Cargando…

Development of a deep learning model for classifying thymoma as Masaoka-Koga stage I or II via preoperative CT images

BACKGROUND: Accurate thymoma staging via computed tomography (CT) images is difficult even for experienced thoracic doctors. Here we developed a preoperative staging tool differentiating Masaoka-Koga (MK) stage I patients from stage II patients using CT images. METHODS: CT images of 174 thymoma pati...

Descripción completa

Detalles Bibliográficos
Autores principales: Yang, Lei, Cai, Wenjia, Yang, Xiaoyu, Zhu, Haoshuai, Liu, Zhenguo, Wu, Xi, Lei, Yiyan, Zou, Jianyong, Zeng, Bo, Tian, Xi, Zhang, Rongguo, Luo, Honghe, Zhu, Ying
Formato: Online Artículo Texto
Lenguaje:English
Publicado: AME Publishing Company 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7186715/
https://www.ncbi.nlm.nih.gov/pubmed/32355731
http://dx.doi.org/10.21037/atm.2020.02.183
_version_ 1783527012297605120
author Yang, Lei
Cai, Wenjia
Yang, Xiaoyu
Zhu, Haoshuai
Liu, Zhenguo
Wu, Xi
Lei, Yiyan
Zou, Jianyong
Zeng, Bo
Tian, Xi
Zhang, Rongguo
Luo, Honghe
Zhu, Ying
author_facet Yang, Lei
Cai, Wenjia
Yang, Xiaoyu
Zhu, Haoshuai
Liu, Zhenguo
Wu, Xi
Lei, Yiyan
Zou, Jianyong
Zeng, Bo
Tian, Xi
Zhang, Rongguo
Luo, Honghe
Zhu, Ying
author_sort Yang, Lei
collection PubMed
description BACKGROUND: Accurate thymoma staging via computed tomography (CT) images is difficult even for experienced thoracic doctors. Here we developed a preoperative staging tool differentiating Masaoka-Koga (MK) stage I patients from stage II patients using CT images. METHODS: CT images of 174 thymoma patients were retrospectively selected. Two chest radiologists independently assessed the images. Variables with statistical differences in univariate analysis were adjusted for age, sex, and smoking history in multivariate logical regression to determine independent predictors of the thymoma stage. We established a deep learning (DL) 3D-DenseNet model to distinguish the MK stage I and stage II thymomas. Furthermore, we compared two different methods to label the regions of interest (ROI) in CT images. RESULTS: In routine CT images, there were statistical differences (P<0.05) in contour, necrosis, cystic components, and the degree of enhancement between stage I and II disease. Multivariate logical regression showed that only the degree of enhancement was an independent predictor of the thymoma stage. The area under the receiver operating characteristic curve (AUC) of routine CT images for classifying thymoma as MK stage I or II was low (AUC =0.639). The AUC of the 3D-DenseNet model showed better performance with a higher AUC (0.773). ROIs outlined by segmentation labels performed better (AUC =0.773) than those outlined by bounding box labels (AUC =0.722). CONCLUSIONS: Our DL 3D-DenseNet may aid thymoma stage classification, which may ultimately guide surgical treatment and improve outcomes. Compared with conventional methods, this approach provides improved staging accuracy. Moreover, ROIs labeled by segmentation is more recommendable when the sample size is limited.
format Online
Article
Text
id pubmed-7186715
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher AME Publishing Company
record_format MEDLINE/PubMed
spelling pubmed-71867152020-04-30 Development of a deep learning model for classifying thymoma as Masaoka-Koga stage I or II via preoperative CT images Yang, Lei Cai, Wenjia Yang, Xiaoyu Zhu, Haoshuai Liu, Zhenguo Wu, Xi Lei, Yiyan Zou, Jianyong Zeng, Bo Tian, Xi Zhang, Rongguo Luo, Honghe Zhu, Ying Ann Transl Med Original Article BACKGROUND: Accurate thymoma staging via computed tomography (CT) images is difficult even for experienced thoracic doctors. Here we developed a preoperative staging tool differentiating Masaoka-Koga (MK) stage I patients from stage II patients using CT images. METHODS: CT images of 174 thymoma patients were retrospectively selected. Two chest radiologists independently assessed the images. Variables with statistical differences in univariate analysis were adjusted for age, sex, and smoking history in multivariate logical regression to determine independent predictors of the thymoma stage. We established a deep learning (DL) 