Clinical evaluation of deep learning systems for assisting in the diagnosis of the epiretinal membrane grade in general ophthalmologists
© 2023. The Author(s), under exclusive licence to The Royal College of Ophthalmologists..
BACKGROUND: Epiretinal membrane (ERM) is a common age-related retinal disease detected by optical coherence tomography (OCT), with a prevalence of 34.1% among people over 60 years old. This study aims to develop artificial intelligence (AI) systems to assist in the diagnosis of ERM grade using OCT images and to clinically evaluate the potential benefits and risks of our AI systems with a comparative experiment.
METHODS: A segmentation deep learning (DL) model that segments retinal features associated with ERM severity and a classification DL model that grades the severity of ERM were developed based on an OCT dataset obtained from three hospitals. A comparative experiment was conducted to compare the performance of four general ophthalmologists with and without assistance from the AI in diagnosing ERM severity.
RESULTS: The segmentation network had a pixel accuracy (PA) of 0.980 and a mean intersection over union (MIoU) of 0.873, while the six-classification network had a total accuracy of 81.3%. The diagnostic accuracy scores of the four ophthalmologists increased with AI assistance from 81.7%, 80.7%, 78.0%, and 80.7% to 87.7%, 86.7%, 89.0%, and 91.3%, respectively, while the corresponding time expenditures were reduced. The specific results of the study as well as the misinterpretations of the AI systems were analysed.
CONCLUSION: Through our comparative experiment, the AI systems proved to be valuable references for medical diagnosis and demonstrated the potential to accelerate clinical workflows. Systematic efforts are needed to ensure the safe and rapid integration of AI systems into ophthalmic practice.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:38 |
---|---|
Enthalten in: |
Eye (London, England) - 38(2024), 4 vom: 06. März, Seite 730-736 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Yan, Yan [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Completed 11.03.2024 Date Revised 11.03.2024 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1038/s41433-023-02765-9 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM363412204 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM363412204 | ||
003 | DE-627 | ||
005 | 20240311231925.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1038/s41433-023-02765-9 |2 doi | |
028 | 5 | 2 | |a pubmed24n1323.xml |
035 | |a (DE-627)NLM363412204 | ||
035 | |a (NLM)37848677 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Yan, Yan |e verfasserin |4 aut | |
245 | 1 | 0 | |a Clinical evaluation of deep learning systems for assisting in the diagnosis of the epiretinal membrane grade in general ophthalmologists |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 11.03.2024 | ||
500 | |a Date Revised 11.03.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2023. The Author(s), under exclusive licence to The Royal College of Ophthalmologists. | ||
520 | |a BACKGROUND: Epiretinal membrane (ERM) is a common age-related retinal disease detected by optical coherence tomography (OCT), with a prevalence of 34.1% among people over 60 years old. This study aims to develop artificial intelligence (AI) systems to assist in the diagnosis of ERM grade using OCT images and to clinically evaluate the potential benefits and risks of our AI systems with a comparative experiment | ||
520 | |a METHODS: A segmentation deep learning (DL) model that segments retinal features associated with ERM severity and a classification DL model that grades the severity of ERM were developed based on an OCT dataset obtained from three hospitals. A comparative experiment was conducted to compare the performance of four general ophthalmologists with and without assistance from the AI in diagnosing ERM severity | ||
520 | |a RESULTS: The segmentation network had a pixel accuracy (PA) of 0.980 and a mean intersection over union (MIoU) of 0.873, while the six-classification network had a total accuracy of 81.3%. The diagnostic accuracy scores of the four ophthalmologists increased with AI assistance from 81.7%, 80.7%, 78.0%, and 80.7% to 87.7%, 86.7%, 89.0%, and 91.3%, respectively, while the corresponding time expenditures were reduced. The specific results of the study as well as the misinterpretations of the AI systems were analysed | ||
520 | |a CONCLUSION: Through our comparative experiment, the AI systems proved to be valuable references for medical diagnosis and demonstrated the potential to accelerate clinical workflows. Systematic efforts are needed to ensure the safe and rapid integration of AI systems into ophthalmic practice | ||
650 | 4 | |a Journal Article | |
700 | 1 | |a Huang, Xiaoling |e verfasserin |4 aut | |
700 | 1 | |a Jiang, Xiaoyu |e verfasserin |4 aut | |
700 | 1 | |a Gao, Zhiyuan |e verfasserin |4 aut | |
700 | 1 | |a Liu, Xindi |e verfasserin |4 aut | |
700 | 1 | |a Jin, Kai |e verfasserin |4 aut | |
700 | 1 | |a Ye, Juan |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Eye (London, England) |d 1995 |g 38(2024), 4 vom: 06. März, Seite 730-736 |w (DE-627)NLM012628646 |x 1476-5454 |7 nnns |
773 | 1 | 8 | |g volume:38 |g year:2024 |g number:4 |g day:06 |g month:03 |g pages:730-736 |
856 | 4 | 0 | |u http://dx.doi.org/10.1038/s41433-023-02765-9 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 38 |j 2024 |e 4 |b 06 |c 03 |h 730-736 |