An Intelligent Diagnostic System for Thyroid-Associated Ophthalmopathy Based on Facial Images

Xiao Huang; Lie Ju; Jian Li; Linfeng He; Fei Tong; Siyu Liu; Pan Li; Yun Zhang; Xin Wang; Zhiwen Yang; Jianhao Xiong; Lin Wang; Xin Zhao; Wanji He; Yelin Huang; Zongyuan Ge; Xuan Yao; Weihua Yang; Ruili Wei

doi:10.3389/fmed.2022.920716

An Intelligent Diagnostic System for Thyroid-Associated Ophthalmopathy Based on Facial Images

Front Med (Lausanne). 2022 Jun 10:9:920716. doi: 10.3389/fmed.2022.920716. eCollection 2022.

Authors

Xiao Huang¹, Lie Ju^{2

3}, Jian Li¹, Linfeng He¹, Fei Tong¹, Siyu Liu^{1

4}, Pan Li¹, Yun Zhang¹, Xin Wang², Zhiwen Yang², Jianhao Xiong², Lin Wang², Xin Zhao², Wanji He², Yelin Huang², Zongyuan Ge^{2

3}, Xuan Yao², Weihua Yang⁵, Ruili Wei¹

Affiliations

¹ Department of Ophthalmology, Changzheng Hospital, Naval Medical University, Shanghai, China.
² Airdoc LLC, Beijing, China.
³ Faculty of Engineering, Monash University, Clayton, VIC, Australia.
⁴ Department of Ophthalmology, Naval Medical Center of the People's Liberation Army, Naval Medical University, Shanghai, China.
⁵ The Laboratory of Artificial Intelligence and Bigdata in Ophthalmology, The Affiliated Eye Hospital of Nanjing Medical University, Nanjing, China.

Abstract

Background: Thyroid-associated ophthalmopathy (TAO) is one of the most common orbital diseases that seriously threatens visual function and significantly affects patients' appearances, rendering them unable to work. This study established an intelligent diagnostic system for TAO based on facial images.

Methods: Patient images and data were obtained from medical records of patients with TAO who visited Shanghai Changzheng Hospital from 2013 to 2018. Eyelid retraction, ocular dyskinesia, conjunctival congestion, and other signs were noted on the images. Patients were classified according to the types, stages, and grades of TAO based on the diagnostic criteria. The diagnostic system consisted of multiple task-specific models.

Results: The intelligent diagnostic system accurately diagnosed TAO in three stages. The built-in models pre-processed the facial images and diagnosed multiple TAO signs, with average areas under the receiver operating characteristic curves exceeding 0.85 (F1 score >0.80).

Conclusion: The intelligent diagnostic system introduced in this study accurately identified several common signs of TAO.

Keywords: artificial intelligence; diagnosis; facial images; machine learning; medical data analysis; thyroid-associated ophthalmopathy.