Deep learning system for the auxiliary diagnosis of thyroid eye disease: evaluation of ocular inflammation, eyelid retraction, and eye movement disorder

ObjectiveThis study aims to construct a semantic segmentation-based auxiliary diagnostic model for thyroid eye disease (TED) focusing on eyelid retraction, eye movement disorders, ocular inflammation related to Clinical Activity Score (CAS), facilitating rapid and non-invasive diagnosis for suspecte...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu Han, Jun Xie, Xiaoyu Li, Xinying Xu, Bin Sun, Han Liu, Chunfang Yan
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Cell and Developmental Biology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fcell.2025.1609231/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849421888151879680
author Yu Han
Jun Xie
Xiaoyu Li
Xinying Xu
Bin Sun
Han Liu
Chunfang Yan
author_facet Yu Han
Jun Xie
Xiaoyu Li
Xinying Xu
Bin Sun
Han Liu
Chunfang Yan
author_sort Yu Han
collection DOAJ
description ObjectiveThis study aims to construct a semantic segmentation-based auxiliary diagnostic model for thyroid eye disease (TED) focusing on eyelid retraction, eye movement disorders, ocular inflammation related to Clinical Activity Score (CAS), facilitating rapid and non-invasive diagnosis for suspected TED patients and enhancing the efficiency of treatment and diagnosis.MethodsData were collected from 153 subjects exhibiting symptoms of eyelid retraction, eye movement disorders, and ocular inflammation related to CAS. After quality screening, datasets for the primary position (303 eyes), gaze positions (1,199 eyes), and a multi-label inflammatory classification dataset (272 eyes) were constructed. The constructed TBRM-Net adopts a dual-branch feature extraction and fusion strategy to extract inflammation features for multi-label classification and recognition; the constructed DSR-Net performs segmentation of ocular structures and has designed a quantitative diagnostic algorithm.ResultsThe semantic segmentation-based auxiliary diagnostic model for TED demonstrated a mean pixel accuracy (MPA) of 94.1% in the primary position dataset and 95.0% in the gaze positions dataset. The accuracy for diagnosing eye movement disorders, upper eyelid retraction, and lower eyelid retraction reached 85.4%, 95.1%, and 87.0%, respectively. The accuracy for Redness of Eyelids, Swelling of Eyelids, Redness of Conjunctiva, Swelling of Conjunctiva, and Swelling of Caruncle or Plica reaches 81.8%, 78.8%, 90.6%, 73.5%, and 83.9%, respectively, with an average accuracy of 81.7%. Segmenting and classifying images of structures affected by ocular inflammation can effectively exclude interfering features. The designed quantitative algorithm provides greater interpretability than existing studies, thereby validating the effectiveness of the diagnostic system.ConclusionThe deep learning-based auxiliary diagnostic model for TED established in this study exhibits high accuracy and interpretability in the diagnosis of ocular inflammation related to CAS, eyelid retraction, and eye movement disorders. It holds significant medical value in assisting doctors in formulating treatment plans and evaluating therapeutic effects.
format Article
id doaj-art-acfa7f8be8d446ddb00f519babbcb4c3
institution Kabale University
issn 2296-634X
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Cell and Developmental Biology
spelling doaj-art-acfa7f8be8d446ddb00f519babbcb4c32025-08-20T03:31:20ZengFrontiers Media S.A.Frontiers in Cell and Developmental Biology2296-634X2025-06-011310.3389/fcell.2025.16092311609231Deep learning system for the auxiliary diagnosis of thyroid eye disease: evaluation of ocular inflammation, eyelid retraction, and eye movement disorderYu Han0Jun Xie1Xiaoyu Li2Xinying Xu3Bin Sun4Han Liu5Chunfang Yan6College of Electronic Information Engineering, Taiyuan University of Technology, Jinzhong, Shanxi, ChinaCollege of Electronic Information Engineering, Taiyuan University of Technology, Jinzhong, Shanxi, ChinaCollege of Electronic Information Engineering, Taiyuan University of Technology, Jinzhong, Shanxi, ChinaCollege of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, Shanxi, ChinaDepartment of Orbital Diseases, Shanxi Eye Hospital Affiliated to Shanxi Medical University, Taiyuan, Shanxi, ChinaDepartment of Orbital Diseases, Shanxi Eye Hospital Affiliated to Shanxi Medical University, Taiyuan, Shanxi, ChinaDepartment of Orbital Diseases, Shanxi Eye Hospital Affiliated to Shanxi Medical University, Taiyuan, Shanxi, ChinaObjectiveThis study aims to construct a semantic segmentation-based auxiliary diagnostic model for thyroid eye disease (TED) focusing on eyelid retraction, eye movement disorders, ocular inflammation related to Clinical Activity Score (CAS), facilitating rapid