Daniel Seknazi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Daniel Seknazi has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Alexandra Miere
Department of Ophthalmology, Centre Hospitalier Intercommunal de Créteil, Université Paris Est Créteil, Créteil, France; and
2 shared publications - Eric H. Souied
Service d'ophtalmologie, centre hospitalier intercommunal de Créteil, 40, avenue de Verdun, 94000 Créteil, France
2 shared publications - Francesca Amoroso
Department of Ophthalmology, Centre Hospitalier Intercommunal de Creteil, Creteil, France; and
2 shared publications - Arthur Kessler
EPISEN—ISBS, University Paris-Est Créteil, 94000 Créteil, France
1 shared publication - Carl-Joe Mehanna
Centre Hospitalier Intercommunal de Créteil
1 shared publication - Carlotta Pallone
Department of Ophthalmology, Centre Hospitalier Intercommunal de Créteil, University Paris-Est Créteil, 94000 Créteil, France
1 shared publication
Latest Publications
- Open Access
- 8 December 2021
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 10 (24) , 5742
Deep Learning to Distinguish ABCA4-Related Stargardt Disease from PRPH2-Related Pseudo-Stargardt Pattern Dystrophy
(1) Background: Recessive Stargardt disease (STGD1) and multifocal pattern dystrophy simulating Stargardt disease (“pseudo-Stargardt pattern dystrophy”, PSPD) share phenotypic similitudes, leading to a difficult clinical diagnosis. Our aim was to assess whether a deep learning classifier pretrained on fundus autofluorescence (FAF) images can assist in distinguishing ABCA4-related STGD1 from the PRPH2/RDS-related PSPD and to compare the performance with that of retinal specialists. (2) Methods: We trained a convolutional neural network (CNN) using 729 FAF images from normal patients or patients with inherited retinal diseases (IRDs). Transfer learning was then used to update the weights of a ResNet50V2 used to classify the 370 FAF images into STGD1 and PSPD. Retina specialists evaluated the same dataset. The performance of the CNN and that of retina specialists were compared in terms of accuracy, sensitivity, and precision. (3) Results: The CNN accuracy on the test dataset of 111 images was 0.882. The AUROC was 0.890, the precision was 0.883 and the sensitivity was 0.883. The accuracy for retina experts averaged 0.816, whereas for retina fellows it averaged 0.724. (4) Conclusions: This proof-of-concept study demonstrates that, even with small databases, a pretrained CNN is able to distinguish between STGD1 and PSPD with good accuracy.
- 8 December 2021
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 10 (24) , 5742
Open AccessDeep Learning to Distinguish ABCA4-Related Stargardt Disease from PRPH2-Related Pseudo-Stargardt Pattern Dystrophy
(1) Background: Recessive Stargardt disease (STGD1) and multifocal pattern dystrophy simulating Stargardt disease (“pseudo-Stargardt pattern dystrophy”, PSPD) share phenotypic similitudes, leading to a difficult clinical diagnosis. Our aim was to assess whether a deep learning classifier pretrained on fundus autofluorescence (FAF) images can assist in distinguishing ABCA4-related STGD1 from the PRPH2/RDS-related PSPD and to compare the performance with that of retinal specialists. (2) Methods: We trained a convolutional neural network (CNN) using 729 FAF images from normal patients or patients with inherited retinal diseases (IRDs). Transfer learning was then used to update the weights of a ResNet50V2 used to classify the 370 FAF images into STGD1 and PSPD. Retina specialists evaluated the same dataset. The performance of the CNN and that of retina specialists were compared in terms of accuracy, sensitivity, and precision. (3) Results: The CNN accuracy on the test dataset of 111 images was 0.882. The AUROC was 0.890, the precision was 0.883 and the sensitivity was 0.883. The accuracy for retina experts averaged 0.816, whereas for retina fellows it averaged 0.724. (4) Conclusions: This proof-of-concept study demonstrates that, even with small databases, a pretrained CNN is able to distinguish between STGD1 and PSPD with good accuracy.
