A Deep Learning Model for Screening Computed Tomography Imaging for Thyroid Eye Disease and Compressive Optic Neuropathy
Purpose: Thyroid eye disease (TED) is an autoimmune condition with an array of clinical manifestations, which can be complicated by compressive optic neuropathy. It is important to identify patients with TED early to ensure close monitoring and treatment to prevent potential permanent disability or...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-01-01
|
Series: | Ophthalmology Science |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2666914523001446 |
_version_ | 1797615893982740480 |
---|---|
author | Lisa Y. Lin, MD, MBE Paul Zhou, MD, MS Min Shi, PhD Jonathan E. Lu, MD Soomin Jeon, PhD Doyun Kim, PhD Josephine M. Liu Mengyu Wang, PhD Synho Do, MS, PhD Nahyoung Grace Lee, MD |
author_facet | Lisa Y. Lin, MD, MBE Paul Zhou, MD, MS Min Shi, PhD Jonathan E. Lu, MD Soomin Jeon, PhD Doyun Kim, PhD Josephine M. Liu Mengyu Wang, PhD Synho Do, MS, PhD Nahyoung Grace Lee, MD |
author_sort | Lisa Y. Lin, MD, MBE |
collection | DOAJ |
description | Purpose: Thyroid eye disease (TED) is an autoimmune condition with an array of clinical manifestations, which can be complicated by compressive optic neuropathy. It is important to identify patients with TED early to ensure close monitoring and treatment to prevent potential permanent disability or vision loss. Deep learning artificial intelligence (AI) algorithms have been utilized in ophthalmology and in other fields of medicine to detect disease. This study aims to introduce a deep learning model to evaluate orbital computed tomography (CT) images for the presence of TED and potential compressive optic neuropathy. Design: Retrospective review and deep learning algorithm modeling. Subjects: Patients with TED with dedicated orbital CT scans and with an examination by an oculoplastic surgeon over a 10-year period at a single academic institution. Patients with no TED and normal CTs were used as normal controls. Those with other diagnoses, such as tumors or other inflammatory processes, were excluded. Methods: Orbital CTs were preprocessed and adopted for the Visual Geometry Group-16 network to distinguish patients with no TED, mild TED, and severe TED with compressive optic neuropathy. The primary model included training and testing of all 3 conditions. Binary model performance was also evaluated. An oculoplastic surgeon was also similarly tested with single and serial images for comparison. Main Outcome Measures: Accuracy of deep learning model discernment of region of interest for CT scans to distinguish TED versus normal control, as well as TED with clinical signs of optic neuropathy. Results: A total of 1187 photos from 141 patients were used to develop the AI model. The primary model trained on patients with no TED, mild TED, and severe TED had 89.5% accuracy (area under the curve: range, 0.96–0.99) in distinguishing patients with these clinical categories. In comparison, testing of an oculoplastic surgeon in these 3 categories showed decreased accuracy (70.0% accuracy in serial image testing). Conclusions: The deep learning model developed in the study can accurately detect TED and further detect TED with clinical signs of optic neuropathy based on orbital CT. The model proved superior compared with human expert grading. With further optimization and validation, this TED deep learning model could help guide frontline health care providers in the detection of TED and help stratify the urgency of a referral to an oculoplastic surgeon and endocrinologist. Financial Disclosure(s): The authors have no proprietary or commercial interest in any materials discussed in this article. |
first_indexed | 2024-03-11T07:33:26Z |
format | Article |
id | doaj.art-f3cf8df84f2b4ca8a75a7eb656feedcd |
institution | Directory Open Access Journal |
issn | 2666-9145 |
language | English |
last_indexed | 2024-03-11T07:33:26Z |
publishDate | 2024-01-01 |
publisher | Elsevier |
record_format | Article |
series | Ophthalmology Science |
spelling | doaj.art-f3cf8df84f2b4ca8a75a7eb656feedcd2023-11-17T05:28:32ZengElsevierOphthalmology Science2666-91452024-01-0141100412A Deep Learning Model for Screening Computed Tomography Imaging for Thyroid Eye Disease and Compressive Optic NeuropathyLisa Y. Lin, MD, MBE0Paul Zhou, MD, MS1Min Shi, PhD2Jonathan E. Lu, MD3Soomin Jeon, PhD4Doyun Kim, PhD5Josephine M. Liu6Mengyu Wang, PhD7Synho Do, MS, PhD8Nahyoung Grace Lee, MD9Department of Ophthalmology, Ophthalmic Plastic Surgery Service, Massachusetts Eye and Ear, Harvard Medical School, Boston, MassachusettsDepartment of Ophthalmology, Gavin Herbert Eye Institute, University of California Irvine, Irvine, CaliforniaHarvard Ophthalmology AI Lab, Schepens Eye Research Institute of Massachusetts Eye and Ear, Harvard Medical School, Boston, MassachusettsDepartment of Ophthalmology, Ophthalmic Plastic Surgery Service, Massachusetts Eye and Ear, Harvard Medical School, Boston, MassachusettsDepartment of Information Sciences and Mathematics, Dong-A University, Busan, Republic of KoreaData Science, Athenahealth, Watertown, MassachusettsDepartment of Radiology, Lab of Medical Imaging and Computation, Massachusetts General Brigham and Harvard Medical School, Boston, MassachusettsHarvard Ophthalmology AI Lab, Schepens Eye Research Institute of Massachusetts Eye and Ear, Harvard Medical School, Boston, MassachusettsDepartment of Radiology, Lab of Medical Imaging and Computation, Massachusetts General Brigham and Harvard Medical School, Boston, MassachusettsDepartment of Ophthalmology, Ophthalmic Plastic Surgery Service, Massachusetts Eye and Ear, Harvard Medical School, Boston, Massachusetts; Correspondence: Nahyoung Grace Lee, Massachusetts Eye and Ear