Souvick Mukherjee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Souvick Mukherjee has a total of 52 co-authors. Here are the top co-authors by number of shared publications:
- Tiarnan D. L. Keenan
Division of Epidemiology and Clinical Applications, National Eye Institute, National Institutes of Health, Bethesda, Maryland, USA
4 shared publications Emily Y. Chew
Division of Epidemiology and Clinical Applications, National Eye Institute, National Institutes of Health, Bethesda, Maryland
3 shared publicationsAkanksha Nagarkar
Division of Epidemiology and Clinical Applications, National Eye Institute, National Institutes of Health, Bethesda, Maryland
2 shared publicationsAlisa T Thavikulwat
Division of Epidemiology and Clinical Applications, National Eye Institute, Bethesda, MD, USA
2 shared publicationsCameron Duic
Division of Epidemiology and Clinical Applications, National Eye Institute, Bethesda, MD, USA
2 shared publications- Catherine A. Cukras
National Eye Institute, National Institutes of Health, Bethesda, Maryland, United States
2 shared publications
Latest Publications
- Open Access
- 1 October 2026
- Published by Taylor & Francis in Clinical Ophthalmology
- Vol. ume 20, 1-12
Macular Thickness and Associated Factors in African Immigrants: Insights from the Africans in America Study
Purpose: Normative optical coherence tomography (OCT) databases may not be generalizable to Africans, one of the fastest growing populations in the United States. Given the paucity of normative OCT data in Africans, we evaluated macular thickness in African immigrants. Patients and Methods: This cross-sectional study analyzed African-born participants enrolled in the Africans in America Study. They underwent history, physical, oral glucose tolerance tests, hemoglobin electrophoresis, and macular OCT (Cirrus HD-OCT). In the primary analysis, multivariable linear regression excluding eyes with retinopathy, glaucoma, or ocular hypertension was used to evaluate the association between the central subfield thickness (CST) and demographic, clinical, and metabolic factors. In the secondary analysis, multivariable analysis was used to evaluate the association between macular layer thicknesses and prediabetes status (prediabetes vs normal glucose tolerance). P values less than 0.05 and false discovery rate (FDR) within 10% were considered significant. Results: Six hundred forty-three eyes of 330 participants (60% male; mean age: 40 ± 11 years) were analyzed. The mean CST thickness for the cohort was 238.53 ± 21.48 μm. On average, women had a lower CST than men [− 10.51 μm, 95% confidence interval: (− 15.75, − 5.26), P < 0.001, FDR < 0.001]. No significant associations were found between prediabetes status and the thickness of any macular layer. Conclusion: These findings provide descriptive reference data on Cirrus-derived macular thickness measurements among African-born adults. Women had a lower CST, on average, than men. In contrast to prior studies, there was no difference in macular layer thicknesses between participants with prediabetes and those with normal glucose tolerance.
- 1 October 2026
- Published by Taylor & Francis in Clinical Ophthalmology
- Vol. ume 20, 1-12
Open AccessMacular Thickness and Associated Factors in African Immigrants: Insights from the Africans in America Study
Purpose: Normative optical coherence tomography (OCT) databases may not be generalizable to Africans, one of the fastest growing populations in the United States. Given the paucity of normative OCT data in Africans, we evaluated macular thickness in African immigrants. Patients and Methods: This cross-sectional study analyzed African-born participants enrolled in the Africans in America Study. They underwent history, physical, oral glucose tolerance tests, hemoglobin electrophoresis, and macular OCT (Cirrus HD-OCT). In the primary analysis, multivariable linear regression excluding eyes with retinopathy, glaucoma, or ocular hypertension was used to evaluate the association between the central subfield thickness (CST) and demographic, clinical, and metabolic factors. In the secondary analysis, multivariable analysis was used to evaluate the association between macular layer thicknesses and prediabetes status (prediabetes vs normal glucose tolerance). P values less than 0.05 and false discovery rate (FDR) within 10% were considered significant. Results: Six hundred forty-three eyes of 330 participants (60% male; mean age: 40 ± 11 years) were analyzed. The mean CST thickness for the cohort was 238.53 ± 21.48 μm. On average, women had a lower CST than men [− 10.51 μm, 95% confidence interval: (− 15.75, − 5.26), P < 0.001, FDR < 0.001]. No significant associations were found between prediabetes status and the thickness of any macular layer. Conclusion: These findings provide descriptive reference data on Cirrus-derived macular thickness measurements among African-born adults. Women had a lower CST, on average, than men. In contrast to prior studies, there was no difference in macular layer thicknesses between participants with prediabetes and those with normal glucose tolerance.
