Postoperative outcome analysis of chronic rhinosinusitis using transfer learning with pre-trained foundation models based on endoscopic images: a multicenter, observational study

Abstract Background This study developed a foundation model-based analytical framework for the analysis of postoperative endoscopic images in chronic rhinosinusitis (CRS). The framework leverages the standardized identification and reproducible results enabled by artificial intelligence algorithms,...

Full description

Saved in:
Bibliographic Details
Main Authors: Wentao Gong, Keguang Chen, Xiao Chen, Xueli Liu, Zhen Li, Li Wang, Yuxuan Shi, Quan Liu, Xicai Sun, Xinsheng Huang, Xu Luo, Hongmeng Yu
Format: Article
Language:English
Published: BMC 2025-07-01
Series:BioMedical Engineering OnLine
Subjects:
Online Access:https://doi.org/10.1186/s12938-025-01428-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849342875829010432
author Wentao Gong
Keguang Chen
Xiao Chen
Xueli Liu
Zhen Li
Li Wang
Yuxuan Shi
Quan Liu
Xicai Sun
Xinsheng Huang
Xu Luo
Hongmeng Yu
author_facet Wentao Gong
Keguang Chen
Xiao Chen
Xueli Liu
Zhen Li
Li Wang
Yuxuan Shi
Quan Liu
Xicai Sun
Xinsheng Huang
Xu Luo
Hongmeng Yu
author_sort Wentao Gong
collection DOAJ
description Abstract Background This study developed a foundation model-based analytical framework for the analysis of postoperative endoscopic images in chronic rhinosinusitis (CRS). The framework leverages the standardized identification and reproducible results enabled by artificial intelligence algorithms, combined with the strengths of pre-trained foundation models in developing downstream applications. This approach effectively addresses the inherent challenge of strong subjectivity in conventional postoperative endoscopic evaluation for CRS. Methods The postoperative sinus cavity status in CRS was classified into three states: "polyp", "edema", and "smooth", to establish an endoscopic image dataset. Using transfer learning based on pre-trained large models for endoscopic images, we developed an analytical model for postoperative outcome evaluation in CRS. Comparative studies with various traditional training methods were conducted to evaluate this approach, demonstrating that it can achieve satisfactory model performance even with limited datasets. Results The endoscopic image-based pre-trained transfer learning model proposed in this study demonstrates significant advantages over conventional methods in diagnostic performance. In the precision evaluation for distinguishing smooth mucosa from rest conditions (edema and polyps), our model achieved mean accuracy and AUC values of 91.17% and 0.97, respectively, with specificity reaching 86.35% and sensitivity attaining 91.85%. This represents an approximate 4% improvement in mean accuracy compared to traditional algorithms. Notably, in the differential diagnosis between polyps and rest conditions (smooth mucosa and edema), the proposed algorithm attained mean accuracy and AUC values of 81.87% and 0.90, respectively, demonstrating specificity of 80.53% and sensitivity of 81.04%. This configuration shows a substantial 15% enhancement in mean accuracy relative to conventional diagnostic approaches. Conclusion The transfer learning algorithm model based on pre-trained foundation models can provide accurate and reproducible analysis of postoperative outcomes in CRS, effectively addressing the issue of high subjectivity in postoperative evaluation. With limited data, our model can achieve better generalization performance compared to traditional algorithms.
format Article
id doaj-art-d5bbd5393c0547e5adce43b4fde1b103
institution Kabale University
issn 1475-925X
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series BioMedical Engineering OnLine
spelling doaj-art-d5bbd5393c0547e5adce43b4fde1b1032025-08-20T03:43:14ZengBMCBioMedical Engineering OnLine1475-925X2025-07-0124111110.1186/s12938-025-01428-yPostoperative outcome analysis of chronic rhinosinusitis using transfer learning with pre-trained foundation models based on endoscopic images: a multicenter, observational studyWentao Gong0Keguang Chen1Xiao Chen2Xueli Liu3Zhen Li4Li Wang5Yuxuan Shi6Quan Liu7Xicai Sun8Xinsheng Huang9Xu Luo10Hongmeng Yu11School of Health Science and Engineering, University of Shanghai for Science and TechnologyDepartment of Otorhinolaryngology-Head and Neck Surgery, Zhongshan Hospital Affiliated to Fudan UniversityENT Institute and Department of Otorhinolaryngology, Eye & ENT Hospital, Fudan UniversityENT Institute and Department of Otorhinolaryngology, Eye & ENT Hospital, Fudan UniversityENT Institute and Department of Otorhinolaryngology, Eye & ENT Hospital, Fudan UniversityENT Institute and Department of Otorhinolaryngology, Eye & ENT Hospital, Fudan UniversityENT Institute and Department of Otorhinolaryngology, Eye & ENT Hospital, Fudan UniversityENT Institute and Department of Otorhinolaryngology, Eye & ENT Hospital, Fudan UniversityENT Institute and Department of Otorhinolaryngology, Eye & ENT Hospital, Fudan UniversityDepartment of Otorhinolaryngology-Head and Neck Surgery, Zhongshan Hospital Affiliated to Fudan UniversityShanghai ZEHNIT Medical Technology Co.,Ltd.School of Health Science and Engineering, University of Shanghai for Science and TechnologyAbstract Background This study developed a foundation model-based analytical framework for the analysis of postoperative endoscopic images in chronic rhinosinusitis (CRS). The framework leverages the standardized identification and reproducible results enabled by artificial intelligence algorithms, combined with the strengths of pre-trained foundation models in developing downstream applications. This approach effectively addresses the inherent challenge of strong