1
|
Mohammadzadeh V, Vepa A, Li C, Wu S, Chew L, Mahmoudinezhad G, Maltz E, Sahin S, Mylavarapu A, Edalati K, Martinyan J, Yalzadeh D, Scalzo F, Caprioli J, Nouri-Mahdavi K. Prediction of Central Visual Field Measures From Macular OCT Volume Scans With Deep Learning. Transl Vis Sci Technol 2023; 12:5. [PMID: 37917086 PMCID: PMC10627306 DOI: 10.1167/tvst.12.11.5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2023] [Accepted: 09/15/2023] [Indexed: 11/03/2023] Open
Abstract
Purpose Predict central 10° global and local visual field (VF) measurements from macular optical coherence tomography (OCT) volume scans with deep learning (DL). Methods This study included 1121 OCT volume scans and 10-2 VFs from 289 eyes (257 patients). Macular scans were used to estimate 10-2 VF mean deviation (MD), threshold sensitivities (TS), and total deviation (TD) values at 68 locations. A three-dimensional (3D) convolutional neural network based on the 3D DenseNet121 architecture was used for prediction. We compared DL predictions to those from baseline linear models. We carried out 10-fold stratified cross-validation to optimize generalizability. The performance of the DL and baseline models was compared based on correlations between ground truth and predicted VF measures and mean absolute error (MAE; ground truth - predicted values). Results Average (SD) MD was -9.3 (7.7) dB. Average (SD) correlations between predicted and ground truth MD and MD MAE were 0.74 (0.09) and 3.5 (0.4) dB, respectively. Estimation accuracy deteriorated with worsening MD. Average (SD) Pearson correlations between predicted and ground truth TS and MAEs for DL and baseline model were 0.71 (0.05) and 0.52 (0.05) (P < 0.001) and 6.5 (0.6) and 7.5 (0.5) dB (P < 0.001), respectively. For TD, correlation (SD) and MAE (SD) for DL and baseline models were 0.69 (0.02) and 0.48 (0.05) (P < 0.001) and 6.1 (0.5) and 7.8 (0.5) dB (P < 0.001), respectively. Conclusions Macular OCT volume scans can be used to predict global central VF parameters with clinically relevant accuracy. Translational Relevance Macular OCT imaging may be used to confirm and supplement central VF findings using deep learning.
Collapse
Affiliation(s)
- Vahid Mohammadzadeh
- Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA
| | - Arvind Vepa
- Department of Computer Science, University of California Los Angeles, Los Angeles, CA, USA
| | - Chuanlong Li
- Department of Neurology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA
| | - Sean Wu
- Department of Computer Science, Pepperdine University, Malibu, CA, USA
| | - Leila Chew
- Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA
| | - Golnoush Mahmoudinezhad
- Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA
| | - Evan Maltz
- Department of Chemistry and Biochemistry, University of California Los Angeles, Los Angeles, CA, USA
| | - Serhat Sahin
- Department of Computer Science, University of California Los Angeles, Los Angeles, CA, USA
| | - Apoorva Mylavarapu
- Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA
| | - Kiumars Edalati
- Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA
| | - Jack Martinyan
- Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA
| | - Dariush Yalzadeh
- Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA
| | - Fabien Scalzo
- Department of Computer Science, University of California Los Angeles, Los Angeles, CA, USA
| | - Joseph Caprioli
- Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA
| | - Kouros Nouri-Mahdavi
- Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA
| |
Collapse
|
2
|
Mylavarapu P, Gupta NE, Gudi V, Mylavarapu A, Daniels LB, Patel M. Diversity Within the Most Competitive Internal Medicine Fellowships: Examining Trends from 2008 to 2018. J Gen Intern Med 2020; 35:2537-2544. [PMID: 32666493 PMCID: PMC7459033 DOI: 10.1007/s11606-020-06008-5] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/06/2019] [Revised: 03/24/2020] [Accepted: 06/23/2020] [Indexed: 11/25/2022]
Abstract
BACKGROUND Prior studies have demonstrated the importance of diversity among physicians. Identifying trends in diversity within the most competitive internal medicine (IM) fellowships can guide focused efforts to address barriers to equal representation. OBJECTIVE To examine the racial and gender composition of resident applicants and accepted fellows to the top five most competitive IM specialties. DESIGN Survey data from the AAMC, JAMA, and NRMP were obtained. Fisher's exact tests were conducted to compare differences in representation between fellows in the most competitive specialties, resident applicants into those specialties, and categorical IM residents. Linear regression was used to analyze trends within each group. PARTICIPANTS Categorical IM residents and fellows at ACGME-accredited M.D. programs in the USA. MAIN MEASURES Proportion of each population by gender and race/ethnicity KEY RESULTS: Women saw an increase in representation among accepted fellows to the most competitive IM fellowships from 2008 to 2013 (+ 4.4%, p < 0.011), but the trend has since plateaued at a level (34%) significantly lower than their representation among IM residents (43%, p < 0.001). Black representation among accepted fellows (4.6%) has been increasing from 2008 to 2018 (+ 1.2%, p = 0.001), but is still significantly lower than their representation among IM residents (5.6%, p < 0.001). Hispanic resident applicant and fellow representation have seen minimal change. CONCLUSION Despite trends towards better representation among women and underrepresented minorities (URMs) among fellows in the most competitive IM specialties from 2008 to 2013, there has been a stagnation in both gender and racial diversity over the past 5 years. Further efforts must be undertaken to address barriers to entry and advocate for better representation of women and URMs in fellowship programs.
