1
|
Liu X, Li X, Zhang Y, Wang M, Yao J, Tang J. Boundary-Repairing Dual-Path Network for Retinal Layer Segmentation in OCT Image with Pigment Epithelial Detachment. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024:10.1007/s10278-024-01093-y. [PMID: 38740662 DOI: 10.1007/s10278-024-01093-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/05/2023] [Revised: 03/05/2024] [Accepted: 03/06/2024] [Indexed: 05/16/2024]
Abstract
Automatic retinal layer segmentation in optical coherence tomography (OCT) images is crucial for the diagnosis of ocular diseases. Currently, automatic retinal layer segmentation works well with normal OCT images. However, pigment epithelial detachment (PED) dramatically alters the retinal structure, causing blurred boundaries and partial disappearance of the Bruch's Membrane (BM), thus posing challenges to the segmentation. To tackle these problems, we propose a novel dual-path U-shaped network for simultaneous layer segmentation and boundary regression. This network first designs a feature interaction fusion (FIF) module to strengthen the boundary shape constraints in the layer path. To address the challenge posed by partial BM disappearance and boundary-blurring, we propose a layer boundary repair (LBR) module. This module aims to use contrastive loss to enhance the confidence of blurred boundary regions and refine the segmentation of layer boundaries through the re-prediction head. In addition, we introduce a novel bilateral threshold distance map (BTDM) designed for the boundary path. The BTDM serves to emphasize information within boundary regions. This map, combined with the updated probability map, culminates in topology-guaranteed segmentation results achieved through a topology correction (TC) module. We investigated the proposed network on two severely deformed datasets (i.e., OCTA-500 and Aier-PED) and one slightly deformed dataset (i.e., DUKE). The proposed method achieves an average Dice score of 94.26% on the OCTA-500 dataset, which was 1.5% higher than BAU-Net and outperformed other methods. In the DUKE and Aier-PED datasets, the proposed method achieved average Dice scores of 91.65% and 95.75%, respectively.
Collapse
Affiliation(s)
- Xiaoming Liu
- School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, 430065, China.
- Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan, 430065, China.
| | - Xiao Li
- School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, 430065, China
- Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan, 430065, China
| | - Ying Zhang
- Wuhan Aier Eye Hospital of Wuhan University, Wuhan, China
| | - Man Wang
- Wuhan Aier Eye Hospital of Wuhan University, Wuhan, China
| | - Junping Yao
- Department of Ophthalmology, Tianyou Hospital Affiliated to Wuhan University of Science and Technology, Wuhan, China
| | - Jinshan Tang
- Department of Health Administration and Policy, College of Health and Human Services, George Mason University, Fairfax, VA, 22030, USA
| |
Collapse
|
2
|
Pfau M, Schmitz-Valckenberg S, Ribeiro R, Safaei R, McKeown A, Fleckenstein M, Holz FG. Association of complement C3 inhibitor pegcetacoplan with reduced photoreceptor degeneration beyond areas of geographic atrophy. Sci Rep 2022; 12:17870. [PMID: 36284220 PMCID: PMC9596427 DOI: 10.1038/s41598-022-22404-9] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/20/2022] [Accepted: 10/14/2022] [Indexed: 01/20/2023] Open
Abstract
Preservation of photoreceptors beyond areas of retinal pigment epithelium atrophy is a critical treatment goal in eyes with geographic atrophy (GA) to prevent vision loss. Thus, we assessed the association of treatment with the complement C3 inhibitor pegcetacoplan with optical coherence tomography (OCT)-based photoreceptor laminae thicknesses in this post hoc analysis of the FILLY trial (NCT02503332). Retinal layers in OCT were segmented using a deep-learning-based pipeline and extracted along evenly spaced contour-lines surrounding areas of GA. The primary outcome measure was change from baseline in (standardized) outer nuclear layer (ONL) thickness at the 5.16°-contour-line at month 12. Participants treated with pegcetacoplan monthly had a thicker ONL along the 5.16° contour-line compared to the pooled sham arm (mean difference [95% CI] + 0.29 z-score units [0.16, 0.42], P < 0.001). The same was evident for eyes treated with pegcetacoplan every other month (+ 0.26 z-score units [0.13, 0.4], P < 0.001). Additionally, eyes treated with pegcetacoplan exhibited a thicker photoreceptor inner segment layer along the 5.16°-contour-line at month 12. These findings suggest that pegcetacoplan could slow GA progression and lead to reduced thinning of photoreceptor layers beyond the GA boundary. Future trials in earlier disease stages, i.e., intermediate AMD, aiming to slow photoreceptor degeneration warrant consideration.
