A VR-based Automated Strabismus Diagnosis System with Progressive Semi-Supervised Learning

TY - JOUR

T1 - A VR-based Automated Strabismus Diagnosis System with Progressive Semi-Supervised Learning

AU - Qiu, Dehui

AU - Ma, Bowei

AU - Xiong, Ze

AU - Wang, Yuhao

AU - Deng, Liguo

AU - Zhou, Longfei

AU - Cao, Xiaojie

AU - Chen, Weiwei

AU - Wang, Yumeng

AU - Jiang, Meixia

AU - Fu, Jing

AU - Zhang, Fa

AU - Wan, Xiaohua

N1 - Publisher Copyright: © 2013 IEEE.

PY - 2026

Y1 - 2026

N2 - Strabismus is a prevalent ocular disorder that can impair visual development and cause psychological issues if not diagnosed early. Conventional clinical diagnosis primarily relies on the prism cover test (PCT), which is subjective, requires patient cooperation, and lacks standardization. Recent advances in virtual reality (VR) and deep learning offer promising solutions for automated and standardized diagnosis. However, practical deployment faces three key challenges: realistic VR simulation of clinical exams, addressing image degradation (reflections/occlusions) with limited annotated data, and precise quantification of ocular deviations. In this study, we propose a novel VR-based automated strabismus diagnosis system by leveraging semi-supervised deep learning, and introduce a new clinical dataset, TongRenD. The framework incorporates five standardized clinical examination scenarios within a VR environment to ensure diagnostic consistency. We introduce ProgNet: an uncertainty-guided progressive semi-supervised segmentation network that integrates a Prototype-based Feature Representation Module (PFRM) to enhance robustness against visual noise and distortions under limited annotations. A dedicated 3D deviation estimation algorithm further enables accurate strabismus classification and angular measurement. Extensive experiments on the TongRenD and TEyeD datasets demonstrate that ProgNet outperforms state-of-the-art methods in segmentation accuracy. Clinical validation confirms that our system achieves high consistency with expert assessments, providing a standardized, non-invasive, and reliable solution for strabismus diagnosis.

AB - Strabismus is a prevalent ocular disorder that can impair visual development and cause psychological issues if not diagnosed early. Conventional clinical diagnosis primarily relies on the prism cover test (PCT), which is subjective, requires patient cooperation, and lacks standardization. Recent advances in virtual reality (VR) and deep learning offer promising solutions for automated and standardized diagnosis. However, practical deployment faces three key challenges: realistic VR simulation of clinical exams, addressing image degradation (reflections/occlusions) with limited annotated data, and precise quantification of ocular deviations. In this study, we propose a novel VR-based automated strabismus diagnosis system by leveraging semi-supervised deep learning, and introduce a new clinical dataset, TongRenD. The framework incorporates five standardized clinical examination scenarios within a VR environment to ensure diagnostic consistency. We introduce ProgNet: an uncertainty-guided progressive semi-supervised segmentation network that integrates a Prototype-based Feature Representation Module (PFRM) to enhance robustness against visual noise and distortions under limited annotations. A dedicated 3D deviation estimation algorithm further enables accurate strabismus classification and angular measurement. Extensive experiments on the TongRenD and TEyeD datasets demonstrate that ProgNet outperforms state-of-the-art methods in segmentation accuracy. Clinical validation confirms that our system achieves high consistency with expert assessments, providing a standardized, non-invasive, and reliable solution for strabismus diagnosis.

KW - Ocular image segmentation

KW - Semi-supervised learning

KW - Strabismus diagnosis

KW - Virtual reality

UR - https://www.scopus.com/pages/publications/105034685008

U2 - 10.1109/JBHI.2026.3679532

DO - 10.1109/JBHI.2026.3679532

M3 - Article

AN - SCOPUS:105034685008

SN - 2168-2194

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

ER -