3D-DenseNet model to distinguish the MK stage I and stage II thymomas. Furthermore, we compared two different methods to label the regions of interest (ROI) in CT images. RESULTS: In routine CT images, there were statistical differences (P<0.05) in contour, necrosis, cystic components, and the degree of enhancement between stage I and II disease. Multivariate logical regression showed that only the degree of enhancement was an independent predictor of the thymoma stage. The area under the receiver operating characteristic curve (AUC) of routine CT images for classifying thymoma as MK stage I or II was low (AUC =0.639). The AUC of the 3D-DenseNet model showed better performance with a higher AUC (0.773). ROIs outlined by segmentation labels performed better (AUC =0.773) than those outlined by bounding box labels (AUC =0.722). CONCLUSIONS: Our DL 3D-DenseNet may aid thymoma stage classification, which may ultimately guide surgical treatment and improve outcomes. Compared with conventional methods, this approach provides improved staging accuracy. Moreover, ROIs labeled by segmentation is more recommendable when the sample size is limited. AME Publishing Company 2020-03 /pmc/articles/PMC7186715/ /pubmed/32355731 http://dx.doi.org/10.21037/atm.2020.02.183 Text en 2020 Annals of Translational Medicine. All rights reserved. https://creativecommons.org/licenses/by-nc-nd/4.0/Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0 (https://creativecommons.org/licenses/by-nc-nd/4.0/) .
spellingShingle Original Article
Yang, Lei
Cai, Wenjia
Yang, Xiaoyu
Zhu, Haoshuai
Liu, Zhenguo
Wu, Xi
Lei, Yiyan
Zou, Jianyong
Zeng, Bo
Tian, Xi
Zhang, Rongguo
Luo, Honghe
Zhu, Ying
Development of a deep learning model for classifying thymoma as Masaoka-Koga stage I or II via preoperative CT images
title Development of a deep learning model for classifying thymoma as Masaoka-Koga stage I or II via preoperative CT images
title_full Development of a deep learning model for classifying thymoma as Masaoka-Koga stage I or II via preoperative CT images
title_fullStr Development of a deep learning model for classifying thymoma as Masaoka-Koga stage I or II via preoperative CT images
title_full_unstemmed Development of a deep learning model for classifying thymoma as Masaoka-Koga stage I or II via preoperative CT images
title_short Development of a deep learning model for classifying thymoma as Masaoka-Koga stage I or II via preoperative CT images
title_sort development of a deep learning model for classifying thymoma as masaoka-koga stage i or ii via preoperative ct images
topic Original Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7186715/
https://www.ncbi.nlm.nih.gov/pubmed/32355731
http://dx.doi.org/10.21037/atm.2020.02.183
work_keys_str_mv AT yanglei developmentofadeeplearningmodelforclassifyingthymomaasmasaokakogastageioriiviapreoperativectimages
AT caiwenjia developmentofadeeplearningmodelforclassifyingthymomaasmasaokakogastageioriiviapreoperativectimages
AT yangxiaoyu developmentofadeeplearningmodelforclassifyingthymomaasmasaokakogastageioriiviapreoperativectimages
AT zhuhaoshuai developmentofadeeplearningmodelforclassifyingthymomaasmasaokakogastageioriiviapreoperativectimages
AT liuzhenguo developmentofadeeplearningmodelforclassifyingthymomaasmasaokakogastageioriiviapreoperativectimages
AT wuxi developmentofadeeplearningmodelforclassifyingthymomaasmasaokakogastageioriiviapreoperativectimages
AT leiyiyan developmentofadeeplearningmodelforclassifyingthymomaasmasaokakogastageioriiviapreoperativectimages
AT zoujianyong developmentofadeeplearningmodelforclassifyingthymomaasmasaokakogastageioriiviapreoperativectimages
AT zengbo developmentofadeeplearningmodelforclassifyingthymomaasmasaokakogastageioriiviapreoperativectimages
AT tianxi developmentofadeeplearningmodelforclassifyingthymomaasmasaokakogastageioriiviapreoperativectimages
AT zhangrongguo developmentofadeeplearningmodelforclassifyingthymomaasmasaokakogastageioriiviapreoperativectimages
AT luohonghe developmentofadeeplearningmodelforclassifyingthymomaasmasaokakogastageioriiviapreoperativectimages
AT zhuying developmentofadeeplearningmodelforclassifyingthymomaasmasaokakogastageioriiviapreoperativectimages