A deep-learning-based prognostic nomogram integrating microscopic digital pathology and macroscopic magnetic resonance images in nasopharyngeal carcinoma: a multi-cohort study

Background: To explore the prognostic value of radiomics-based and digital pathology-based imaging biomarkers from macroscopic magnetic resonance imaging (MRI) and microscopic whole-slide images for patients with nasopharyngeal carcinoma (NPC). Methods: We recruited 220 NPC patients and divided them...

Full description

Bibliographic Details
Main Authors: Fan Zhang, Lian-Zhen Zhong, Xun Zhao, Di Dong, Ji-Jin Yao, Si-Yang Wang, Ye Liu, Ding Zhu, Yin Wang, Guo-Jie Wang, Yi-Ming Wang, Dan Li, Jiang Wei, Jie Tian, Hong Shan
Format: Article
Language:English
Published: SAGE Publishing 2020-12-01
Series:Therapeutic Advances in Medical Oncology
Online Access:https://doi.org/10.1177/1758835920971416
id doaj-f478636085984139a54a1e51d0765ef5
record_format Article
spelling doaj-f478636085984139a54a1e51d0765ef52020-12-15T01:33:22ZengSAGE PublishingTherapeutic Advances in Medical Oncology1758-83592020-12-011210.1177/1758835920971416A deep-learning-based prognostic nomogram integrating microscopic digital pathology and macroscopic magnetic resonance images in nasopharyngeal carcinoma: a multi-cohort studyFan ZhangLian-Zhen ZhongXun ZhaoDi DongJi-Jin YaoSi-Yang WangYe LiuDing ZhuYin WangGuo-Jie WangYi-Ming WangDan LiJiang WeiJie TianHong ShanBackground: To explore the prognostic value of radiomics-based and digital pathology-based imaging biomarkers from macroscopic magnetic resonance imaging (MRI) and microscopic whole-slide images for patients with nasopharyngeal carcinoma (NPC). Methods: We recruited 220 NPC patients and divided them into training ( n  = 132), internal test ( n  = 44), and external test ( n  = 44) cohorts. The primary endpoint was failure-free survival (FFS). Radiomic features were extracted from pretreatment MRI and selected and integrated into a radiomic signature. The histopathological signature was extracted from whole-slide images of biopsy specimens using an end-to-end deep-learning method. Incorporating two signatures and independent clinical factors, a multi-scale nomogram was constructed. We also tested the correlation between the key imaging features and genetic alternations in an independent cohort of 16 patients (biological test cohort). Results: Both radiomic and histopathologic signatures presented significant associations with treatment failure in the three cohorts (C-index: 0.689–0.779, all p  < 0.050). The multi-scale nomogram showed a consistent significant improvement for predicting treatment failure compared with the clinical model in the training (C-index: 0.817 versus 0.730, p  < 0.050), internal test (C-index: 0.828 versus 0.602, p  < 0.050) and external test (C-index: 0.834 versus 0.679, p  < 0.050) cohorts. Furthermore, patients were stratified successfully into two groups with distinguishable prognosis (log-rank p  < 0.0010) using our nomogram. We also found that two texture features were related to the genetic alternations of chromatin remodeling pathways in another independent cohort. Conclusion: The multi-scale imaging features showed a complementary value in prognostic prediction and may improve individualized treatment in NPC.https://doi.org/10.1177/1758835920971416
collection DOAJ
language English
format Article
sources DOAJ
author Fan Zhang
Lian-Zhen Zhong
Xun Zhao
Di Dong
Ji-Jin Yao
Si-Yang Wang
Ye Liu
Ding Zhu
Yin Wang
Guo-Jie Wang
Yi-Ming Wang
Dan Li
Jiang Wei
Jie Tian
Hong Shan
spellingShingle Fan Zhang
Lian-Zhen Zhong
Xun Zhao
Di Dong
Ji-Jin Yao
Si-Yang Wang
Ye Liu
Ding Zhu
Yin Wang
Guo-Jie Wang
Yi-Ming Wang
Dan Li
Jiang Wei
Jie Tian
Hong Shan
A deep-learning-based prognostic nomogram integrating microscopic digital pathology and macroscopic magnetic resonance images in nasopharyngeal carcinoma: a multi-cohort study
Therapeutic Advances in Medical Oncology
author_facet Fan Zhang
Lian-Zhen Zhong
Xun Zhao
Di Dong
Ji-Jin Yao
Si-Yang Wang
Ye Liu
Ding Zhu
Yin Wang
Guo-Jie Wang
Yi-Ming Wang
Dan Li
Jiang Wei
Jie Tian
Hong Shan
author_sort Fan Zhang
title A deep-learning-based prognostic nomogram integrating microscopic digital pathology and macroscopic magnetic resonance images in nasopharyngeal carcinoma: a multi-cohort study
title_short A deep-learning-based prognostic nomogram integrating microscopic digital pathology and macroscopic magnetic resonance images in nasopharyngeal carcinoma: a multi-cohort study
title_full A deep-learning-based prognostic nomogram integrating microscopic digital pathology and macroscopic magnetic resonance images in nasopharyngeal carcinoma: a multi-cohort study
