1
|
Feo A, Stradiotto E, Sacconi R, Menean M, Querques G, Romano MR. Subretinal hyperreflective material in retinal and chorioretinal disorders: A comprehensive review. Surv Ophthalmol 2024; 69:362-377. [PMID: 38160737 DOI: 10.1016/j.survophthal.2023.10.013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/19/2023] [Revised: 09/25/2023] [Accepted: 10/03/2023] [Indexed: 01/03/2024]
Abstract
Subretinal hyperreflective material (SHRM) is a common and remarkable optical coherence tomography (OCT) biomarker whose importance is emerging in several retinal and chorioretinal diseases, including age-related macular degeneration, central serous chorioretinopathy, polypoidal choroidal vasculopathy, pathologic myopia, posterior uveitis, vitelliform lesions and macular dystrophies, and rarer disorders. Multimodal imaging, also thanks to the introduction of OCT angiography, allowed a deeper characterisation of SHRM components and its morphological changes after treatment, suggesting its usefulness in clinical practice. We discuss and summarize the nature, multimodal imaging characteristics, and prognostic and predictive significance of SHRM in the different retinal and choroidal disorders in which it has been described.
Collapse
Affiliation(s)
- Alessandro Feo
- Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20072 Milan, Italy.
| | - Elisa Stradiotto
- Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20072 Milan, Italy.
| | - Riccardo Sacconi
- Department of Ophthalmology, University Vita-Salute, IRCCS Ospedale San Raffaele, Milan, Italy.
| | - Matteo Menean
- Department of Ophthalmology, University Vita-Salute, IRCCS Ospedale San Raffaele, Milan, Italy.
| | - Giuseppe Querques
- Department of Ophthalmology, University Vita-Salute, IRCCS Ospedale San Raffaele, Milan, Italy.
| | - Mario R Romano
- Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20072 Milan, Italy; Department of Ophthalmology, Eye Unit Humanitas Gavazzeni-Castelli, Via Mazzini 11, Bergamo, Italy.
| |
Collapse
|
2
|
Yang M, Han J, Park JI, Hwang JS, Han JM, Yoon J, Choi S, Hwang G, Hwang DDJ. Prediction of Visual Acuity in Pathologic Myopia with Myopic Choroidal Neovascularization Treated with Anti-Vascular Endothelial Growth Factor Using a Deep Neural Network Based on Optical Coherence Tomography Images. Biomedicines 2023; 11:2238. [PMID: 37626734 PMCID: PMC10452208 DOI: 10.3390/biomedicines11082238] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/16/2023] [Revised: 08/03/2023] [Accepted: 08/08/2023] [Indexed: 08/27/2023] Open
Abstract
Myopic choroidal neovascularization (mCNV) is a common cause of vision loss in patients with pathological myopia. However, predicting the visual prognosis of patients with mCNV remains challenging. This study aimed to develop an artificial intelligence (AI) model to predict visual acuity (VA) in patients with mCNV. This study included 279 patients with mCNV at baseline; patient data were collected, including optical coherence tomography (OCT) images, VA, and demographic information. Two models were developed: one comprising horizontal/vertical OCT images (H/V cuts) and the second comprising 25 volume scan images. The coefficient of determination (R2) and root mean square error (RMSE) were computed to evaluate the performance of the trained network. The models achieved high performance in predicting VA after 1 (R2 = 0.911, RMSE = 0.151), 2 (R2 = 0.894, RMSE = 0.254), and 3 (R2 = 0.891, RMSE = 0.227) years. Using multiple-volume scanning, OCT images enhanced the performance of the models relative to using only H/V cuts. This study proposes AI models to predict VA in patients with mCNV. The models achieved high performance by incorporating the baseline VA, OCT images, and post-injection data. This model could assist in predicting the visual prognosis and evaluating treatment outcomes in patients with mCNV undergoing intravitreal anti-vascular endothelial growth factor therapy.
Collapse
Affiliation(s)
- Migyeong Yang
- Department of Applied Artificial Intelligence, Sungkyunkwan University, Seoul 03603, Republic of Korea; (M.Y.); (J.H.); (J.Y.); (S.C.)
| | - Jinyoung Han
- Department of Applied Artificial Intelligence, Sungkyunkwan University, Seoul 03603, Republic of Korea; (M.Y.); (J.H.); (J.Y.); (S.C.)
- Department of Human-Artificial Intelligence Interaction, Sungkyunkwan University, Seoul 03603, Republic of Korea
| | - Ji In Park
- Department of Medicine, Kangwon National University Hospital, Kangwon National University School of Medicine, Chuncheon 24341, Gangwon-do, Republic of Korea;
| | | | - Jeong Mo Han
- Seoul Bombit Eye Clinic, Sejong 30127, Republic of Korea;
| | - Jeewoo Yoon
- Department of Applied Artificial Intelligence, Sungkyunkwan University, Seoul 03603, Republic of Korea; (M.Y.); (J.H.); (J.Y.); (S.C.)
- RAONDATA, Seoul 04615, Republic of Korea
| | - Seong Choi
- Department of Applied Artificial Intelligence, Sungkyunkwan University, Seoul 03603, Republic of Korea; (M.Y.); (J.H.); (J.Y.); (S.C.)
- RAONDATA, Seoul 04615, Republic of Korea
| | - Gyudeok Hwang
- Department of Ophthalmology, Hangil Eye Hospital, Incheon 21388, Republic of Korea;
| | - Daniel Duck-Jin Hwang
- Department of Ophthalmology, Hangil Eye Hospital, Incheon 21388, Republic of Korea;
- Department of Ophthalmology, Catholic Kwandong University College of Medicine, Incheon 22711, Republic of Korea
| |
Collapse
|