and non-invasive diagnosis for suspected TED patients and enhancing the efficiency of treatment and diagnosis.MethodsData were collected from 153 subjects exhibiting symptoms of eyelid retraction, eye movement disorders, and ocular inflammation related to CAS. After quality screening, datasets for the primary position (303 eyes), gaze positions (1,199 eyes), and a multi-label inflammatory classification dataset (272 eyes) were constructed. The constructed TBRM-Net adopts a dual-branch feature extraction and fusion strategy to extract inflammation features for multi-label classification and recognition; the constructed DSR-Net performs segmentation of ocular structures and has designed a quantitative diagnostic algorithm.ResultsThe semantic segmentation-based auxiliary diagnostic model for TED demonstrated a mean pixel accuracy (MPA) of 94.1% in the primary position dataset and 95.0% in the gaze positions dataset. The accuracy for diagnosing eye movement disorders, upper eyelid retraction, and lower eyelid retraction reached 85.4%, 95.1%, and 87.0%, respectively. The accuracy for Redness of Eyelids, Swelling of Eyelids, Redness of Conjunctiva, Swelling of Conjunctiva, and Swelling of Caruncle or Plica reaches 81.8%, 78.8%, 90.6%, 73.5%, and 83.9%, respectively, with an average accuracy of 81.7%. Segmenting and classifying images of structures affected by ocular inflammation can effectively exclude interfering features. The designed quantitative algorithm provides greater interpretability than existing studies, thereby validating the effectiveness of the diagnostic system.ConclusionThe deep learning-based auxiliary diagnostic model for TED established in this study exhibits high accuracy and interpretability in the diagnosis of ocular inflammation related to CAS, eyelid retraction, and eye movement disorders. It holds significant medical value in assisting doctors in formulating treatment plans and evaluating therapeutic effects.https://www.frontiersin.org/articles/10.3389/fcell.2025.1609231/fullthyroid eye disease (TED)multi-label image classificationsemantic segmentationfeature extractionautomatic quantizationeye digital image dataset
spellingShingle Yu Han
Jun Xie
Xiaoyu Li
Xinying Xu
Bin Sun
Han Liu
Chunfang Yan
Deep learning system for the auxiliary diagnosis of thyroid eye disease: evaluation of ocular inflammation, eyelid retraction, and eye movement disorder
Frontiers in Cell and Developmental Biology
thyroid eye disease (TED)
multi-label image classification
semantic segmentation
feature extraction
automatic quantization
eye digital image dataset
title Deep learning system for the auxiliary diagnosis of thyroid eye disease: evaluation of ocular inflammation, eyelid retraction, and eye movement disorder
title_full Deep learning system for the auxiliary diagnosis of thyroid eye disease: evaluation of ocular inflammation, eyelid retraction, and eye movement disorder
title_fullStr Deep learning system for the auxiliary diagnosis of thyroid eye disease: evaluation of ocular inflammation, eyelid retraction, and eye movement disorder
title_full_unstemmed Deep learning system for the auxiliary diagnosis of thyroid eye disease: evaluation of ocular inflammation, eyelid retraction, and eye movement disorder
title_short Deep learning system for the auxiliary diagnosis of thyroid eye disease: evaluation of ocular inflammation, eyelid retraction, and eye movement disorder
title_sort deep learning system for the auxiliary diagnosis of thyroid eye disease evaluation of ocular inflammation eyelid retraction and eye movement disorder
topic thyroid eye disease (TED)
multi-label image classification
semantic segmentation
feature extraction
automatic quantization
eye digital image dataset
url https://www.frontiersin.org/articles/10.3389/fcell.2025.1609231/full
work_keys_str_mv AT yuhan deeplearningsystemfortheauxiliarydiagnosisofthyroideyediseaseevaluationofocularinflammationeyelidretractionandeyemovementdisorder
AT junxie deeplearningsystemfortheauxiliarydiagnosisofthyroideyediseaseevaluationofocularinflammationeyelidretractionandeyemovementdisorder
AT xiaoyuli deeplearningsystemfortheauxiliarydiagnosisofthyroideyediseaseevaluationofocularinflammationeyelidretractionandeyemovementdisorder
AT xinyingxu deeplearningsystemfortheauxiliarydiagnosisofthyroideyediseaseevaluationofocularinflammationeyelidretractionandeyemovementdisorder
AT binsun deeplearningsystemfortheauxiliarydiagnosisofthyroideyediseaseevaluationofocularinflammationeyelidretractionandeyemovementdisorder
AT hanliu deeplearningsystemfortheauxiliarydiagnosisofthyroideyediseaseevaluationofocularinflammationeyelidretractionandeyemovementdisorder
AT chunfangyan deeplearningsystemfortheauxiliarydiagnosisofthyroideyediseaseevaluationofocularinflammationeyelidretractionandeyemovementdisorder