Cargando…

Predicting Chemotherapeutic Response for Far-advanced Gastric Cancer by Radiomics with Deep Learning Semi-automatic Segmentation

Purpose: To build a dual-energy computed tomography (DECT) delta radiomics model to predict chemotherapeutic response for far-advanced gastric cancer (GC) patients. A semi-automatic segmentation method based on deep learning was designed, and its performance was compared with that of manual segmenta...

Descripción completa

Detalles Bibliográficos
Autores principales: Tan, Jing-wen, Wang, Lan, Chen, Yong, Xi, WenQi, Ji, Jun, Wang, Lingyun, Xu, Xin, Zou, Long-kuan, Feng, Jian-xing, Zhang, Jun, Zhang, Huan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Ivyspring International Publisher 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7646171/
https://www.ncbi.nlm.nih.gov/pubmed/33193886
http://dx.doi.org/10.7150/jca.46704
_version_ 1783606742081339392
author Tan, Jing-wen
Wang, Lan
Chen, Yong
Xi, WenQi
Ji, Jun
Wang, Lingyun
Xu, Xin
Zou, Long-kuan
Feng, Jian-xing
Zhang, Jun
Zhang, Huan
author_facet Tan, Jing-wen
Wang, Lan
Chen, Yong
Xi, WenQi
Ji, Jun
Wang, Lingyun
Xu, Xin
Zou, Long-kuan
Feng, Jian-xing
Zhang, Jun
Zhang, Huan
author_sort Tan, Jing-wen
collection PubMed
description Purpose: To build a dual-energy computed tomography (DECT) delta radiomics model to predict chemotherapeutic response for far-advanced gastric cancer (GC) patients. A semi-automatic segmentation method based on deep learning was designed, and its performance was compared with that of manual segmentation. Methods: This retrospective study included 86 patients with far-advanced GC treated with chemotherapy from September 2016 to December 2017 (66 and 20 in the training and testing cohorts, respectively). Delta radiomics features between the baseline and first follow-up DECT were modeled by random forest to predict the chemotherapeutic response evaluated by the second follow-up DECT. Nine feature subsets from confounding factors and delta radiomics features were used to choose the best model with 10-fold cross-validation in the training cohort. A semi-automatic segmentation method based on deep learning was developed to predict the chemotherapeutic response and compared with manual segmentation in the testing cohort, which was further validated in an independent validation cohort of 30 patients. Results: The best model, constructed by confounding factors and texture features, reached an average AUC of 0.752 in the training cohort. Our proposed semi-automatic segmentation method was more time-effective than manual segmentation, with average saving-time of 11.2333 ± 6.3989 minutes and 9.9889 ±5.5086 minutes in the testing cohort and the independent validation cohort, respectively (both p < 0.05). The predictive ability of the semi-automatic segmentation was also better than that of the manual segmentation both in the testing cohort and the independent validation cohort (AUC: 0.728 vs. 0.687 and 0.828 vs. 0.749, respectively). Conclusion: DECT delta radiomics serves as a promising biomarker for predicting chemotherapeutic response for far-advanced GC. Semi-automatic segmentation based on deep learning shows the potential for clinical use with increased reproducibility and decreased labor costs compared to the manual version.
format Online
Article
Text
id pubmed-7646171
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Ivyspring International Publisher
record_format MEDLINE/PubMed
spelling pubmed-76461712020-11-12 Predicting Chemotherapeutic Response for Far-advanced Gastric Cancer by Radiomics with Deep Learning Semi-automatic Segmentation Tan, Jing-wen Wang, Lan Chen, Yong Xi, WenQi Ji, Jun Wang, Lingyun Xu, Xin Zou, Long-kuan Feng, Jian-xing Zhang, Jun Zhang, Huan J Cancer Research Paper Purpose: To build a dual-energy computed tomography (DECT) delta radiomics model to predict chemotherapeutic response for far-advanced gastric cancer (GC) patients. A semi-automatic segmentation method based on deep learning was designed, and its performance was compared with that of manual segmentation. Methods: This retrospective study included 86 patients with far-advanced GC treated with chemotherapy from September 2016 to December 2017 (66 and 20 in the training and testing cohorts, respectively). Delta radiomics features between the baseline and first follow-up DECT were modeled by random forest to predict the