Deep Learning−Driven Exophthalmometry through Facial Photographs in Thyroid Eye Disease

Objective: To develop and evaluate a deep learning (DL)-assisted system for proptosis measurement using facial photographs in thyroid eye disease (TED). Design: A retrospective cohort study. Participants: This study included 1108 patients with TED from Severance Hospital (SH) and 171 from Seoul Nati...

Full description

Saved in:
Bibliographic Details
Main Authors: Joonhyeon Park, PhD, Jin Sook Yoon, MD, PhD, Namju Kim, MD, PhD, Kyubo Shin, PhD, Hyun Young Park, MD, PhD, Jongchan Kim, MS, Jaemin Park, MS, Jae Hoon Moon, MD, PhD, JaeSang Ko, MD, PhD
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Ophthalmology Science
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666914525000892
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850267968502497280
author Joonhyeon Park, PhD
Jin Sook Yoon, MD, PhD
Namju Kim, MD, PhD
Kyubo Shin, PhD
Hyun Young Park, MD, PhD
Jongchan Kim, MS
Jaemin Park, MS
Jae Hoon Moon, MD, PhD
JaeSang Ko, MD, PhD
author_facet Joonhyeon Park, PhD
Jin Sook Yoon, MD, PhD
Namju Kim, MD, PhD
Kyubo Shin, PhD
Hyun Young Park, MD, PhD
Jongchan Kim, MS
Jaemin Park, MS
Jae Hoon Moon, MD, PhD
JaeSang Ko, MD, PhD
author_sort Joonhyeon Park, PhD
collection DOAJ
description Objective: To develop and evaluate a deep learning (DL)-assisted system for proptosis measurement using facial photographs in thyroid eye disease (TED). Design: A retrospective cohort study. Participants: This study included 1108 patients with TED from Severance Hospital (SH) and 171 from Seoul National University Bundang Hospital (SNUBH). Methods: The DL-assisted system was trained using 1610 facial images paired with Hertel exophthalmometry measurements from SH and externally validated using 511 SNUBH images. The system employs a dual-stream ResNet-18 neural network, utilizing both red-green-blue images and depth maps generated by the ZoeDepth algorithm. Main Outcome Measures: Accuracy was assessed using mean absolute error (MAE), Pearson correlation coefficient, intraclass correlation coefficient (ICC), and area under the curve of the receiver operating characteristic curve. Results: The DL-assisted system achieved an MAE of 1.27 mm for the SH dataset and 1.24 mm for the SNUBH dataset. Pearson correlation coefficients were 0.82 and 0.77, respectively, with ICCs indicating strong reliability (0.80 for SH and 0.73 for SNUBH). The receiver operating characteristic curve analysis showed area under the curves of 0.91 for SH and 0.88 for SNUBH in detecting proptosis. The system detected significant proptosis changes (≥ 2 mm) with 74.6% accuracy. Conclusions: The DL-assisted system offers an accurate, accessible method for exophthalmometry in patients with TED using facial photographs. This tool presents a promising alternative to traditional exophthalmometry, potentially improving access to reliable proptosis measurement in both clinical and nonspecialist settings. Financial Disclosure(s): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
format Article
id doaj-art-54e059d218d34dc3a4e069c27ad43a72
institution OA Journals
issn 2666-9145
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Ophthalmology Science
spelling doaj-art-54e059d218d34dc3a4e069c27ad43a722025-08-20T01:53:35ZengElsevierOphthalmology Science2666-91452025-09-015510079110.1016/j.xops.2025.100791Deep Learning−Driven Exophthalmometry through Facial Photographs in Thyroid Eye DiseaseJoonhyeon Park, PhD0Jin Sook Yoon, MD, PhD1Namju Kim, MD, PhD2Kyubo Shin, PhD3Hyun Young Park, MD, PhD4Jongchan Kim, MS5Jaemin Park, MS6Jae Hoon Moon, MD, PhD7JaeSang Ko, MD, PhD8Division of Research & Development, THYROSCOPE Inc., Ulsan, Republic of KoreaDepartment of Ophthalmology, Severance Hospital, Institute of Vision Research, Yonsei University College of Medicine, Seoul, Republic of KoreaDepartment of Ophthalmology, Seoul National University Bundang Hospital and Seoul National University College of Medicine, Seongnam, Republic of KoreaDivision of Research & Development, THYROSCOPE Inc., Ulsan, Republic of KoreaDepartment of Ophthalmology, Severance Hospital, Institute of Vision Research, Yonsei University College of Medicine, Seoul, Republic of KoreaDivision of Research & Development, THYROSCOPE Inc., Ulsan, Republic of KoreaDivision of Research & Development, THYROSCOPE Inc., Ulsan, Republic of KoreaDivision of Research & Development, THYROSCOPE Inc., Ulsan, Republic of Korea; Department of Internal Medicine, Seoul National University Bundang Hospital and Seoul National University College of Medicine, Seongnam, Republic of Korea; Center for Artificial Intelligence in Healthcare, Seoul