Integrating Clinical Data and Attentional CT Imaging Features for Esophageal Fistula Prediction in Esophageal Cancer

Background and PurposeThis study aims to develop a risk model to predict esophageal fistula in esophageal cancer (EC) patients by learning from both clinical data and computerized tomography (CT) radiomic features.Materials and MethodsIn this retrospective study, computerized tomography (CT) images...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Yiyue Xu, Hui Cui, Taotao Dong, Bing Zou, Bingjie Fan, Wanlong Li, Shijiang Wang, Xindong Sun, Jinming Yu, Linlin Wang
Formato: article
Lenguaje:EN
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://doaj.org/article/fcf5aba1cfac43928a6f6bcb67f44353
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:fcf5aba1cfac43928a6f6bcb67f44353
record_format dspace
spelling oai:doaj.org-article:fcf5aba1cfac43928a6f6bcb67f443532021-11-30T11:18:48ZIntegrating Clinical Data and Attentional CT Imaging Features for Esophageal Fistula Prediction in Esophageal Cancer2234-943X10.3389/fonc.2021.688706https://doaj.org/article/fcf5aba1cfac43928a6f6bcb67f443532021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fonc.2021.688706/fullhttps://doaj.org/toc/2234-943XBackground and PurposeThis study aims to develop a risk model to predict esophageal fistula in esophageal cancer (EC) patients by learning from both clinical data and computerized tomography (CT) radiomic features.Materials and MethodsIn this retrospective study, computerized tomography (CT) images and clinical data of 186 esophageal fistula patients and 372 controls (1:2 matched by the diagnosis time of EC, sex, marriage, and race) were collected. All patients had esophageal cancer and did not receive esophageal surgery. 70% patients were assigned into training set randomly and 30% into validation set. We firstly use a novel attentional convolutional neural network for radiographic descriptor extraction from nine views of planes of contextual CT, segmented tumor and neighboring structures. Then clinical factors including general, diagnostic, pathologic, therapeutic and hematological parameters are fed into neural network for high-level latent representation. The radiographic descriptors and latent clinical factor representations are finally associated by a fully connected layer for patient level risk prediction using SoftMax classifier.Results512 deep radiographic features and 32 clinical features were extracted. The integrative deep learning model achieved C-index of 0.901, sensitivity of 0.835, and specificity of 0.918 on validation set with superior performance than non-integrative model using CT imaging alone (C-index = 0.857) or clinical data alone (C-index = 0.780).ConclusionThe integration of radiomic descriptors from CT and clinical data significantly improved the esophageal fistula prediction. We suggest that this model has the potential to support individualized stratification and treatment planning for EC patients.Yiyue XuYiyue XuYiyue XuHui CuiTaotao DongBing ZouBingjie FanWanlong LiShijiang WangXindong SunJinming YuLinlin WangFrontiers Media S.A.articleesophageal canceresophageal fistularadiomicsdeep learningprediction modelNeoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENFrontiers in Oncology, Vol 11 (2021)
institution DOAJ
collection DOAJ
language EN
topic esophageal cancer
esophageal fistula
radiomics
deep learning
prediction model
Neoplasms. Tumors. Oncology. Including cancer and carcinogens
RC254-282
spellingShingle esophageal cancer
esophageal fistula
radiomics
deep learning
prediction model
Neoplasms. Tumors. Oncology. Including cancer and carcinogens
RC254-282
Yiyue Xu
Yiyue Xu
Yiyue Xu
Hui Cui
Taotao Dong
Bing Zou
Bingjie Fan
Wanlong Li
Shijiang Wang
Xindong Sun
Jinming Yu
Linlin Wang
Integrating Clinical Data and Attentional CT Imaging Features for Esophageal Fistula Prediction in Esophageal Cancer
description Background and PurposeThis study aims to develop a risk model to predict esophageal fistula in esophageal cancer (EC) patients by learning from both clinical data and computerized tomography (CT) radiomic features.Materials and MethodsIn this retrospective study, computerized tomography (CT) images and clinical data of 186 esophageal fistula patients and 372 controls (1:2 matched by the diagnosis time of EC, sex, marriage, and race) were collected. All patients had esophageal cancer and did not receive esophageal surgery. 70% patients were assigned into training set randomly and 30% into validation set. We firstly use a novel attentional convolutional neural network for radiographic descriptor extraction from nine views of planes of contextual CT, segmented tumor and neighboring structures. Then clinical factors including general, diagnostic, pathologic, therapeutic and hematological parameters are fed into neural network for high-level latent representation. The radiographic descriptors and latent clinical factor representations are finally associated by a fully connected layer for patient level risk prediction using SoftMax classifier.Results512 deep radiographic features and 32 clinical features were extracted. The integrative deep learning model achieved C-index of 0.901, sensitivity of 0.835, and specificity of 0.918 on validation set with superior performance than non-integrative model using CT imaging alone (C-index = 0.857) or clinical data alone (C-index = 0.780).ConclusionThe integration of radiomic descriptors from CT and clinical data significantly improved the esophageal fistula prediction. We suggest that this model has the potential to support individualized stratification and treatment planning for EC patients.