Collapse
Affiliation(s)
| | | | - Varun Gudi
- St. George's University, St. George's, Grenada
| | - Apoorva Mylavarapu
- David Geffen School of Medicine, University of California, Los Angeles, CA, USA
| | - Lori B Daniels
- Department of Cardiology, University of California, San Diego, CA, USA
| | - Mitul Patel
- Department of Cardiology, University of California, San Diego, CA, USA
| |
Collapse
|
3
|
Mahmoudinezhad G, Mohammadzadeh V, Amini N, Toriz V, Pourhomayoun M, Heydarzadeh S, Mylavarapu A, Morales E, Caprioli J, Nouri-Mahdavi K. Local Macular Thickness Relationships between 2 OCT Devices. Ophthalmol Glaucoma 2020; 4:209-215. [PMID: 32866692 DOI: 10.1016/j.ogla.2020.08.012] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/07/2020] [Revised: 08/07/2020] [Accepted: 08/24/2020] [Indexed: 02/07/2023]
Abstract
PURPOSE To compare local ganglion cell-inner plexiform layer (GCIPL) thickness measurements between 2 OCT devices and to explore factors that may influence the difference in measurements. DESIGN Cross-sectional study. PARTICIPANTS Sixty-nine glaucoma eyes (63 patients) with evidence of central damage or mean deviation (MD) of -6.0 dB or worse on a 24-2 visual field (VF). METHODS Cirrus and Spectralis OCT macular volume scans were exported, data from the central 20° of both OCT devices were centered and aligned, and 50 × 50 arrays of 0.4° × 0.4° superpixels were created. We estimated nonparametric (Spearman's) correlations and used Bland-Altman plots to compare GCIPL thickness measurements between the two OCTs at the superpixel level. Factors that may have influenced the differences between thickness measurements between the two devices were explored with linear mixed models. MAIN OUTCOME MEASURES Pooled and individual-eye Spearman's correlation and agreement between thickness measurements from the two devices. RESULTS The median 24-2 VF MD was -6.8 dB (interquartile range [IQR], -4.9 to -12.3 dB). The overall pooled Spearman's correlation between the two devices for all superpixels and eyes was 0.97 (P < 0.001). The median within-eye correlation coefficient was 0.72 (IQR, 0.59-0.79). Bland-Altman plots demonstrated a systematic bias in most individual eyes, with Spectralis GCIPL measurements becoming larger than Cirrus measurements with increasing superpixel thickness. The average superpixel thickness and distance to the fovea influenced the thickness difference between the two devices in multivariate models (P < 0.001). CONCLUSIONS Local macular thickness measurements from the Spectralis and Cirrus devices are highly correlated, but not interchangeable. Differences in thickness measurements between the two devices are influenced by the location of superpixels and their thickness.
Collapse
Affiliation(s)
- Golnoush Mahmoudinezhad
- Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California at Los Angeles, Los Angeles, California
| | - Vahid Mohammadzadeh
- Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California at Los Angeles, Los Angeles, California
| | - Navid Amini
- Department of Computer Science, California State University, Los Angeles, California
| | - Veronica Toriz
- Department of Computer Science, California State University, Los Angeles, California
| | - Mohammad Pourhomayoun
- Department of Computer Science, California State University, Los Angeles, California
| | - Sepideh Heydarzadeh
- Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California at Los Angeles, Los Angeles, California
| | - Apoorva Mylavarapu
- Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California at Los Angeles, Los Angeles, California
| | - Esteban Morales
- Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California at Los Angeles, Los Angeles, California
| | - Joseph Caprioli
- Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California at Los Angeles, Los Angeles, California
| | - Kouros Nouri-Mahdavi
- Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California at Los Angeles, Los Angeles, California.
