MLPP for pancreas segmentation. For evaluation, Dice similarity coefficient (DSC) and recall were used as the metrics in this work. Results The proposed method preceded the baseline network 5.30% and 6.16% on metrics DSC and recall, and achieved competitive results compared with the-state-of-art methods. Conclusions Our algorithm showed great segmentation performance even on the particularly challenging pancreas dataset, this indicates that the proposed model is a satisfactory and promising segmentor.
format	article
author	Meiyu Li Fenghui Lian Chunyu Wang Shuxu Guo
author_facet	Meiyu Li Fenghui Lian Chunyu Wang Shuxu Guo
author_sort	Meiyu Li
title	Accurate pancreas segmentation using multi-level pyramidal pooling residual U-Net with adversarial mechanism
title_short	Accurate pancreas segmentation using multi-level pyramidal pooling residual U-Net with adversarial mechanism
title_full	Accurate pancreas segmentation using multi-level pyramidal pooling residual U-Net with adversarial mechanism
title_fullStr	Accurate pancreas segmentation using multi-level pyramidal pooling residual U-Net with adversarial mechanism
title_full_unstemmed	Accurate pancreas segmentation using multi-level pyramidal pooling residual U-Net with adversarial mechanism
title_sort	accurate pancreas segmentation using multi-level pyramidal pooling residual u-net with adversarial mechanism
publisher	BMC
publishDate	2021
url	https://doaj.org/article/6172d803667641d1ac167f3267bc6747
work_keys_str_mv	AT meiyuli accuratepancreassegmentationusingmultilevelpyramidalpoolingresidualunetwithadversarialmechanism AT fenghuilian accuratepancreassegmentationusingmultilevelpyramidalpoolingresidualunetwithadversarialmechanism AT chunyuwang accuratepancreassegmentationusingmultilevelpyramidalpoolingresidualunetwithadversarialmechanism AT shuxuguo accuratepancreassegmentationusingmultilevelpyramidalpoolingresidualunetwithadversarialmechanism
_version_	1718429170437980160

Accurate pancreas segmentation using multi-level pyramidal pooling residual U-Net with adversarial mechanism

Ejemplares similares