Back to Authors

Cohen, Salomon Y.

https://orcid.org/0000-0003-1181-4379

Mayo Clinic

Centre Ophtalmologique d'Imagerie et de Laser

Citations 5

Artificial Intelligence‐Based Detection of Central Retinal Artery Occlusion Within 4.5 Hours on Standard Fundus Photographs
Gungor, Ayse , Sarbout, Ilias , Gilbert, Aubrey L. , Hamann, Steffen, Lebranchu, Pierre , Gohier, Philippe , Vignal‐Clermont, Catherine, Dumitrascu, Oana M. , Cohen, Salomon Y. , Lagrèze, Wolf A. , Heide, Frank van der, Lamirel, C. , Obadia, Michaël , Miléa, Dan , Gohier, Philippe , Dumitrascu, Oana M , Cohen, Salomon-Yves , Lagrèze, Wolf A , Feltgen, Nicolas , Lamirel, Cédric , Jonas, Jost B , Obadia, Michael , Racoceanu, Daniel , Milea, Dan , Hamann, Steffen , Hobeanu, Cristina , Heide, Frank C. T. van der

Journal of the American Heart Association | June 27, 2025 | Volume: 14 | Issue: 13 | Pages: No page available

10.1161/jaha.124.041441 Get It

Background Prompt diagnosis of acute central retinal artery occlusion (CRAO) is crucial for therapeutic management and stroke prevention. However, most stroke centers lack onsite ophthalmic expertise before considering fibrinolytic treatment. This study aimed to develop, train, and test a deep learning system to detect hyperacute CRAO on retinal fundus photographs within the critical 4.5‐hour treatment window and up to 24 hours after visual loss to aid in secondary stroke prevention. Methods Our retrospective, cross‐sectional study included 1322 color fundus photographs from 771 patients with acute visual loss due to CRAO, central retinal vein occlusion, nonarteritic anterior ischemic optic neuropathy, and healthy controls. Photographs were collected from 9 expert neuro‐ophthalmology centers in 6 countries, including 3 randomized clinical trials. Training included 1039 photographs (517 patients), followed by testing on 2 data sets: (1) hyperacute CRAO (54 photographs, 54 patients) and (2) CRAO within 24 hours after visual loss (110 photographs, 109 patients). Results The deep learning system achieved an area under the receiver operating characteristic curve of 0.96 (95% confidence interval (CI), 0.95–0.98), a sensitivity of 92.6% (95% CI, 87.0–98.0), and a specificity of 85.0% (95% CI, 81.8–92.8) for detecting CRAO at hyperacute stage, with similar results within 24 hours. The deep learning system outperformed stroke neurologists on a subset of hyperacute testing data set (120 photographs, 120 patients). Conclusions A deep learning system can accurately detect hyperacute CRAO on retinal photographs within a time window compatible with urgent fibrinolysis. If further validated, such systems could improve patient selection for fibrinolytic trials and optimize secondary stroke prevention. Registration URL: https://www.clinicaltrials.gov ; Unique identifier: NCT06390579.
Cerebellopontine Angle Malt Lymphoma
Cohen, Salomon Y. , Perry, Avital , Graffeo, Christopher S. , Link, Michael P., Carlstrom, Lucas P. , Link, Michael

Journal of Neurological Surgery Part B: Skull Base | March 6, 2019 | Volume: No volume available | Issue: No issue available | Pages: No page available

10.1055/s-0039-1679758 Get It

Where the Wild Things Are: An Expedition through the Cerebellopontine Angle
Graffeo, Christopher S. , Cohen, Salomon Y. , Perry, Avital , Rayan, Tarek, Link, Michael P., Carlstrom, Lucas P. , Link, Michael

Journal of Neurological Surgery Part B: Skull Base | March 6, 2019 | Volume: No volume available | Issue: No issue available | Pages: No page available

10.1055/s-0039-1679756 Get It

MULTIMODAL IMAGING OF CHOROIDAL AND OPTIC DISK VESSELS NEAR OPTIC DISK PITS
Adams, Matthew K., Cohen, Salomon Y. , Souied, Eric H., Goldenberg, Dafna, Olsen, Timothy W. , Pulido, José S. , Souied, Eric H. , Loewenstein, Anat

RETINAL Cases & Brief Reports | July 25, 2018 | Volume: 14 | Issue: 4 | Pages: 289-296

10.1097/icb.0000000000000765 Get It

Purpose: To describe modern multimodal imaging of the choroidal and optic disk vessels in optic disk pits. Methods: Case reports of four patients with optic disk pit who underwent multimodal imaging of the optic pit and surrounding structures. Patients included in this article were found to have optic disk pits and subsequently underwent multimodal imaging. Results: Cilioretinal arteries were present in two of the four cases (50%). SPECTRALIS optical coherence tomography showed intraretinal and subretinal fluid in all cases. Small vessels in the choroid and in the disk around the pit were also present in all cases through optical coherence tomographic angiography. Confocal fluorescein angiographic imaging in the first case showed leakage from the vessels adjacent to the optic disk pit. Conclusion: Modern multimodal imaging shows that there are anomalous vessels in and around an optic pit. Whether these vessels affect the development of optic pit, maculopathy needs to be further evaluated.
FOVEAL EXUDATE AND CHOROIDAL NEOVASCULARIZATION IN ATYPICAL CASES OF MULTIPLE EVANESCENT WHITE DOT SYNDROME
Chen, Kevin C. , Marsiglia, Marcela, Dolz‐Marco, Rosa , Zahid, Sarwar, Mrejen, Sarah , Pulido, José S. , Cohen, Salomon Y. , Freilich, Benjamin D, Yannuzzi, Lawrence A. , Freund, K. Bailey

Retina | January 17, 2017 | Volume: 37 | Issue: 11 | Pages: 2025-2034

10.1097/iae.0000000000001486 Get It

Purpose: To describe atypical cases of multiple evanescent white dot syndrome (MEWDS) associated with foveal exudation, increased choroidal thickness, and secondary Type 2 (subretinal) neovascularization. Methods: Four cases of atypical MEWDS were studied at a retina referral center. Patients underwent evaluation with multimodal retinal imaging, including fluorescein angiography, indocyanine green angiography, spectral-domain and enhanced depth imaging optical coherence tomography (OCT). Two patients were imaged with OCT angiography. Results: Four patients (3 female, 1 male) with a median age of 23.5 years presented with acute onset, painless, decreased central vision. All cases demonstrated fundus findings consistent with MEWDS on color photography, indocyanine green angiography, fluorescein angiography, fundus autofluorescence, and structural OCT imaging. On structural OCT, all 4 patients were noted to have hyperreflective subretinal material and increased subfoveal choroidal thickness ranging from 307 μm to 515 μm. Type 2 neovascularization was diagnosed in all four patients using fluorescein angiography, indocyanine green angiography, and/or OCT angiography. Two patients had poor visual acuity at the last follow-up despite resolution of characteristic clinical findings of MEWDS. Conclusion: A subset of patients with atypical MEWDS may develop persistent poor vision due to subfoveal exudation and secondary Type 2 neovascularization. Patients showing increased choroidal thickness at presentation may be more susceptible to this unusual presentation.