Cargando…

Automatic Meningioma Segmentation and Grading Prediction: A Hybrid Deep-Learning Method

The purpose of this study was to determine whether a deep-learning-based assessment system could facilitate preoperative grading of meningioma. This was a retrospective study conducted at two institutions covering 643 patients. The system, designed with a cascade network structure, was developed usi...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Chaoyue, Cheng, Yisong, Xu, Jianfeng, Zhang, Ting, Shu, Xin, Huang, Wei, Hua, Yu, Zhang, Yang, Teng, Yuen, Zhang, Lei, Xu, Jianguo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8401675/
https://www.ncbi.nlm.nih.gov/pubmed/34442431
http://dx.doi.org/10.3390/jpm11080786
_version_ 1783745607530184704
author Chen, Chaoyue
Cheng, Yisong
Xu, Jianfeng
Zhang, Ting
Shu, Xin
Huang, Wei
Hua, Yu
Zhang, Yang
Teng, Yuen
Zhang, Lei
Xu, Jianguo
author_facet Chen, Chaoyue
Cheng, Yisong
Xu, Jianfeng
Zhang, Ting
Shu, Xin
Huang, Wei
Hua, Yu
Zhang, Yang
Teng, Yuen
Zhang, Lei
Xu, Jianguo
author_sort Chen, Chaoyue
collection PubMed
description The purpose of this study was to determine whether a deep-learning-based assessment system could facilitate preoperative grading of meningioma. This was a retrospective study conducted at two institutions covering 643 patients. The system, designed with a cascade network structure, was developed using deep-learning technology for automatic tumor detection, visual assessment, and grading prediction. Specifically, a modified U-Net convolutional neural network was first established to segment tumor images. Subsequently, the segmentations were introduced into rendering algorithms for spatial reconstruction and another DenseNet convolutional neural network for grading prediction. The trained models were integrated as a system, and the robustness was tested based on its performance on an external dataset from the second institution involving different magnetic resonance imaging platforms. The results showed that the segment model represented a noteworthy performance with dice coefficients of 0.920 ± 0.009 in the validation group. With accurate segmented tumor images, the rendering model delicately reconstructed the tumor body and clearly displayed the important intracranial vessels. The DenseNet model also achieved high accuracy with an area under the curve of 0.918 ± 0.006 and accuracy of 0.901 ± 0.039 when classifying tumors into low-grade and high-grade meningiomas. Moreover, the system exhibited good performance on the external validation dataset.
format Online
Article
Text
id pubmed-8401675
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-84016752021-08-29 Automatic Meningioma Segmentation and Grading Prediction: A Hybrid Deep-Learning Method Chen, Chaoyue Cheng, Yisong Xu, Jianfeng Zhang, Ting Shu, Xin Huang, Wei Hua, Yu Zhang, Yang Teng, Yuen Zhang, Lei Xu, Jianguo J Pers Med Article The purpose of this study was to determine whether a deep-learning-based assessment system could facilitate preoperative grading of meningioma. This was a retrospective study conducted at two institutions covering 643 patients. The system, designed with a cascade network structure, was developed using deep-learning technology for automatic tumor detection, visual assessment, and grading prediction. Specifically, a modified U-Net convolutional neural network was first established to segment tumor images. Subsequently, the segmentations were introduced into rendering algorithms for spatial reconstruction and another DenseNet convolutional neural network for grading prediction. The trained models were integrated as a system, and the robustness was tested based on its performance on an external dataset from the second institution involving different magnetic resonance imaging platforms. The results showed that the segment model represented a noteworthy performance with dice coefficients of 0.920 ± 0.009 in the validation group. With accurate segmented tumor images, the rendering model delicately reconstructed the tumor body and clearly displayed the important intracranial vessels. The DenseNet model also achieved high accuracy with an area under the curve of 0.918 ± 0.006 and accuracy of 0.901 ± 0.039 when classifying tumors into low-grade and high-grade meningiomas. Moreover, the system exhibited good performance on the external validation dataset. MDPI 2021-08-12 /pmc/articles/PMC8401675/ /pubmed/34442431 http://dx.doi.org/10.3390/jpm11080786 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Chen, Chaoyue
Cheng, Yisong
Xu, Jianfeng
Zhang, Ting
Shu, Xin
Huang, Wei
Hua, Yu
Zhang, Yang
Teng, Yuen
Zhang, Lei
Xu, Jianguo
Automatic Meningioma Segmentation and Grading Prediction: A Hybrid Deep-Learning Method
title Automatic Meningioma Segmentation and Grading Prediction: A Hybrid Deep-Learning Method
title_full Automatic Meningioma Segmentation and Grading Prediction: A Hybrid Deep-Learning Method
title_fullStr Automatic Meningioma Segmentation and Grading Prediction: A Hybrid Deep-Learning Method
title_full_unstemmed Automatic Meningioma Segmentation and Grading Prediction: A Hybrid Deep-Learning Method
title_short Automatic Meningioma Segmentation and Grading Prediction: A Hybrid Deep-Learning Method
title_sort automatic meningioma segmentation and grading prediction: a hybrid deep-learning method
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8401675/
https://www.ncbi.nlm.nih.gov/pubmed/34442431
http://dx.doi.org/10.3390/jpm11080786
work_keys_str_mv AT chenchaoyue automaticmeningiomasegmentationandgradingpredictionahybriddeeplearningmethod
AT chengyisong automaticmeningiomasegmentationandgradingpredictionahybriddeeplearningmethod
AT xujianfeng automaticmeningiomasegmentationandgradingpredictionahybriddeeplearningmethod
AT zhangting automaticmeningiomasegmentationandgradingpredictionahybriddeeplearningmethod
AT shuxin automaticmeningiomasegmentationandgradingpredictionahybriddeeplearningmethod
AT huangwei automaticmeningiomasegmentationandgradingpredictionahybriddeeplearningmethod
AT huayu automaticmeningiomasegmentationandgradingpredictionahybriddeeplearningmethod
AT zhangyang automaticmeningiomasegmentationandgradingpredictionahybriddeeplearningmethod
AT tengyuen automaticmeningiomasegmentationandgradingpredictionahybriddeeplearningmethod
AT zhanglei automaticmeningiomasegmentationandgradingpredictionahybriddeeplearningmethod
AT xujianguo automaticmeningiomasegmentationandgradingpredictionahybriddeeplearningmethod