scholarly journals A Deep Learning Model for Automated Sub-Basal Corneal Nerve Segmentation and Evaluation Using In Vivo Confocal Microscopy

2020 ◽  
Vol 9 (2) ◽  
pp. 32
Author(s):  
Shanshan Wei ◽  
Faqiang Shi ◽  
Yuexin Wang ◽  
Yilin Chou ◽  
Xuemin Li
Keyword(s):  
Deep Learning ◽  
Confocal Microscopy ◽  
Learning Model ◽  
In Vivo Confocal Microscopy ◽  
Corneal Nerve ◽  
Deep Learning Model

Bilateral morphometric analysis of corneal sub-basal nerve plexus in patients undergoing unilateral cataract surgery: a preliminary in vivo confocal microscopy study

2020 ◽  
pp. bjophthalmol-2019-315449 ◽  
Author(s):  
Giuseppe Giannaccare ◽  
Federico Bernabei ◽  
Marco Pellegrini ◽  
Fabio Guaraldi ◽  
Federica Turchi ◽  
...  
Keyword(s):  
Confocal Microscopy ◽  
Cataract Surgery ◽  
Nerve Fibre ◽  
Fibre Length ◽  
Nerve Plexus ◽  
In Vivo Confocal Microscopy ◽  
Corneal Nerve ◽  
Branch Density ◽  
Unilateral Cataract

AimsTo evaluate bilateral morphometric changes of corneal sub-basal nerve plexus (CSNP) occurring after unilateral cataract surgery by in vivo confocal microscopy (IVCM) images analysed with automated software.MethodsIVCM was performed before (V0) and 1 month after surgery (V1) in both operated eyes (OEs) and unoperated eyes (UEs) of 30 patients. Thirty age and sex-matched subjects acted as controls. Corneal nerve fibre density (CNFD), corneal nerve branch density (CNBD), corneal nerve fibre length (CNFL), corneal nerve total branch density (CTBD), corneal nerve fibre area (CNFA), corneal nerve fibre width, corneal nerve fractal dimension (CNFrD) and dendritic cells density were calculated.ResultsMean CNFD, CNBD, CNFL, CTBD, CNFA and CNFrD significantly decreased at V1 versus V0 in both eyes (respectively, 15.35±7.00 vs 21.21±6.56 n/mm2 in OEs and 20.11±6.69 vs 23.20±7.26 in UEs; 13.57±12.16 vs 26.79±16.91 n/mm2 in OEs and 24.28±14.88 vs 29.76±15.25 in UEs; 9.67±3.44 mm/mm2 vs 13.49±3.42 in OEs and 12.53±3.60 vs 14.02±3.82 in UEs; 22.81±18.77 vs 42.25±24.64 n/mm2 in OEs and 38.06±20.52 vs 43.93±22.27 in UEs; 0.0040±0.0021 vs 0.0058±0.0020 mm2/mm2 in OEs and 0.0049±0.0016 vs 0.0057±0.0019 in UEs; 1.418±0.058 vs 1.470±0.037 in OEs and 1.466±0.040 vs 1.477±0.036 in UEs; always p<0.049).ConclusionPatients undergoing cataract surgery exhibit bilateral alterations of CSNP. This finding could have broad implications in the setting of sequential cataract surgery.

IN VIVO CONFOCAL MICROSCOPY FOR STUDYING CORNEAL DISEASES/CONDITIONS ASSOCIATED WITH CORNEAL NERVE DAMAGE AND OCULAR SURFACE DISEASE.

Cornea ◽  
2000 ◽  
Vol 19 (Supplement 2) ◽  
pp. S131
Author(s):  
T Tervo ◽  
T U Valle ◽  
J AO Moilanen ◽  
M E Rosenberg ◽  
I SJ Tuominen ◽  
...  
Keyword(s):  
Confocal Microscopy ◽  
Ocular Surface ◽  
Nerve Damage ◽  
Ocular Surface Disease ◽  
In Vivo Confocal Microscopy ◽  
Corneal Nerve

scholarly journals Combining In Vivo Corneal Confocal Microscopy with Deep Learning-based Analysis Reveals Sensory Nerve Fiber Loss in Acute SIV Infection

2020 ◽  
Author(s):  
Megan E. McCarron ◽  
Rachel L. Weinberg ◽  
Jessica M. Izzi ◽  
Suzanne E. Queen ◽  
Stuti L. Misra ◽  
...  
Keyword(s):  
Fractal Dimension ◽  
Deep Learning ◽  
Confocal Microscopy ◽  
Nerve Fiber ◽  
Fiber Length ◽  
Sensory Nerve ◽  
Corneal Confocal Microscopy ◽  
Siv Infection ◽  
Corneal Nerve