- Open Access
- 18 September 2026
- Published by Elsevier in Ophthalmology Retina
Association of Reticular Pseudodrusen Burden and Dark Adaptation in Nonadvanced Age-Related Macular Degeneration
- 18 September 2026
- Published by Elsevier in Ophthalmology Retina
Open AccessAssociation of Reticular Pseudodrusen Burden and Dark Adaptation in Nonadvanced Age-Related Macular Degeneration
- Open Access
- 12 February 2026
- Published by Elsevier in Ophthalmology Science
- Vol. 6 (4) , 101115
A Datasheet for the Age-Related Eye Disease Study (AREDS) on the database of Genotypes and Phenotypes
- 12 February 2026
- Published by Elsevier in Ophthalmology Science
- Vol. 6 (4) , 101115
Open AccessA Datasheet for the Age-Related Eye Disease Study (AREDS) on the database of Genotypes and Phenotypes
- Open Access
- 4 October 2025
- Published by Elsevier in Ophthalmology Science
- Vol. 6 (2) , 100953
A Datasheet for Age-Related Eye Disease Study 2 on the Database of Genotypes and Phenotypes
- 4 October 2025
- Published by Elsevier in Ophthalmology Science
- Vol. 6 (2) , 100953
Open AccessA Datasheet for Age-Related Eye Disease Study 2 on the Database of Genotypes and Phenotypes
- 11 September 2025
- Published by Elsevier in Ophthalmology Retina
- Vol. 10 (3) , 231-240
Risk Factors for 15-Letter Visual Acuity Loss from Geographic Atrophy Progression over 1 Year in the Age-Related Eye Disease Study 2
- 11 September 2025
- Published by Elsevier in Ophthalmology Retina
- Vol. 10 (3) , 231-240
Risk Factors for 15-Letter Visual Acuity Loss from Geographic Atrophy Progression over 1 Year in the Age-Related Eye Disease Study 2
- 23 July 2025
- Published by Springer Nature
- p. 121-135
Artificial Intelligence in Age-Related Macular Degeneration (AMD)
- 23 July 2025
- Published by Springer Nature
- p. 121-135
Artificial Intelligence in Age-Related Macular Degeneration (AMD)
- Open Access
- 4 December 2024
- Published by Elsevier in Ophthalmology Science
- Vol. 5 (3) , 100670
Validation of Deep Learning–Based Automatic Retinal Layer Segmentation Algorithms for Age-Related Macular Degeneration with 2 Spectral-Domain OCT Devices
- 4 December 2024
- Published by Elsevier in Ophthalmology Science
- Vol. 5 (3) , 100670
Open AccessValidation of Deep Learning–Based Automatic Retinal Layer Segmentation Algorithms for Age-Related Macular Degeneration with 2 Spectral-Domain OCT Devices
- 5 May 2022
- Published by Optica Publishing Group in Biomedical Optics Express
- Vol. 13 (6) , 3195-3210
Retinal layer segmentation in optical coherence tomography (OCT) using a 3D deep-convolutional regression network for patients with age-related macular degeneration
Introduction – Retinal layer segmentation in optical coherence tomography (OCT) images is an important approach for detecting and prognosing disease. Automating segmentation using robust machine learning techniques lead to computationally efficient solutions and significantly reduces the cost of labor-intensive labeling, which is traditionally performed by trained graders at a reading center, sometimes aided by semi-automated algorithms. Although several algorithms have been proposed since the revival of deep learning, eyes with severe pathological conditions continue to challenge fully automated segmentation approaches. There remains an opportunity to leverage the underlying spatial correlations between the retinal surfaces in the segmentation approach. Methods - Some of these proposed traditional methods can be expanded to utilize the three-dimensional spatial context governing the retinal image volumes by replacing the use of 2D filters with 3D filters. Towards this purpose, we propose a spatial-context, continuity and anatomical relationship preserving semantic segmentation algorithm, which utilizes the 3D spatial context from the image volumes with the use of 3D filters. We propose a 3D deep neural network capable of learning the surface positions of the layers in the retinal volumes. Results - We utilize a dataset of OCT images from patients with Age-related Macular Degeneration (AMD) to assess performance of our model and provide both qualitative (including segmentation maps and thickness maps) and quantitative (including error metric comparisons and volumetric comparisons) results, which demonstrate that our proposed method performs favorably even for eyes with pathological changes caused by severe retinal diseases. The Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) for patients with a wide range of AMD severity scores (0–11) were within 0.84±0.41 and 1.33±0.73 pixels, respectively, which are significantly better than some of the other state-of-the-art algorithms. Conclusion – The results demonstrate the utility of extracting features from the entire OCT volume by treating the volume as a correlated entity and show the benefit of utilizing 3D autoencoder based regression networks for smoothing the approximated retinal layers by inducing shape based regularization constraints.
- 5 May 2022
- Published by Optica Publishing Group in Biomedical Optics Express
- Vol. 13 (6) , 3195-3210
Retinal layer segmentation in optical coherence tomography (OCT) using a 3D deep-convolutional regression network for patients with age-related macular degeneration
Introduction – Retinal layer segmentation in optical coherence tomography (OCT) images is an important approach for detecting and prognosing disease. Automating segmentation using robust machine learning techniques lead to computationally efficient solutions and significantly reduces the cost of labor-intensive labeling, which is traditionally performed by trained graders at a reading center, sometimes aided by semi-automated algorithms. Although several algorithms have been proposed since the revival of deep learning, eyes with severe pathological conditions continue to challenge fully automated segmentation approaches. There remains an opportunity to leverage the underlying spatial correlations between the retinal surfaces in the segmentation approach. Methods - Some of these proposed traditional methods can be expanded to utilize the three-dimensional spatial context governing the retinal image volumes by replacing the use of 2D filters with 3D filters. Towards this purpose, we propose a spatial-context, continuity and anatomical relationship preserving semantic segmentation algorithm, which utilizes the 3D spatial context from the image volumes with the use of 3D filters. We propose a 3D deep neural network capable of learning the surface positions of the layers in the retinal volumes. Results - We utilize a dataset of OCT images from patients with Age-related Macular Degeneration (AMD) to assess performance of our model and provide both qualitative (including segmentation maps and thickness maps) and quantitative (including error metric comparisons and volumetric comparisons) results, which demonstrate that our proposed method performs favorably even for eyes with pathological changes caused by severe retinal diseases. The Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) for patients with a wide range of AMD severity scores (0–11) were within 0.84±0.41 and 1.33±0.73 pixels, respectively, which are significantly better than some of the other state-of-the-art algorithms. Conclusion – The results demonstrate the utility of extracting features from the entire OCT volume by treating the volume as a correlated entity and show the benefit of utilizing 3D autoencoder based regression networks for smoothing the approximated retinal layers by inducing shape based regularization constraints.