subjectivity in conventional postoperative endoscopic evaluation for CRS. Methods The postoperative sinus cavity status in CRS was classified into three states: "polyp", "edema", and "smooth", to establish an endoscopic image dataset. Using transfer learning based on pre-trained large models for endoscopic images, we developed an analytical model for postoperative outcome evaluation in CRS. Comparative studies with various traditional training methods were conducted to evaluate this approach, demonstrating that it can achieve satisfactory model performance even with limited datasets. Results The endoscopic image-based pre-trained transfer learning model proposed in this study demonstrates significant advantages over conventional methods in diagnostic performance. In the precision evaluation for distinguishing smooth mucosa from rest conditions (edema and polyps), our model achieved mean accuracy and AUC values of 91.17% and 0.97, respectively, with specificity reaching 86.35% and sensitivity attaining 91.85%. This represents an approximate 4% improvement in mean accuracy compared to traditional algorithms. Notably, in the differential diagnosis between polyps and rest conditions (smooth mucosa and edema), the proposed algorithm attained mean accuracy and AUC values of 81.87% and 0.90, respectively, demonstrating specificity of 80.53% and sensitivity of 81.04%. This configuration shows a substantial 15% enhancement in mean accuracy relative to conventional diagnostic approaches. Conclusion The transfer learning algorithm model based on pre-trained foundation models can provide accurate and reproducible analysis of postoperative outcomes in CRS, effectively addressing the issue of high subjectivity in postoperative evaluation. With limited data, our model can achieve better generalization performance compared to traditional algorithms.https://doi.org/10.1186/s12938-025-01428-yChronic rhinosinusitisSurgical prognosisTransfer learningPre-trained foundation model
spellingShingle Wentao Gong
Keguang Chen
Xiao Chen
Xueli Liu
Zhen Li
Li Wang
Yuxuan Shi
Quan Liu
Xicai Sun
Xinsheng Huang
Xu Luo
Hongmeng Yu
Postoperative outcome analysis of chronic rhinosinusitis using transfer learning with pre-trained foundation models based on endoscopic images: a multicenter, observational study
BioMedical Engineering OnLine
Chronic rhinosinusitis
Surgical prognosis
Transfer learning
Pre-trained foundation model
title Postoperative outcome analysis of chronic rhinosinusitis using transfer learning with pre-trained foundation models based on endoscopic images: a multicenter, observational study
title_full Postoperative outcome analysis of chronic rhinosinusitis using transfer learning with pre-trained foundation models based on endoscopic images: a multicenter, observational study
title_fullStr Postoperative outcome analysis of chronic rhinosinusitis using transfer learning with pre-trained foundation models based on endoscopic images: a multicenter, observational study
title_full_unstemmed Postoperative outcome analysis of chronic rhinosinusitis using transfer learning with pre-trained foundation models based on endoscopic images: a multicenter, observational study
title_short Postoperative outcome analysis of chronic rhinosinusitis using transfer learning with pre-trained foundation models based on endoscopic images: a multicenter, observational study
title_sort postoperative outcome analysis of chronic rhinosinusitis using transfer learning with pre trained foundation models based on endoscopic images a multicenter observational study
topic Chronic rhinosinusitis
Surgical prognosis
Transfer learning
Pre-trained foundation model
url https://doi.org/10.1186/s12938-025-01428-y
work_keys_str_mv AT wentaogong postoperativeoutcomeanalysisofchronicrhinosinusitisusingtransferlearningwithpretrainedfoundationmodelsbasedonendoscopicimagesamulticenterobservationalstudy
AT keguangchen postoperativeoutcomeanalysisofchronicrhinosinusitisusingtransferlearningwithpretrainedfoundationmodelsbasedonendoscopicimagesamulticenterobservationalstudy
AT xiaochen postoperativeoutcomeanalysisofchronicrhinosinusitisusingtransferlearningwithpretrainedfoundationmodelsbasedonendoscopicimagesamulticenterobservationalstudy
AT xueliliu postoperativeoutcomeanalysisofchronicrhinosinusitisusingtransferlearningwithpretrainedfoundationmodelsbasedonendoscopicimagesamulticenterobservationalstudy
AT zhenli postoperativeoutcomeanalysisofchronicrhinosinusitisusingtransferlearningwithpretrainedfoundationmodelsbasedonendoscopicimagesamulticenterobservationalstudy
AT liwang postoperativeoutcomeanalysisofchronicrhinosinusitisusingtransferlearningwithpretrainedfoundationmodelsbasedonendoscopicimagesamulticenterobservationalstudy
AT yuxuanshi postoperativeoutcomeanalysisofchronicrhinosinusitisusingtransferlearningwithpretrainedfoundationmodelsbasedonendoscopicimagesamulticenterobservationalstudy
AT quanliu postoperativeoutcomeanalysisofchronicrhinosinusitisusingtransferlearningwithpretrainedfoundationmodelsbasedonendoscopicimagesamulticenterobservationalstudy
AT xicaisun postoperativeoutcomeanalysisofchronicrhinosinusitisusingtransferlearningwithpretrainedfoundationmodelsbasedonendoscopicimagesamulticenterobservationalstudy
AT xinshenghuang postoperativeoutcomeanalysisofchronicrhinosinusitisusingtransferlearningwithpretrainedfoundationmodelsbasedonendoscopicimagesamulticenterobservationalstudy
AT xuluo postoperativeoutcomeanalysisofchronicrhinosinusitisusingtransferlearningwithpretrainedfoundationmodelsbasedonendoscopicimagesamulticenterobservationalstudy
AT hongmengyu postoperativeoutcomeanalysisofchronicrhinosinusitisusingtransferlearningwithpretrainedfoundationmodelsbasedonendoscopicimagesamulticenterobservationalstudy