AbstractPurposeTo characterize corneal subbasal nerve plexus morphologic features using in vivo corneal confocal microscopy (IVCM) in normal and SIV-infected macaques and to implement automated assessments using novel deep learning-based methods customized for macaque studies.MethodsIn vivo corneal confocal microscopy images were collected from both male and female age-matched specific-pathogen free rhesus and pigtailed macaques housed at the Johns Hopkins University breeding colony using the Heidelberg HRTIII with Rostock Corneal Module. We also obtained repeat IVCM images of 12 SIV-infected animals including pre-infection and 10 day post-SIV infection time-points. All IVCM images were analyzed using a novel deep convolutional neural network architecture developed specifically for macaque studies.ResultsDeep learning-based segmentation of subbasal nerves in IVCM images from macaques demonstrated that corneal nerve fiber length (CNFL) and fractal dimension measurements did not differ between species, but pigtailed macaques had significantly higher baseline corneal nerve fiber tortuosity than rhesus macaques (P = 0.005). Neither sex nor age of macaques was associated with differences in any of the assessed corneal subbasal nerve parameters. In the SIV/macaque model of HIV, acute SIV infection induced significant decreases in both corneal nerve fiber length and fractal dimension (P= 0.01 and P= 0.008 respectively).ConclusionsThe combination of IVCM and objective, robust, and rapid deep-learning analysis serves as a powerful noninvasive research and clinical tool to track sensory nerve damage, enabling early detection of neuropathy. Adapting the deep-learning analyses to human corneal nerve assessments will refine our ability to predict and monitor damage to small sensory nerve fibers in a number of clinical settings including HIV, multiple sclerosis, Parkinson’s disease, diabetes, and chemotherapeutic neurotoxicity.

scholarly journals Evaluation of Corneal Nerves and Dendritic Cells By in Vivo Confocal Microscopy After Descemet’s Membrane Keratoplasty For Bullous Keratopathy

2022 ◽  
Author(s):  
Takahiko Hayashi ◽  
Atsuyuki Ishida ◽  
Akira Kobayashi ◽  
Takefumi Yamaguchi ◽  
Nobuhisa Mizuki ◽  
...  
Keyword(s):  
Dendritic Cells ◽  
Confocal Microscopy ◽  
Bullous Keratopathy ◽  
Dependent Manner ◽  
In Vivo Confocal Microscopy ◽  
Descemet Membrane Endothelial Keratoplasty ◽  
Corneal Nerves ◽  
Corneal Nerve ◽  
Number Of Branches

Abstract This study evaluated changes in corneal nerves and the number of dendritic cells (DCs) in corneal basal epithelium following Descemet membrane endothelial keratoplasty (DMEK) surgery for bullous keratopathy (BK). Twenty-three eyes from 16 consecutive patients that underwent DMEK for BK were included. Eyes of age-matched patients that underwent pre-cataract surgery (12 eyes) were used as controls. In vivo confocal microscopy was performed pre- and postoperatively at 6, 12, and 24 months. Corneal nerve length, corneal nerve trunks, number of branches, and the number of DCs were determined. The total corneal nerve length of 1634.7 ± 1389.1 μm /mm2 before surgery was significantly increased in a time-dependent manner to 4485.8 ± 1403.7 μm /mm2, 6949.5 ± 1477.1 μm /mm2, and 9389.2 ± 2302.2 μm /mm2 at 6, 12, and 24 months after DMEK surgery, respectively. The DC density in BK cornea pre- and postoperatively at 6 months was significantly higher than in the controls, and decreased postoperatively at 12 and 24 months and was significantly lower than that at 6 months postoperatively. Thus, our results suggest that DMEK can repair and normalize the corneal environment.

scholarly journals ScanNet: An interpretable geometric deep learning model for structure-based protein binding site prediction

2021 ◽  
Author(s):  
Jérôme Tubiana ◽  
Dina Schneidman-Duhovny ◽  
Haim J. Wolfson
Keyword(s):  
Deep Learning ◽  
Small Molecules ◽  
Binding Sites ◽  
Comparative Modeling ◽  
Learning Model ◽  
Functional Sites ◽  
Site Prediction ◽  
Interpretable Model ◽  
Deep Learning Model

Predicting the functional sites of a protein from its structure, such as the binding sites of small molecules, other proteins or antibodies sheds light on its function in vivo. Currently, two classes of methods prevail: Machine Learning (ML) models built on top of handcrafted features and comparative modeling. They are respectively limited by the expressivity of the handcrafted features and the availability of similar proteins. Here, we introduce ScanNet, an end-to-end, interpretable geometric deep learning model that learns features directly from 3D structures. ScanNet builds representations of atoms and amino acids based on the spatio-chemical arrangement of their neighbors. We train ScanNet for detecting protein-protein and protein-antibody binding sites, demonstrate its accuracy - including for unseen protein folds - and interpret the filters learned. Finally, we predict epitopes of the SARS-CoV-2 spike protein, validating known antigenic regions and predicting previously uncharacterized ones. Overall, ScanNet is a versatile, powerful, and interpretable model suitable for functional site prediction tasks. A webserver for ScanNet is available from http://bioinfo3d.cs.tau.ac.il/ScanNet/

