Deep Learning-Based Segmentation and Quantification of Retinal Capillary Non-Perfusion on Ultra-Wide-Field Retinal Fluorescein Angiography
Reliable outcome measures are required for clinical trials investigating novel agents for preventing progression of capillary non-perfusion (CNP) in retinal vascular diseases. Currently, accurate quantification of topographical distribution of CNP on ultrawide field fluorescein angiography (UWF-FA)...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/9/8/2537 |
| _version_ | 1797560079358099456 |
|---|---|
| author | Joan M. Nunez do Rio Piyali Sen Rajna Rasheed Akanksha Bagchi Luke Nicholson Adam M. Dubis Christos Bergeles Sobha Sivaprasad |
| author_facet | Joan M. Nunez do Rio Piyali Sen Rajna Rasheed Akanksha Bagchi Luke Nicholson Adam M. Dubis Christos Bergeles Sobha Sivaprasad |
| author_sort | Joan M. Nunez do Rio |
| collection | DOAJ |
| description | Reliable outcome measures are required for clinical trials investigating novel agents for preventing progression of capillary non-perfusion (CNP) in retinal vascular diseases. Currently, accurate quantification of topographical distribution of CNP on ultrawide field fluorescein angiography (UWF-FA) by retinal experts is subjective and lack standardisation. A U-net style network was trained to extract a dense segmentation of CNP from a newly created dataset of 75 UWF-FA images. A subset of 20 images was also segmented by a second expert grader for inter-grader reliability evaluation. Further, a circular grid centred on the FAZ was used to provide standardised CNP distribution analysis. The model for dense segmentation was five-fold cross-validated achieving area under the receiving operating characteristic of 0.82 (0.03) and area under precision-recall curve 0.73 (0.05). Inter-grader assessment on the 20 image subset achieves: precision 59.34 (10.92), recall 76.99 (12.5), and dice similarity coefficient (DSC) 65.51 (4.91), and the centred operating point of the automated model reached: precision 64.41 (13.66), recall 70.02 (16.2), and DSC 66.09 (13.32). Agreement of CNP grid assessment reached: Kappa 0.55 (0.03), perfused intraclass correlation (ICC) 0.89 (0.77, 0.93), non-perfused ICC 0.86 (0.73, 0.92), inter-grader agreement of CNP grid assessment values are Kappa 0.43 (0.03), perfused ICC 0.70 (0.48, 0.83), non-perfused ICC 0.71 (0.48, 0.83). Automated dense segmentation of CNP in UWF-FA images achieves performance levels comparable to inter-grader agreement values. A grid placed on the deep learning-based automatic segmentation of CNP generates a reliable and quantifiable method of measurement of CNP, to overcome the subjectivity of human graders. |
| first_indexed | 2024-03-10T17:54:22Z |
| format | Article |
| id | doaj.art-ea381429b2864d588c321f5ae694449b |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-10T17:54:22Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-ea381429b2864d588c321f5ae694449b2023-11-20T09:15:55ZengMDPI AGJournal of Clinical Medicine2077-03832020-08-0198253710.3390/jcm9082537Deep Learning-Based Segmentation and Quantification of Retinal Capillary Non-Perfusion on Ultra-Wide-Field Retinal Fluorescein AngiographyJoan M. Nunez do Rio0Piyali Sen1Rajna Rasheed2Akanksha Bagchi3Luke Nicholson4Adam M. Dubis5Christos Bergeles6Sobha Sivaprasad7Institute of Ophthalmology, University College London, London EC1V 9EL, UKInstitute of Ophthalmology, University College London, London EC1V 9EL, UKInstitute of Ophthalmology, University College London, London EC1V 9EL, UKNIHR Moorfields Biomedical Research Centre, Moorfields Eye Hospital, London EC1V 2PD, UKInstitute of Ophthalmology, University College London, London EC1V 9EL, UKInstitute of Ophthalmology, University College London, London EC1V 9EL, UKKing’s College London, School of Biomedical Engineering & Imaging Sciences, London SE1 7EU, UKInstitute of Ophthalmology, University College London, London EC1V 9EL, UKReliable outcome measures are required for clinical trials investigating novel agents for preventing progression of capillary non-perfusion (CNP) in retinal vascular diseases. Currently, accurate quantification of topographical distribution of CNP on ultrawide