DeepQuality improves infant retinopathy screening
© 2023. Springer Nature Limited..
Image quality variation is a prominent cause of performance degradation for intelligent disease diagnostic models in clinical applications. Image quality issues are particularly prominent in infantile fundus photography due to poor patient cooperation, which poses a high risk of misdiagnosis. Here, we developed a deep learning-based image quality assessment and enhancement system (DeepQuality) for infantile fundus images to improve infant retinopathy screening. DeepQuality can accurately detect various quality defects concerning integrity, illumination, and clarity with area under the curve (AUC) values ranging from 0.933 to 0.995. It can also comprehensively score the overall quality of each fundus photograph. By analyzing 2,015,758 infantile fundus photographs from real-world settings using DeepQuality, we found that 58.3% of them had varying degrees of quality defects, and large variations were observed among different regions and categories of hospitals. Additionally, DeepQuality provides quality enhancement based on the results of quality assessment. After quality enhancement, the performance of retinopathy of prematurity (ROP) diagnosis of clinicians was significantly improved. Moreover, the integration of DeepQuality and AI diagnostic models can effectively improve the model performance for detecting ROP. This study may be an important reference for the future development of other image-based intelligent disease screening systems.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:6 |
---|---|
Enthalten in: |
NPJ digital medicine - 6(2023), 1 vom: 16. Okt., Seite 192 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Li, Longhui [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Revised 21.11.2023 published: Electronic Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.1038/s41746-023-00943-3 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM363380388 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM363380388 | ||
003 | DE-627 | ||
005 | 20231226093226.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1038/s41746-023-00943-3 |2 doi | |
028 | 5 | 2 | |a pubmed24n1211.xml |
035 | |a (DE-627)NLM363380388 | ||
035 | |a (NLM)37845275 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Li, Longhui |e verfasserin |4 aut | |
245 | 1 | 0 | |a DeepQuality improves infant retinopathy screening |
264 | 1 | |c 2023 | |
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 21.11.2023 | ||
500 | |a published: Electronic | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a © 2023. Springer Nature Limited. | ||
520 | |a Image quality variation is a prominent cause of performance degradation for intelligent disease diagnostic models in clinical applications. Image quality issues are particularly prominent in infantile fundus photography due to poor patient cooperation, which poses a high risk of misdiagnosis. Here, we developed a deep learning-based image quality assessment and enhancement system (DeepQuality) for infantile fundus images to improve infant retinopathy screening. DeepQuality can accurately detect various quality defects concerning integrity, illumination, and clarity with area under the curve (AUC) values ranging from 0.933 to 0.995. It can also comprehensively score the overall quality of each fundus photograph. By analyzing 2,015,758 infantile fundus photographs from real-world settings using DeepQuality, we found that 58.3% of them had varying degrees of quality defects, and large variations were observed among different regions and categories of hospitals. Additionally, DeepQuality provides quality enhancement based on the results of quality assessment. After quality enhancement, the performance of retinopathy of prematurity (ROP) diagnosis of clinicians was significantly improved. Moreover, the integration of DeepQuality and AI diagnostic models can effectively improve the model performance for detecting ROP. This study may be an important reference for the future development of other image-based intelligent disease screening systems | ||
650 | 4 | |a Journal Article | |
700 | 1 | |a Lin, Duoru |e verfasserin |4 aut | |
700 | 1 | |a Lin, Zhenzhe |e verfasserin |4 aut | |
700 | 1 | |a Li, Mingyuan |e verfasserin |4 aut | |
700 | 1 | |a Lian, Zhangkai |e verfasserin |4 aut | |
700 | 1 | |a Zhao, Lanqin |e verfasserin |4 aut | |
700 | 1 | |a Wu, Xiaohang |e verfasserin |4 aut | |
700 | 1 | |a Liu, Lixue |e verfasserin |4 aut | |
700 | 1 | |a Liu, Jiali |e verfasserin |4 aut | |
700 | 1 | |a Wei, Xiaoyue |e verfasserin |4 aut | |
700 | 1 | |a Luo, Mingjie |e verfasserin |4 aut | |
700 | 1 | |a Zeng, Danqi |e verfasserin |4 aut | |
700 | 1 | |a Yan, Anqi |e verfasserin |4 aut | |
700 | 1 | |a Iao, Wai Cheng |e verfasserin |4 aut | |
700 | 1 | |a Shang, Yuanjun |e verfasserin |4 aut | |
700 | 1 | |a Xu, Fabao |e verfasserin |4 aut | |
700 | 1 | |a Xiang, Wei |e verfasserin |4 aut | |
700 | 1 | |a He, Muchen |e verfasserin |4 aut | |
700 | 1 | |a Fu, Zhe |e verfasserin |4 aut | |
700 | 1 | |a Wang, Xueyu |e verfasserin |4 aut | |
700 | 1 | |a Deng, Yaru |e verfasserin |4 aut | |
700 | 1 | |a Fan, Xinyan |e verfasserin |4 aut | |
700 | 1 | |a Ye, Zhijun |e verfasserin |4 aut | |
700 | 1 | |a Wei, Meirong |e verfasserin |4 aut | |
700 | 1 | |a Zhang, Jianping |e verfasserin |4 aut | |
700 | 1 | |a Liu, Baohai |e verfasserin |4 aut | |
700 | 1 | |a Li, Jianqiao |e verfasserin |4 aut | |
700 | 1 | |a Ding, Xiaoyan |e verfasserin |4 aut | |
700 | 1 | |a Lin, Haotian |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t NPJ digital medicine |d 2018 |g 6(2023), 1 vom: 16. Okt., Seite 192 |w (DE-627)NLM293151253 |x 2398-6352 |7 nnns |
773 | 1 | 8 | |g volume:6 |g year:2023 |g number:1 |g day:16 |g month:10 |g pages:192 |
856 | 4 | 0 | |u http://dx.doi.org/10.1038/s41746-023-00943-3 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 6 |j 2023 |e 1 |b 16 |c 10 |h 192 |