Infirmary, 243 Charles St., 10th floor – Eye Plastics, Boston, MA 02114.Purpose: Thyroid eye disease (TED) is an autoimmune condition with an array of clinical manifestations, which can be complicated by compressive optic neuropathy. It is important to identify patients with TED early to ensure close monitoring and treatment to prevent potential permanent disability or vision loss. Deep learning artificial intelligence (AI) algorithms have been utilized in ophthalmology and in other fields of medicine to detect disease. This study aims to introduce a deep learning model to evaluate orbital computed tomography (CT) images for the presence of TED and potential compressive optic neuropathy. Design: Retrospective review and deep learning algorithm modeling. Subjects: Patients with TED with dedicated orbital CT scans and with an examination by an oculoplastic surgeon over a 10-year period at a single academic institution. Patients with no TED and normal CTs were used as normal controls. Those with other diagnoses, such as tumors or other inflammatory processes, were excluded. Methods: Orbital CTs were preprocessed and adopted for the Visual Geometry Group-16 network to distinguish patients with no TED, mild TED, and severe TED with compressive optic neuropathy. The primary model included training and testing of all 3 conditions. Binary model performance was also evaluated. An oculoplastic surgeon was also similarly tested with single and serial images for comparison. Main Outcome Measures: Accuracy of deep learning model discernment of region of interest for CT scans to distinguish TED versus normal control, as well as TED with clinical signs of optic neuropathy. Results: A total of 1187 photos from 141 patients were used to develop the AI model. The primary model trained on patients with no TED, mild TED, and severe TED had 89.5% accuracy (area under the curve: range, 0.96–0.99) in distinguishing patients with these clinical categories. In comparison, testing of an oculoplastic surgeon in these 3 categories showed decreased accuracy (70.0% accuracy in serial image testing). Conclusions: The deep learning model developed in the study can accurately detect TED and further detect TED with clinical signs of optic neuropathy based on orbital CT. The model proved superior compared with human expert grading. With further optimization and validation, this TED deep learning model could help guide frontline health care providers in the detection of TED and help stratify the urgency of a referral to an oculoplastic surgeon and endocrinologist. Financial Disclosure(s): The authors have no proprietary or commercial interest in any materials discussed in this article.http://www.sciencedirect.com/science/article/pii/S2666914523001446Artificial intelligenceCompressiveDeep learningOptic neuropathyThyroid eye disease |
spellingShingle | Lisa Y. Lin, MD, MBE Paul Zhou, MD, MS Min Shi, PhD Jonathan E. Lu, MD Soomin Jeon, PhD Doyun Kim, PhD Josephine M. Liu Mengyu Wang, PhD Synho Do, MS, PhD Nahyoung Grace Lee, MD A Deep Learning Model for Screening Computed Tomography Imaging for Thyroid Eye Disease and Compressive Optic Neuropathy Ophthalmology Science Artificial intelligence Compressive Deep learning Optic neuropathy Thyroid eye disease |
title | A Deep Learning Model for Screening Computed Tomography Imaging for Thyroid Eye Disease and Compressive Optic Neuropathy |
title_full | A Deep Learning Model for Screening Computed Tomography Imaging for Thyroid Eye Disease and Compressive Optic Neuropathy |
title_fullStr | A Deep Learning Model for Screening Computed Tomography Imaging for Thyroid Eye Disease and Compressive Optic Neuropathy |
title_full_unstemmed | A Deep Learning Model for Screening Computed Tomography Imaging for Thyroid Eye Disease and Compressive Optic Neuropathy |
title_short | A Deep Learning Model for Screening Computed Tomography Imaging for Thyroid Eye Disease and Compressive Optic Neuropathy |
title_sort | deep learning model for screening computed tomography imaging for thyroid eye disease and compressive optic neuropathy |
topic | Artificial intelligence Compressive Deep learning Optic neuropathy Thyroid eye disease |
url | http://www.sciencedirect.com/science/article/pii/S2666914523001446 |
work_keys_str_mv | AT lisaylinmdmbe adeeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT paulzhoumdms adeeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT minshiphd adeeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT jonathanelumd adeeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT soominjeonphd adeeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT doyunkimphd adeeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT josephinemliu adeeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT mengyuwangphd adeeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT synhodomsphd adeeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT nahyounggraceleemd adeeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT lisaylinmdmbe deeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT paulzhoumdms deeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT minshiphd deeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT jonathanelumd deeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT soominjeonphd deeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT doyunkimphd deeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT josephinemliu deeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT mengyuwangphd deeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT synhodomsphd deeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy AT nahyounggraceleemd deeplearningmodelforscreeningcomputedtomographyimagingforthyroideyediseaseandcompressiveopticneuropathy |