field fluorescein angiography (UWF-FA) by retinal experts is subjective and lack standardisation. A U-net style network was trained to extract a dense segmentation of CNP from a newly created dataset of 75 UWF-FA images. A subset of 20 images was also segmented by a second expert grader for inter-grader reliability evaluation. Further, a circular grid centred on the FAZ was used to provide standardised CNP distribution analysis. The model for dense segmentation was five-fold cross-validated achieving area under the receiving operating characteristic of 0.82 (0.03) and area under precision-recall curve 0.73 (0.05). Inter-grader assessment on the 20 image subset achieves: precision 59.34 (10.92), recall 76.99 (12.5), and dice similarity coefficient (DSC) 65.51 (4.91), and the centred operating point of the automated model reached: precision 64.41 (13.66), recall 70.02 (16.2), and DSC 66.09 (13.32). Agreement of CNP grid assessment reached: Kappa 0.55 (0.03), perfused intraclass correlation (ICC) 0.89 (0.77, 0.93), non-perfused ICC 0.86 (0.73, 0.92), inter-grader agreement of CNP grid assessment values are Kappa 0.43 (0.03), perfused ICC 0.70 (0.48, 0.83), non-perfused ICC 0.71 (0.48, 0.83). Automated dense segmentation of CNP in UWF-FA images achieves performance levels comparable to inter-grader agreement values. A grid placed on the deep learning-based automatic segmentation of CNP generates a reliable and quantifiable method of measurement of CNP, to overcome the subjectivity of human graders.https://www.mdpi.com/2077-0383/9/8/2537retinal non-perfusionfluorescein angiographyimage segmentation |
| spellingShingle | Joan M. Nunez do Rio Piyali Sen Rajna Rasheed Akanksha Bagchi Luke Nicholson Adam M. Dubis Christos Bergeles Sobha Sivaprasad Deep Learning-Based Segmentation and Quantification of Retinal Capillary Non-Perfusion on Ultra-Wide-Field Retinal Fluorescein Angiography Journal of Clinical Medicine retinal non-perfusion fluorescein angiography image segmentation |
| title | Deep Learning-Based Segmentation and Quantification of Retinal Capillary Non-Perfusion on Ultra-Wide-Field Retinal Fluorescein Angiography |
| title_full | Deep Learning-Based Segmentation and Quantification of Retinal Capillary Non-Perfusion on Ultra-Wide-Field Retinal Fluorescein Angiography |
| title_fullStr | Deep Learning-Based Segmentation and Quantification of Retinal Capillary Non-Perfusion on Ultra-Wide-Field Retinal Fluorescein Angiography |
| title_full_unstemmed | Deep Learning-Based Segmentation and Quantification of Retinal Capillary Non-Perfusion on Ultra-Wide-Field Retinal Fluorescein Angiography |
| title_short | Deep Learning-Based Segmentation and Quantification of Retinal Capillary Non-Perfusion on Ultra-Wide-Field Retinal Fluorescein Angiography |
| title_sort | deep learning based segmentation and quantification of retinal capillary non perfusion on ultra wide field retinal fluorescein angiography |
| topic | retinal non-perfusion fluorescein angiography image segmentation |
| url | https://www.mdpi.com/2077-0383/9/8/2537 |
| work_keys_str_mv | AT joanmnunezdorio deeplearningbasedsegmentationandquantificationofretinalcapillarynonperfusiononultrawidefieldretinalfluoresceinangiography AT piyalisen deeplearningbasedsegmentationandquantificationofretinalcapillarynonperfusiononultrawidefieldretinalfluoresceinangiography AT rajnarasheed deeplearningbasedsegmentationandquantificationofretinalcapillarynonperfusiononultrawidefieldretinalfluoresceinangiography AT akankshabagchi deeplearningbasedsegmentationandquantificationofretinalcapillarynonperfusiononultrawidefieldretinalfluoresceinangiography AT lukenicholson deeplearningbasedsegmentationandquantificationofretinalcapillarynonperfusiononultrawidefieldretinalfluoresceinangiography AT adammdubis deeplearningbasedsegmentationandquantificationofretinalcapillarynonperfusiononultrawidefieldretinalfluoresceinangiography AT christosbergeles deeplearningbasedsegmentationandquantificationofretinalcapillarynonperfusiononultrawidefieldretinalfluoresceinangiography AT sobhasivaprasad deeplearningbasedsegmentationandquantificationofretinalcapillarynonperfusiononultrawidefieldretinalfluoresceinangiography |