title_fullStr A deep-learning-based prognostic nomogram integrating microscopic digital pathology and macroscopic magnetic resonance images in nasopharyngeal carcinoma: a multi-cohort study
title_full_unstemmed A deep-learning-based prognostic nomogram integrating microscopic digital pathology and macroscopic magnetic resonance images in nasopharyngeal carcinoma: a multi-cohort study
title_sort deep-learning-based prognostic nomogram integrating microscopic digital pathology and macroscopic magnetic resonance images in nasopharyngeal carcinoma: a multi-cohort study
publisher SAGE Publishing
series Therapeutic Advances in Medical Oncology
issn 1758-8359
publishDate 2020-12-01
description Background: To explore the prognostic value of radiomics-based and digital pathology-based imaging biomarkers from macroscopic magnetic resonance imaging (MRI) and microscopic whole-slide images for patients with nasopharyngeal carcinoma (NPC). Methods: We recruited 220 NPC patients and divided them into training ( n  = 132), internal test ( n  = 44), and external test ( n  = 44) cohorts. The primary endpoint was failure-free survival (FFS). Radiomic features were extracted from pretreatment MRI and selected and integrated into a radiomic signature. The histopathological signature was extracted from whole-slide images of biopsy specimens using an end-to-end deep-learning method. Incorporating two signatures and independent clinical factors, a multi-scale nomogram was constructed. We also tested the correlation between the key imaging features and genetic alternations in an independent cohort of 16 patients (biological test cohort). Results: Both radiomic and histopathologic signatures presented significant associations with treatment failure in the three cohorts (C-index: 0.689–0.779, all p  < 0.050). The multi-scale nomogram showed a consistent significant improvement for predicting treatment failure compared with the clinical model in the training (C-index: 0.817 versus 0.730, p  < 0.050), internal test (C-index: 0.828 versus 0.602, p  < 0.050) and external test (C-index: 0.834 versus 0.679, p  < 0.050) cohorts. Furthermore, patients were stratified successfully into two groups with distinguishable prognosis (log-rank p  < 0.0010) using our nomogram. We also found that two texture features were related to the genetic alternations of chromatin remodeling pathways in another independent cohort. Conclusion: The multi-scale imaging features showed a complementary value in prognostic prediction and may improve individualized treatment in NPC.
url https://doi.org/10.1177/1758835920971416
work_keys_str_mv AT fanzhang adeeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT lianzhenzhong adeeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT xunzhao adeeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT didong adeeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT jijinyao adeeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT siyangwang adeeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT yeliu adeeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT dingzhu adeeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT yinwang adeeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT guojiewang adeeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT yimingwang adeeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT danli adeeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT jiangwei adeeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT jietian adeeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT hongshan adeeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT fanzhang deeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT lianzhenzhong deeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT xunzhao deeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT didong deeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT jijinyao deeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT siyangwang deeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT yeliu deeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT dingzhu deeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT yinwang deeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT guojiewang deeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT yimingwang deeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT danli deeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT jiangwei deeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT jietian deeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
AT hongshan deeplearningbasedprognosticnomogramintegratingmicroscopicdigitalpathologyandmacroscopicmagneticresonanceimagesinnasopharyngealcarcinomaamulticohortstudy
_version_ 1724382972262481920