format article
author Yiyue Xu
Yiyue Xu
Yiyue Xu
Hui Cui
Taotao Dong
Bing Zou
Bingjie Fan
Wanlong Li
Shijiang Wang
Xindong Sun
Jinming Yu
Linlin Wang
author_facet Yiyue Xu
Yiyue Xu
Yiyue Xu
Hui Cui
Taotao Dong
Bing Zou
Bingjie Fan
Wanlong Li
Shijiang Wang
Xindong Sun
Jinming Yu
Linlin Wang
author_sort Yiyue Xu
title Integrating Clinical Data and Attentional CT Imaging Features for Esophageal Fistula Prediction in Esophageal Cancer
title_short Integrating Clinical Data and Attentional CT Imaging Features for Esophageal Fistula Prediction in Esophageal Cancer
title_full Integrating Clinical Data and Attentional CT Imaging Features for Esophageal Fistula Prediction in Esophageal Cancer
title_fullStr Integrating Clinical Data and Attentional CT Imaging Features for Esophageal Fistula Prediction in Esophageal Cancer
title_full_unstemmed Integrating Clinical Data and Attentional CT Imaging Features for Esophageal Fistula Prediction in Esophageal Cancer
title_sort integrating clinical data and attentional ct imaging features for esophageal fistula prediction in esophageal cancer
publisher Frontiers Media S.A.
publishDate 2021
url https://doaj.org/article/fcf5aba1cfac43928a6f6bcb67f44353
work_keys_str_mv AT yiyuexu integratingclinicaldataandattentionalctimagingfeaturesforesophagealfistulapredictioninesophagealcancer
AT yiyuexu integratingclinicaldataandattentionalctimagingfeaturesforesophagealfistulapredictioninesophagealcancer
AT yiyuexu integratingclinicaldataandattentionalctimagingfeaturesforesophagealfistulapredictioninesophagealcancer
AT huicui integratingclinicaldataandattentionalctimagingfeaturesforesophagealfistulapredictioninesophagealcancer
AT taotaodong integratingclinicaldataandattentionalctimagingfeaturesforesophagealfistulapredictioninesophagealcancer
AT bingzou integratingclinicaldataandattentionalctimagingfeaturesforesophagealfistulapredictioninesophagealcancer
AT bingjiefan integratingclinicaldataandattentionalctimagingfeaturesforesophagealfistulapredictioninesophagealcancer
AT wanlongli integratingclinicaldataandattentionalctimagingfeaturesforesophagealfistulapredictioninesophagealcancer
AT shijiangwang integratingclinicaldataandattentionalctimagingfeaturesforesophagealfistulapredictioninesophagealcancer
AT xindongsun integratingclinicaldataandattentionalctimagingfeaturesforesophagealfistulapredictioninesophagealcancer
AT jinmingyu integratingclinicaldataandattentionalctimagingfeaturesforesophagealfistulapredictioninesophagealcancer
AT linlinwang integratingclinicaldataandattentionalctimagingfeaturesforesophagealfistulapredictioninesophagealcancer
_version_ 1718406721870757888