A deep learning based smartphone application for early detection of nasopharyngeal carcinoma using endoscopic images

Abstract Nasal endoscopy is crucial for the early detection of nasopharyngeal carcinoma (NPC), but its accuracy relies heavily on the clinician’s expertise, posing challenges for primary healthcare providers. Here, we retrospectively analysed 39,340 nasal endoscopic white-light images from three hig...

Full description

Saved in:
Bibliographic Details
Main Authors: Yubiao Yue, Xinyu Zeng, Huanjie Lin, Jialong Xu, Fan Zhang, KeLin Zhou, Li Li, Zhenzhang Li
Format: Article
Language:English
Published: Nature Portfolio 2024-12-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-024-01403-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850282197987098624
author Yubiao Yue
Xinyu Zeng
Huanjie Lin
Jialong Xu
Fan Zhang
KeLin Zhou
Li Li
Zhenzhang Li
author_facet Yubiao Yue
Xinyu Zeng
Huanjie Lin
Jialong Xu
Fan Zhang
KeLin Zhou
Li Li
Zhenzhang Li
author_sort Yubiao Yue
collection DOAJ
description Abstract Nasal endoscopy is crucial for the early detection of nasopharyngeal carcinoma (NPC), but its accuracy relies heavily on the clinician’s expertise, posing challenges for primary healthcare providers. Here, we retrospectively analysed 39,340 nasal endoscopic white-light images from three high-incidence NPC centres, utilising eight advanced deep learning models to develop an Internet-enabled smartphone application, “Nose-Keeper”, that can be used for early detection of NPC and five prevalent nasal diseases and assessment of healthy individuals. Our app demonstrated a remarkable overall accuracy of 92.27% (95% Confidence Interval (CI): 90.66%–93.61%). Notably, its sensitivity and specificity in NPC detection achieved 96.39% and 99.91%, respectively, outperforming nine experienced otolaryngologists. Explainable artificial intelligence was employed to highlight key lesion areas, improving Nose-Keeper’s decision-making accuracy and safety. Nose-Keeper can assist primary healthcare providers in diagnosing NPC and common nasal diseases efficiently, offering a valuable resource for people in high-incidence NPC regions to manage nasal cavity health effectively.
format Article
id doaj-art-d630dd36f67941a48ef629871df18e4d
institution OA Journals
issn 2398-6352
language English
publishDate 2024-12-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-d630dd36f67941a48ef629871df18e4d2025-08-20T01:48:03ZengNature Portfolionpj Digital Medicine2398-63522024-12-017111610.1038/s41746-024-01403-2A deep learning based smartphone application for early detection of nasopharyngeal carcinoma using endoscopic imagesYubiao Yue0Xinyu Zeng1Huanjie Lin2Jialong Xu3Fan Zhang4KeLin Zhou5Li Li6Zhenzhang Li7School of Mathematics and Systems Science, Guangdong Polytechnic Normal UniversityDepartment of Otorhinolaryngology, The Second Affiliated Hospital of Shenzhen UniversityDepartment of Radiology, The Second Affiliated Hospital of Guangzhou Medical UniversitySchool of Biomedical Engineering, Guangzhou Medical UniversityDepartment of science and education, Foshan Sanshui District People’s HospitalDepartment of Otorhinolaryngology, Leizhou People’s HospitalDepartment of Otorhinolaryngology, Leizhou People’s HospitalSchool of Mathematics and Systems Science, Guangdong Polytechnic Normal UniversityAbstract Nasal endoscopy is crucial for the early detection of nasopharyngeal carcinoma (NPC), but its accuracy relies heavily on the clinician’s expertise, posing challenges for primary healthcare providers. Here, we retrospectively analysed 39,340 nasal endoscopic white-light images from three high-incidence NPC centres, utilising eight advanced deep learning models to develop an Internet-enabled