| |
Collapse
|
4
|
Lazaro MT, Taxidis J, Shuman T, Bachmutsky I, Ikrar T, Santos R, Marcello GM, Mylavarapu A, Chandra S, Foreman A, Goli R, Tran D, Sharma N, Azhdam M, Dong H, Choe KY, Peñagarikano O, Masmanidis SC, Rácz B, Xu X, Geschwind DH, Golshani P. Reduced Prefrontal Synaptic Connectivity and Disturbed Oscillatory Population Dynamics in the CNTNAP2 Model of Autism. Cell Rep 2019; 27:2567-2578.e6. [PMID: 31141683 PMCID: PMC6553483 DOI: 10.1016/j.celrep.2019.05.006] [Citation(s) in RCA: 63] [Impact Index Per Article: 12.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2018] [Revised: 02/20/2019] [Accepted: 04/30/2019] [Indexed: 11/25/2022] Open
Abstract
Loss-of-function mutations in CNTNAP2 cause a syndromic form of autism spectrum disorder in humans and produce social deficits, repetitive behaviors, and seizures in mice. However, the functional effects of these mutations at cellular and circuit levels remain elusive. Using laser-scanning photostimulation, whole-cell recordings, and electron microscopy, we found a dramatic decrease in excitatory and inhibitory synaptic inputs onto L2/3 pyramidal neurons of the medial prefrontal cortex (mPFC) of Cntnap2 knockout (KO) mice, concurrent with reduced spines and synapses, despite normal dendritic complexity and intrinsic excitability. Moreover, recording of mPFC local field potentials (LFPs) and unit spiking in vivo revealed increased activity in inhibitory neurons, reduced phase-locking to delta and theta oscillations, and delayed phase preference during locomotion. Excitatory neurons showed similar phase modulation changes at delta frequencies. Finally, pairwise correlations increased during immobility in KO mice. Thus, reduced synaptic inputs can yield perturbed temporal coordination of neuronal firing in cortical ensembles.
Collapse
Affiliation(s)
- Maria T Lazaro
- Interdepartmental Program for Neuroscience, UCLA, Los Angeles, CA, USA; Center for Neurobehavioral Genetics, Semel Institute, UCLA, Los Angeles, CA, USA; Department of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USA
| | - Jiannis Taxidis
- Department of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USA; Integrative Center for Learning and Memory, Brain Research Institute, UCLA, Los Angeles, CA, USA
| | - Tristan Shuman
- Department of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USA; Integrative Center for Learning and Memory, Brain Research Institute, UCLA, Los Angeles, CA, USA; Department of Neuroscience, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Iris Bachmutsky
- Department of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USA
| | - Taruna Ikrar
- Department of Anatomy and Neurobiology, UC Irvine, Irvine, CA, USA
| | - Rommel Santos
- Department of Anatomy and Neurobiology, UC Irvine, Irvine, CA, USA
| | - G Mark Marcello
- Department of Anatomy and Histology, University of Veterinary Medicine, Budapest, Hungary
| | - Apoorva Mylavarapu
- Department of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USA
| | - Swasty Chandra
- Department of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USA
| | - Allison Foreman
- Department of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USA
| | - Rachna Goli
- Department of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USA
| | - Duy Tran
- Department of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USA
| | - Nikhil Sharma
- Department of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USA
| | - Michelle Azhdam
- Department of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USA
| | - Hongmei Dong
- Department of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USA
| | - Katrina Y Choe
- Center for Neurobehavioral Genetics, Semel Institute, UCLA, Los Angeles, CA, USA
| | - Olga Peñagarikano
- Department of Pharmacology, School of Medicine, University of the Basque Country (UPV/EHU), Vizcaya, Spain; Centro de Investigación Biomédica en Red en Salud Mental (CIBERSAM), Madrid, Spain
| | - Sotiris C Masmanidis
- Integrative Center for Learning and Memory, Brain Research Institute, UCLA, Los Angeles, CA, USA
| | - Bence Rácz
- Department of Anatomy and Histology, University of Veterinary Medicine, Budapest, Hungary
| | - Xiangmin Xu
- Department of Anatomy and Neurobiology, UC Irvine, Irvine, CA, USA
| | - Daniel H Geschwind
- Center for Neurobehavioral Genetics, Semel Institute, UCLA, Los Angeles, CA, USA; Department of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USA; Center for Autism Research and Treatment, Semel Institute, UCLA, Los Angeles, CA, USA; Intellectual Development and Disabilities Research Center, UCLA, Los Angeles, CA, USA.
| | - Peyman Golshani
- Department of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USA; Integrative Center for Learning and Memory, Brain Research Institute, UCLA, Los Angeles, CA, USA; Intellectual Development and Disabilities Research Center, UCLA, Los Angeles, CA, USA; West Los Angeles VA Medical Center, Los Angeles, CA.
| |
Collapse
|