- Open Access
- 20 May 2021
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 10 (10) , 2216
Secondary Sutureless Posterior Chamber Lens Implantation with Two Specifically Designed IOLs: Iris Claw Lens versus Sutureless Trans-Scleral Plugs Fixated Lens
Background. The management of patients with aphakia and/or lack of capsular support remains debated. The sutureless posterior chamber IOL (PCIOL) fixation is a very useful surgical option. The purpose of the study was to compare the early outcomes as well as post-operative best corrected visual acuity, refractive errors and complications of two different techniques of sutureless PCIOL secondary implantation. Methods. Patients who underwent secondary implantation from December 2019 to January 2021 in the Department of Ophthalmology of Creteil Hospital, and in the Granville Ophthalmology Center, were retrospectively included. Eyes implanted with the iris claw lens (Artisan Aphakia IOL model 205, Ophtec BV, Groningen, The Netherlands) were included in group 1, and eyes implanted with a newly developed sutureless trans-scleral plugs fixated lens (STSPFL, Carlevale lens, Soleko, Pontecorvo, Italy) were included in group 2. Results. Twenty-two eyes of 22 patients were enrolled in group 1, and twenty eyes of 20 patients in group 2. No difference was found in visual acuity between two groups (0.35 +/− 0.29 logmar for group 1 and 0.23 +/− 0.51 logmar for group 2) (p = 0.15) at mean post-operative follow up (6.19 +/− 3.44 months for group 1 and 6.42 +/− 3.96 months for group 2) (p = 0.13). Both the mean refractive error (MRE) and induced astigmatism (IA) were greater in group 1 compared to group 2, respectively: the MRE was 0.99 +/− 0.57 vs. 0.46 +/− 0.36 (p < 0.01), and IA was 1.72 +/− 0.96 vs. 0.72 +/− 0.52 (p < 0.01). Conclusions. No significant differences in terms of the recovery of visual acuity were found between the two groups. Group 2 (STPFL) gives better results in our sample due to less post-operative induced astigmatism and less refractive error.
- 20 May 2021
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 10 (10) , 2216
Open AccessSecondary Sutureless Posterior Chamber Lens Implantation with Two Specifically Designed IOLs: Iris Claw Lens versus Sutureless Trans-Scleral Plugs Fixated Lens
Background. The management of patients with aphakia and/or lack of capsular support remains debated. The sutureless posterior chamber IOL (PCIOL) fixation is a very useful surgical option. The purpose of the study was to compare the early outcomes as well as post-operative best corrected visual acuity, refractive errors and complications of two different techniques of sutureless PCIOL secondary implantation. Methods. Patients who underwent secondary implantation from December 2019 to January 2021 in the Department of Ophthalmology of Creteil Hospital, and in the Granville Ophthalmology Center, were retrospectively included. Eyes implanted with the iris claw lens (Artisan Aphakia IOL model 205, Ophtec BV, Groningen, The Netherlands) were included in group 1, and eyes implanted with a newly developed sutureless trans-scleral plugs fixated lens (STSPFL, Carlevale lens, Soleko, Pontecorvo, Italy) were included in group 2. Results. Twenty-two eyes of 22 patients were enrolled in group 1, and twenty eyes of 20 patients in group 2. No difference was found in visual acuity between two groups (0.35 +/− 0.29 logmar for group 1 and 0.23 +/− 0.51 logmar for group 2) (p = 0.15) at mean post-operative follow up (6.19 +/− 3.44 months for group 1 and 6.42 +/− 3.96 months for group 2) (p = 0.13). Both the mean refractive error (MRE) and induced astigmatism (IA) were greater in group 1 compared to group 2, respectively: the MRE was 0.99 +/− 0.57 vs. 0.46 +/− 0.36 (p < 0.01), and IA was 1.72 +/− 0.96 vs. 0.72 +/− 0.52 (p < 0.01). Conclusions. No significant differences in terms of the recovery of visual acuity were found between the two groups. Group 2 (STPFL) gives better results in our sample due to less post-operative induced astigmatism and less refractive error.