smartphone application, “Nose-Keeper”, that can be used for early detection of NPC and five prevalent nasal diseases and assessment of healthy individuals. Our app demonstrated a remarkable overall accuracy of 92.27% (95% Confidence Interval (CI): 90.66%–93.61%). Notably, its sensitivity and specificity in NPC detection achieved 96.39% and 99.91%, respectively, outperforming nine experienced otolaryngologists. Explainable artificial intelligence was employed to highlight key lesion areas, improving Nose-Keeper’s decision-making accuracy and safety. Nose-Keeper can assist primary healthcare providers in diagnosing NPC and common nasal diseases efficiently, offering a valuable resource for people in high-incidence NPC regions to manage nasal cavity health effectively.https://doi.org/10.1038/s41746-024-01403-2
spellingShingle Yubiao Yue
Xinyu Zeng
Huanjie Lin
Jialong Xu
Fan Zhang
KeLin Zhou
Li Li
Zhenzhang Li
A deep learning based smartphone application for early detection of nasopharyngeal carcinoma using endoscopic images
npj Digital Medicine
title A deep learning based smartphone application for early detection of nasopharyngeal carcinoma using endoscopic images
title_full A deep learning based smartphone application for early detection of nasopharyngeal carcinoma using endoscopic images
title_fullStr A deep learning based smartphone application for early detection of nasopharyngeal carcinoma using endoscopic images
title_full_unstemmed A deep learning based smartphone application for early detection of nasopharyngeal carcinoma using endoscopic images
title_short A deep learning based smartphone application for early detection of nasopharyngeal carcinoma using endoscopic images
title_sort deep learning based smartphone application for early detection of nasopharyngeal carcinoma using endoscopic images
url https://doi.org/10.1038/s41746-024-01403-2
work_keys_str_mv AT yubiaoyue adeeplearningbasedsmartphoneapplicationforearlydetectionofnasopharyngealcarcinomausingendoscopicimages
AT xinyuzeng adeeplearningbasedsmartphoneapplicationforearlydetectionofnasopharyngealcarcinomausingendoscopicimages
AT huanjielin adeeplearningbasedsmartphoneapplicationforearlydetectionofnasopharyngealcarcinomausingendoscopicimages
AT jialongxu adeeplearningbasedsmartphoneapplicationforearlydetectionofnasopharyngealcarcinomausingendoscopicimages
AT fanzhang adeeplearningbasedsmartphoneapplicationforearlydetectionofnasopharyngealcarcinomausingendoscopicimages
AT kelinzhou adeeplearningbasedsmartphoneapplicationforearlydetectionofnasopharyngealcarcinomausingendoscopicimages
AT lili adeeplearningbasedsmartphoneapplicationforearlydetectionofnasopharyngealcarcinomausingendoscopicimages
AT zhenzhangli adeeplearningbasedsmartphoneapplicationforearlydetectionofnasopharyngealcarcinomausingendoscopicimages
AT yubiaoyue deeplearningbasedsmartphoneapplicationforearlydetectionofnasopharyngealcarcinomausingendoscopicimages
AT xinyuzeng deeplearningbasedsmartphoneapplicationforearlydetectionofnasopharyngealcarcinomausingendoscopicimages
AT huanjielin deeplearningbasedsmartphoneapplicationforearlydetectionofnasopharyngealcarcinomausingendoscopicimages
AT jialongxu deeplearningbasedsmartphoneapplicationforearlydetectionofnasopharyngealcarcinomausingendoscopicimages
AT fanzhang deeplearningbasedsmartphoneapplicationforearlydetectionofnasopharyngealcarcinomausingendoscopicimages
AT kelinzhou deeplearningbasedsmartphoneapplicationforearlydetectionofnasopharyngealcarcinomausingendoscopicimages
AT lili deeplearningbasedsmartphoneapplicationforearlydetectionofnasopharyngealcarcinomausingendoscopicimages
AT zhenzhangli deeplearningbasedsmartphoneapplicationforearlydetectionofnasopharyngealcarcinomausingendoscopicimages