Association between alterations of corneal sub-basal nerve plexus analyzed with in vivo confocal microscopy and long-term glycemic variability

2020 ◽  
pp. 112067212096412
Author(s):  
Marco Pellegrini ◽  
Stefano Sebastiani ◽  
Lorenzo Tucci ◽  
Giuseppe Giannaccare ◽  
Simona Moscatiello ◽  
...  
Keyword(s):  
Confocal Microscopy ◽  
Glycemic Variability ◽  
Diabetes Duration ◽  
Nerve Plexus ◽  
Cold Sensitivity ◽  
In Vivo Confocal Microscopy ◽  
Corneal Nerve ◽  
Automated Software

Purpose: The effect of long-term glycemic variability upon corneal sub-basal nerve plexus (CSNP) morphology analyzed by in vivo confocal microscopy (IVCM) has been poorly investigated in the setting of type 1 diabetes mellitus (T1DM). Our purpose was to analyze the association between morphometric parameters of CSNP and new markers of glycemic variability in a population of patients with T1DM. Methods: Forty patients with T1DM underwent: assessment of diabetic neuropathy (DN); analysis of subcutaneous advanced glycated end-products; IVCM scans of CSNP. The fully automated software ACCMetrics was employed to analyze IVCM images and calculate seven corneal nerve parameters. Data of diabetes duration, mean and standard deviation (SD) of either last-year and all-time glycated hemoglobin (HbA1C) were retrieved. Results: Diabetes duration and all-time SD of HbA1C were independently associated with CNFD (R = –0.26, p = 0.01; R = –0.27, p = 0.047 respectively), CNFL (R = –0.12; p = 0.01; R = –0.17, p = 0.01 respectively) and CNFrD (R = –0.001, p = 0.009; R = –0.002, p = 0.007 respectively). The analysis of the association among IVCM parameters and specific subtypes of DN showed that altered cold sensitivity was independently associated with CNFD (B = –0.24, p = 0.01), CNFL (B = –0.46, p = 0.01) and CNFrD (B = –28.65, p = 0.03). Conclusions: All-time SD of HbA1C and disease duration were found to be independent predictors of damage to CSNP in patients with T1DM.

Effect of herpes simplex keratitis scar location on bilateral corneal nerve alterations: an in vivo confocal microscopy study

2020 ◽  
pp. bjophthalmol-2020-316628
Author(s):  
Chareenun Chirapapaisan ◽  
Rodrigo T. Muller ◽  
Afsun Sahin ◽  
Andrea Cruzat ◽  
Bernardo M. Cavalcanti ◽  
...  
Keyword(s):  
Herpes Simplex ◽  
Confocal Microscopy ◽  
Peripheral Nerves ◽  
In Vivo Confocal Microscopy ◽  
Corneal Sensation ◽  
Scar Area ◽  
Corneal Nerve ◽  
The Impact ◽  
Peripheral Cornea

AimsTo evaluate the impact of herpes simplex virus (HSV)-induced scar location on bilateral corneal nerve alterations using laser in vivo confocal microscopy (IVCM).MethodsCentral and peripheral corneal subbasal nerve density (CSND) were assessed bilaterally in 39 patients with unilateral HSV-induced corneal scars (21 central scars (CS), 18 peripheral scars (PS)) using IVCM. Results were compared between patients and 24 age-matched controls. CSND was correlated to corneal sensation for all locations.ResultsOverall patients revealed significant decrease of CSND in the central and peripheral cornea (9.13±0.98 and 6.26±0.53 mm/mm2, p<0.001), compared with controls (22.60±0.77 and 9.88±0.49 mm/mm2). CS group showed a decrease in central (8.09±1.30 mm/mm2) and total peripheral nerves (5.15±0.62 mm/mm2) of the affected eyes, whereas PS group demonstrated a decrease in central (10.34±1.48 mm/mm2) and localised peripheral nerves only in the scar area (4.22±0.77 mm/mm2) (all p<0.001). In contralateral eyes, CSND decreased in the central cornea of the CS group (16.88±1.27, p=0.004), and in the peripheral area, mirroring the scar area in the affected eyes of the PS group (7.20±0.87, p=0.032). Corneal sensation significantly decreased in the whole cornea of the affected, but not in contralateral eyes (p<0.001). A positive correlation between CSND and corneal sensation was found in all locations (p<0.001).ConclusionsPatients with HSV scar demonstrate bilateral CSND decrease as shown by IVCM. CSND and corneal sensation decrease in both central and peripheral cornea in affected eyes, although only in the scar area in PS group. Interestingly, diminishment of CSND was found locally in the contralateral eyes, corresponding and mirroring the scar location in the affected eyes.

Sign in / Sign up

Export Citation Format

Share Document