chemotherapeutic response evaluated by the second follow-up DECT. Nine feature subsets from confounding factors and delta radiomics features were used to choose the best model with 10-fold cross-validation in the training cohort. A semi-automatic segmentation method based on deep learning was developed to predict the chemotherapeutic response and compared with manual segmentation in the testing cohort, which was further validated in an independent validation cohort of 30 patients. Results: The best model, constructed by confounding factors and texture features, reached an average AUC of 0.752 in the training cohort. Our proposed semi-automatic segmentation method was more time-effective than manual segmentation, with average saving-time of 11.2333 ± 6.3989 minutes and 9.9889 ±5.5086 minutes in the testing cohort and the independent validation cohort, respectively (both p < 0.05). The predictive ability of the semi-automatic segmentation was also better than that of the manual segmentation both in the testing cohort and the independent validation cohort (AUC: 0.728 vs. 0.687 and 0.828 vs. 0.749, respectively). Conclusion: DECT delta radiomics serves as a promising biomarker for predicting chemotherapeutic response for far-advanced GC. Semi-automatic segmentation based on deep learning shows the potential for clinical use with increased reproducibility and decreased labor costs compared to the manual version. Ivyspring International Publisher 2020-10-18 /pmc/articles/PMC7646171/ /pubmed/33193886 http://dx.doi.org/10.7150/jca.46704 Text en © The author(s) This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/). See http://ivyspring.com/terms for full terms and conditions.
spellingShingle Research Paper
Tan, Jing-wen
Wang, Lan
Chen, Yong
Xi, WenQi
Ji, Jun
Wang, Lingyun
Xu, Xin
Zou, Long-kuan
Feng, Jian-xing
Zhang, Jun
Zhang, Huan
Predicting Chemotherapeutic Response for Far-advanced Gastric Cancer by Radiomics with Deep Learning Semi-automatic Segmentation
title Predicting Chemotherapeutic Response for Far-advanced Gastric Cancer by Radiomics with Deep Learning Semi-automatic Segmentation
title_full Predicting Chemotherapeutic Response for Far-advanced Gastric Cancer by Radiomics with Deep Learning Semi-automatic Segmentation
title_fullStr Predicting Chemotherapeutic Response for Far-advanced Gastric Cancer by Radiomics with Deep Learning Semi-automatic Segmentation
title_full_unstemmed Predicting Chemotherapeutic Response for Far-advanced Gastric Cancer by Radiomics with Deep Learning Semi-automatic Segmentation
title_short Predicting Chemotherapeutic Response for Far-advanced Gastric Cancer by Radiomics with Deep Learning Semi-automatic Segmentation
title_sort predicting chemotherapeutic response for far-advanced gastric cancer by radiomics with deep learning semi-automatic segmentation
topic Research Paper
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7646171/
https://www.ncbi.nlm.nih.gov/pubmed/33193886
http://dx.doi.org/10.7150/jca.46704
work_keys_str_mv AT tanjingwen predictingchemotherapeuticresponseforfaradvancedgastriccancerbyradiomicswithdeeplearningsemiautomaticsegmentation
AT wanglan predictingchemotherapeuticresponseforfaradvancedgastriccancerbyradiomicswithdeeplearningsemiautomaticsegmentation
AT chenyong predictingchemotherapeuticresponseforfaradvancedgastriccancerbyradiomicswithdeeplearningsemiautomaticsegmentation
AT xiwenqi predictingchemotherapeuticresponseforfaradvancedgastriccancerbyradiomicswithdeeplearningsemiautomaticsegmentation
AT jijun predictingchemotherapeuticresponseforfaradvancedgastriccancerbyradiomicswithdeeplearningsemiautomaticsegmentation
AT wanglingyun predictingchemotherapeuticresponseforfaradvancedgastriccancerbyradiomicswithdeeplearningsemiautomaticsegmentation
AT xuxin predictingchemotherapeuticresponseforfaradvancedgastriccancerbyradiomicswithdeeplearningsemiautomaticsegmentation
AT zoulongkuan predictingchemotherapeuticresponseforfaradvancedgastriccancerbyradiomicswithdeeplearningsemiautomaticsegmentation
AT fengjianxing predictingchemotherapeuticresponseforfaradvancedgastriccancerbyradiomicswithdeeplearningsemiautomaticsegmentation
AT zhangjun predictingchemotherapeuticresponseforfaradvancedgastriccancerbyradiomicswithdeeplearningsemiautomaticsegmentation
AT zhanghuan predictingchemotherapeuticresponseforfaradvancedgastriccancerbyradiomicswithdeeplearningsemiautomaticsegmentation