Han Yu, Xie Jun, Li Xiaoyu, Xu Xinying, Sun Bin, Liu Han, Yan Chunfang
College of Electronic Information Engineering, Taiyuan University of Technology, Jinzhong, Shanxi, China.
College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, Shanxi, China.
Front Cell Dev Biol. 2025 Jun 16;13:1609231. doi: 10.3389/fcell.2025.1609231. eCollection 2025.
This 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.
Data 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.
The 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.
The 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.
本研究旨在构建一种基于语义分割的甲状腺眼病（TED）辅助诊断模型，重点关注眼睑退缩、眼球运动障碍以及与临床活动评分（CAS）相关的眼部炎症，以促进对疑似TED患者的快速、非侵入性诊断，并提高治疗和诊断效率。
收集了153例表现出眼睑退缩、眼球运动障碍以及与CAS相关的眼部炎症症状的受试者的数据。经过质量筛选后，构建了主要位置（303只眼）、注视位置（1199只眼）的数据集以及多标签炎症分类数据集（272只眼）。构建的TBRM-Net采用双分支特征提取和融合策略来提取炎症特征以进行多标签分类和识别；构建的DSR-Net对眼部结构进行分割，并设计了一种定量诊断算法。
基于语义分割的TED辅助诊断模型在主要位置数据集上的平均像素准确率（MPA）为94.1%，在注视位置数据集上为95.0%。诊断眼球运动障碍、上睑退缩和下睑退缩的准确率分别达到85.4%、95.1%和87.0%。眼睑发红、眼睑肿胀、结膜发红、结膜肿胀以及泪阜或皱襞肿胀的诊断准确率分别达到81.8%、78.8%、90.6%、73.5%和83.9%，平均准确率为81.7%。对受眼部炎症影响的结构图像进行分割和分类可以有效排除干扰特征。所设计的定量算法比现有研究具有更高的可解释性，从而验证了诊断系统的有效性。
本研究建立的基于深度学习的TED辅助诊断模型在诊断与CAS相关的眼部炎症、眼睑退缩和眼球运动障碍方面具有较高的准确性和可解释性。它在协助医生制定治疗方案和评估治疗效果方面具有重要的医学价值。
