Fully automated grading system for the evaluation of punctate epithelial erosions using deep neural networks
© Author(s) (or their employer(s)) 2023. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ..
PURPOSE: The goal was to develop a fully automated grading system for the evaluation of punctate epithelial erosions (PEEs) using deep neural networks.
METHODS: A fully automated system was developed to detect corneal position and grade staining severity given a corneal fluorescein staining image. The fully automated pipeline consists of the following three steps: a corneal segmentation model extracts corneal area; five image patches are cropped from the staining image based on the five subregions of extracted cornea; a staining grading model predicts a score for each image patch from 0 to 3, and automated grading score for the whole cornea is obtained from 0 to 15. Finally, the clinical grading scores annotated by three ophthalmologists were compared with automated grading scores.
RESULTS: For corneal segmentation, the segmentation model achieved an intersection over union of 0.937. For punctate staining grading, the grading model achieved a classification accuracy of 76.5% and an area under the receiver operating characteristic curve of 0.940 (95% CI 0.932 to 0.949). For the fully automated pipeline, Pearson's correlation coefficient between the clinical and automated grading scores was 0.908 (p<0.01). Bland-Altman analysis revealed 95% limits of agreement between the clinical and automated grading scores of between -4.125 and 3.720 (concordance correlation coefficient=0.904). The average time required for processing a single stained image during pipeline was 0.58 s.
CONCLUSION: A fully automated grading system was developed to evaluate PEEs. The grading results may serve as a reference for ophthalmologists in clinical trials and residency training procedures.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:107 |
---|---|
Enthalten in: |
The British journal of ophthalmology - 107(2023), 4 vom: 20. Apr., Seite 453-460 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Qu, Jing-Hao [VerfasserIn] |
---|
Links: |
---|
Themen: |
Cornea |
---|
Anmerkungen: |
Date Completed 24.03.2023 Date Revised 13.04.2023 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1136/bjophthalmol-2021-319755 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM332109674 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM332109674 | ||
003 | DE-627 | ||
005 | 20231225214922.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1136/bjophthalmol-2021-319755 |2 doi | |
028 | 5 | 2 | |a pubmed24n1106.xml |
035 | |a (DE-627)NLM332109674 | ||
035 | |a (NLM)34670751 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Qu, Jing-Hao |e verfasserin |4 aut | |
245 | 1 | 0 | |a Fully automated grading system for the evaluation of punctate epithelial erosions using deep neural networks |
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 Completed 24.03.2023 | ||
500 | |a Date Revised 13.04.2023 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © Author(s) (or their employer(s)) 2023. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ. | ||
520 | |a PURPOSE: The goal was to develop a fully automated grading system for the evaluation of punctate epithelial erosions (PEEs) using deep neural networks | ||
520 | |a METHODS: A fully automated system was developed to detect corneal position and grade staining severity given a corneal fluorescein staining image. The fully automated pipeline consists of the following three steps: a corneal segmentation model extracts corneal area; five image patches are cropped from the staining image based on the five subregions of extracted cornea; a staining grading model predicts a score for each image patch from 0 to 3, and automated grading score for the whole cornea is obtained from 0 to 15. Finally, the clinical grading scores annotated by three ophthalmologists were compared with automated grading scores | ||
520 | |a RESULTS: For corneal segmentation, the segmentation model achieved an intersection over union of 0.937. For punctate staining grading, the grading model achieved a classification accuracy of 76.5% and an area under the receiver operating characteristic curve of 0.940 (95% CI 0.932 to 0.949). For the fully automated pipeline, Pearson's correlation coefficient between the clinical and automated grading scores was 0.908 (p<0.01). Bland-Altman analysis revealed 95% limits of agreement between the clinical and automated grading scores of between -4.125 and 3.720 (concordance correlation coefficient=0.904). The average time required for processing a single stained image during pipeline was 0.58 s | ||
520 | |a CONCLUSION: A fully automated grading system was developed to evaluate PEEs. The grading results may serve as a reference for ophthalmologists in clinical trials and residency training procedures | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
650 | 4 | |a cornea | |
650 | 4 | |a imaging | |
650 | 7 | |a Fluorescein |2 NLM | |
650 | 7 | |a TPY09G7XIR |2 NLM | |
700 | 1 | |a Qin, Xiao-Ran |e verfasserin |4 aut | |
700 | 1 | |a Li, Chen-Di |e verfasserin |4 aut | |
700 | 1 | |a Peng, Rong-Mei |e verfasserin |4 aut | |
700 | 1 | |a Xiao, Ge-Ge |e verfasserin |4 aut | |
700 | 1 | |a Cheng, Jian |e verfasserin |4 aut | |
700 | 1 | |a Gu, Shao-Feng |e verfasserin |4 aut | |
700 | 1 | |a Wang, Hai-Kun |e verfasserin |4 aut | |
700 | 1 | |a Hong, Jing |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t The British journal of ophthalmology |d 1917 |g 107(2023), 4 vom: 20. Apr., Seite 453-460 |w (DE-627)NLM000087556 |x 1468-2079 |7 nnns |
773 | 1 | 8 | |g volume:107 |g year:2023 |g number:4 |g day:20 |g month:04 |g pages:453-460 |
856 | 4 | 0 | |u http://dx.doi.org/10.1136/bjophthalmol-2021-319755 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 107 |j 2023 |e 4 |b 20 |c 04 |h 453-460 |