Domain Adaptation-Based Deep Learning Model for Forecasting and Diagnosis of Glaucoma Disease
The main factor causing irreversible blindness is glaucoma. Early detection greatly reduces the risk of further vision loss. To address this problem, we developed a domain adaptation-based deep learning model called Glaucoma Domain Adaptation (GDA) based on 66,742 fundus photographs collected from 3272 eyes of 1636 subjects. GDA learns domain-invariant and domain-specific representations to extract both general and specific features. We also developed a progressive weighting mechanism to accurately transfer the source domain knowledge while mitigating the transfer of negative knowledge from the source to the target domain. We employed low-rank coding for aligning the source and target distributions. We trained GDA based on three different scenarios including eyes annotated as glaucoma due to 1) optic disc abnormalities regardless of visual field abnormalities, 2) optic disc or visual field abnormalities except ones that are glaucoma due to both optic disc and visual field abnormalities at the same time, and 3) visual field abnormalities regardless of optic disc abnormalities We then evaluate the generalizability of GDA based on two independent datasets. The AUCs of GDA in forecasting glaucoma based on the first, second, and third scenarios were 0.90, 0.88, and 0.80 and the Accuracies were 0.82, 0.78, and 0.72, respectively. The AUCs of GDA in diagnosing glaucoma based on the first, second, and third scenarios were 0.98, 0.96, and 0.93 and the Accuracies were 0.93, 0.91, and 0.88, respectively. The proposed GDA model achieved high performance and generalizability for forecasting and diagnosis of glaucoma disease from fundus photographs. GDA may augment glaucoma research and clinical practice in identifying patients with glaucoma and forecasting those who may develop glaucoma thus preventing future vision loss.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:92 |
|---|---|
| Enthalten in: |
Biomedical signal processing and control - 92(2024) vom: 11. März |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Madadi, Yeganeh [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Deep learning |
|---|
| Anmerkungen: |
Date Revised 13.03.2024 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1016/j.bspc.2024.106061 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM369531671 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM369531671 | ||
| 003 | DE-627 | ||
| 005 | 20240313234710.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240311s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.bspc.2024.106061 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1326.xml |
| 035 | |a (DE-627)NLM369531671 | ||
| 035 | |a (NLM)38463435 | ||
| 035 | |a (PII)106061 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Madadi, Yeganeh |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Domain Adaptation-Based Deep Learning Model for Forecasting and Diagnosis of Glaucoma Disease |
| 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 Revised 13.03.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a The main factor causing irreversible blindness is glaucoma. Early detection greatly reduces the risk of further vision loss. To address this problem, we developed a domain adaptation-based deep learning model called Glaucoma Domain Adaptation (GDA) based on 66,742 fundus photographs collected from 3272 eyes of 1636 subjects. GDA learns domain-invariant and domain-specific representations to extract both general and specific features. We also developed a progressive weighting mechanism to accurately transfer the source domain knowledge while mitigating the transfer of negative knowledge from the source to the target domain. We employed low-rank coding for aligning the source and target distributions. We trained GDA based on three different scenarios including eyes annotated as glaucoma due to 1) optic disc abnormalities regardless of visual field abnormalities, 2) optic disc or visual field abnormalities except ones that are glaucoma due to both optic disc and visual field abnormalities at the same time, and 3) visual field abnormalities regardless of optic disc abnormalities We then evaluate the generalizability of GDA based on two independent datasets. The AUCs of GDA in forecasting glaucoma based on the first, second, and third scenarios were 0.90, 0.88, and 0.80 and the Accuracies were 0.82, 0.78, and 0.72, respectively. The AUCs of GDA in diagnosing glaucoma based on the first, second, and third scenarios were 0.98, 0.96, and 0.93 and the Accuracies were 0.93, 0.91, and 0.88, respectively. The proposed GDA model achieved high performance and generalizability for forecasting and diagnosis of glaucoma disease from fundus photographs. GDA may augment glaucoma research and clinical practice in identifying patients with glaucoma and forecasting those who may develop glaucoma thus preventing future vision loss | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Domain adaptation | |
| 650 | 4 | |a deep learning | |
| 650 | 4 | |a diagnosis | |
| 650 | 4 | |a forecasting | |
| 650 | 4 | |a glaucoma | |
| 650 | 4 | |a low-rank representation | |
| 700 | 1 | |a Abu-Serhan, Hashem |e verfasserin |4 aut | |
| 700 | 1 | |a Yousefi, Siamak |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Biomedical signal processing and control |d 2007 |g 92(2024) vom: 11. März |w (DE-627)NLM178615463 |x 1746-8094 |7 nnns |
| 773 | 1 | 8 | |g volume:92 |g year:2024 |g day:11 |g month:03 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.bspc.2024.106061 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 92 |j 2024 |b 11 |c 03 | ||