National University Bundang Hospital, Seongnam, Republic of Korea; Jae Hoon Moon, MD, PhD, Department of Internal Medicine, Seoul National University Bundang Hospital, Seoul National University College of Medicine 82, Gumi-ro 173 Beon-gil, Bundang-gu, Seongnam-si, Gyeonggi-do 13620, Republic of Korea.Division of Research & Development, THYROSCOPE Inc., Ulsan, Republic of Korea; Department of Ophthalmology, Severance Hospital, Institute of Vision Research, Yonsei University College of Medicine, Seoul, Republic of Korea; Correspondence: JaeSang Ko, MD, PhD, Department of Ophthalmology, Severance Hospital, Institute of Vision Research, Yonsei University College of Medicine, 50-1, Yonsei-ro, Seodaemun-gu, Seoul 03722, Republic of Korea.Objective: To develop and evaluate a deep learning (DL)-assisted system for proptosis measurement using facial photographs in thyroid eye disease (TED). Design: A retrospective cohort study. Participants: This study included 1108 patients with TED from Severance Hospital (SH) and 171 from Seoul National University Bundang Hospital (SNUBH). Methods: The DL-assisted system was trained using 1610 facial images paired with Hertel exophthalmometry measurements from SH and externally validated using 511 SNUBH images. The system employs a dual-stream ResNet-18 neural network, utilizing both red-green-blue images and depth maps generated by the ZoeDepth algorithm. Main Outcome Measures: Accuracy was assessed using mean absolute error (MAE), Pearson correlation coefficient, intraclass correlation coefficient (ICC), and area under the curve of the receiver operating characteristic curve. Results: The DL-assisted system achieved an MAE of 1.27 mm for the SH dataset and 1.24 mm for the SNUBH dataset. Pearson correlation coefficients were 0.82 and 0.77, respectively, with ICCs indicating strong reliability (0.80 for SH and 0.73 for SNUBH). The receiver operating characteristic curve analysis showed area under the curves of 0.91 for SH and 0.88 for SNUBH in detecting proptosis. The system detected significant proptosis changes (≥ 2 mm) with 74.6% accuracy. Conclusions: The DL-assisted system offers an accurate, accessible method for exophthalmometry in patients with TED using facial photographs. This tool presents a promising alternative to traditional exophthalmometry, potentially improving access to reliable proptosis measurement in both clinical and nonspecialist settings. Financial Disclosure(s): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.http://www.sciencedirect.com/science/article/pii/S2666914525000892Deep learningExophthalmometryThyroid eye diseaseProptosisDual-stream ResNet-18
spellingShingle Joonhyeon Park, PhD
Jin Sook Yoon, MD, PhD
Namju Kim, MD, PhD
Kyubo Shin, PhD
Hyun Young Park, MD, PhD
Jongchan Kim, MS
Jaemin Park, MS
Jae Hoon Moon, MD, PhD
JaeSang Ko, MD, PhD
Deep Learning−Driven Exophthalmometry through Facial Photographs in Thyroid Eye Disease
Ophthalmology Science
Deep learning
Exophthalmometry
Thyroid eye disease
Proptosis
Dual-stream ResNet-18
title Deep Learning−Driven Exophthalmometry through Facial Photographs in Thyroid Eye Disease
title_full Deep Learning−Driven Exophthalmometry through Facial Photographs in Thyroid Eye Disease
title_fullStr Deep Learning−Driven Exophthalmometry through Facial Photographs in Thyroid Eye Disease
title_full_unstemmed Deep Learning−Driven Exophthalmometry through Facial Photographs in Thyroid Eye Disease
title_short Deep Learning−Driven Exophthalmometry through Facial Photographs in Thyroid Eye Disease
title_sort deep learning driven exophthalmometry through facial photographs in thyroid eye disease
topic Deep learning
Exophthalmometry
Thyroid eye disease
Proptosis
Dual-stream ResNet-18
url http://www.sciencedirect.com/science/article/pii/S2666914525000892
work_keys_str_mv AT joonhyeonparkphd deeplearningdrivenexophthalmometrythroughfacialphotographsinthyroideyedisease
AT jinsookyoonmdphd deeplearningdrivenexophthalmometrythroughfacialphotographsinthyroideyedisease
AT namjukimmdphd deeplearningdrivenexophthalmometrythroughfacialphotographsinthyroideyedisease
AT kyuboshinphd deeplearningdrivenexophthalmometrythroughfacialphotographsinthyroideyedisease
AT hyunyoungparkmdphd deeplearningdrivenexophthalmometrythroughfacialphotographsinthyroideyedisease
AT jongchankimms deeplearningdrivenexophthalmometrythroughfacialphotographsinthyroideyedisease
AT jaeminparkms deeplearningdrivenexophthalmometrythroughfacialphotographsinthyroideyedisease
AT jaehoonmoonmdphd deeplearningdrivenexophthalmometrythroughfacialphotographsinthyroideyedisease
AT jaesangkomdphd deeplearningdrivenexophthalmometrythroughfacialphotographsinthyroideyedisease