Collapse
Affiliation(s)
- Maximilian Pfau
- Department of Ophthalmology, University of Bonn, Bonn, Germany
- GRADE Reading Center, Bonn, Germany
- Institute of Molecular and Clinical Ophthalmology Basel, Basel, Switzerland
| | - Steffen Schmitz-Valckenberg
- Department of Ophthalmology, University of Bonn, Bonn, Germany.
- GRADE Reading Center, Bonn, Germany.
- Department of Ophthalmology & Visual Sciences, John A. Moran Eye Center, University of Utah, 65 North Mario Capecchi Drive, Salt Lake City, UT, 84312, USA.
| | | | | | | | - Monika Fleckenstein
- GRADE Reading Center, Bonn, Germany
- Department of Ophthalmology & Visual Sciences, John A. Moran Eye Center, University of Utah, 65 North Mario Capecchi Drive, Salt Lake City, UT, 84312, USA
| | - Frank G Holz
- Department of Ophthalmology, University of Bonn, Bonn, Germany
- GRADE Reading Center, Bonn, Germany
| |
Collapse
|
3
|
Choovuthayakorn J, Chokesuwattanaskul S, Phinyo P, Hansapinyo L, Pathanapitoon K, Chaikitmongkol V, Watanachai N, Kunavisarut P, Patikulsila D. Reference Database of Inner Retinal Layer Thickness and Thickness Asymmetry in Healthy Thai Adults as Measured by the Spectralis Spectral-Domain Optical Coherence Tomography. Ophthalmic Res 2022; 65:668-677. [PMID: 35709686 DOI: 10.1159/000525512] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2022] [Accepted: 05/19/2022] [Indexed: 12/13/2022]
Abstract
INTRODUCTION The study aimed to determine a reference database of the thickness and intraocular thickness asymmetry of total retina, retinal nerve fiber layer (RNFL), ganglion cell layer (GCL), and inner plexiform layer (IPL) in healthy Thai subjects measured by the Spectralis spectral-domain optical coherence tomography. METHODS This cross-sectional study recruited the healthy subjects age ≥18 years, having spherical refraction within ±6 diopters and cylindrical refraction ±3 diopters, from a hospital's personnel and the people visiting the ophthalmology department. Only 1 eye of each subject was randomly selected for an analysis. Macular images were obtained using posterior pole thickness scan protocol over a 24° × 24° area at the center of the fovea. The automated retinal thickness segmentation values of total retina and three inner retinal layers were calculated for the mean and the mean intraocular thickness difference between superior and inferior retinal hemispheres. The influence of age, gender, and axial length on thickness and thickness asymmetry of individualized retinal layer was evaluated. RESULTS 252 subjects were included in study with a mean (SD) age of 46.7 (15.8) years, and 120 (47.6%) were males. According to the Early Treatment Diabetic Retinopathy Study map, the inner ring area was the thickest location of the total retina (range; 326.0-341.5 µm), GCL (range; 47.7-52.7 µm), and IPL (range; 39.9-42.1 µm), whereas the thickest location of RNFL was at the outer ring area (range; 18.8-47.5 µm). For posterior pole intraocular thickness asymmetry, the greatest mean ± SD difference was observed for total retina (9.0 ± 2.2 µm), followed by RNFL (9.9 ± 3.2 µm) and GCL (2.7 ± 0.6 µm), and the lowest mean difference was noted for IPL (2.4 ± 0.5 µm). The thickness and thickness asymmetry of each retinal layer were variably influenced by age, gender, and axial length; however, these factors had a minimal influence on the thickness asymmetry maps of GCL and RNFL. CONCLUSION The reference database of the macular thickness and thickness asymmetry from this study would be beneficial in determining physiologic variations of the OCT parameters in the healthy Thai population.
Collapse
Affiliation(s)
- Janejit Choovuthayakorn
- Department of Ophthalmology, Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand
| | - Susama Chokesuwattanaskul
- Department of Ophthalmology, Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand.,Cornea and Refractive Surgery Unit, Department of Ophthalmology, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Bangkok, Thailand
| | - Phichayut Phinyo
- Department of Family Medicine, Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand.,Musculoskeletal Science and Translational Research (MSTR), Chiang Mai University, Chiang Mai, Thailand.,Clinical Epidemiology and Clinical Statistics Center, Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand
| | - Linda Hansapinyo
- Department of Ophthalmology, Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand
| | - Kessara Pathanapitoon
- Department of Ophthalmology, Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand
| | - Voraporn Chaikitmongkol
- Department of Ophthalmology, Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand
| | - Nawat Watanachai
- Department of Ophthalmology, Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand
| | - Paradee Kunavisarut
- Department of Ophthalmology, Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand
| | - Direk Patikulsila
- Department of Ophthalmology, Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand
| |
Collapse
|
4
|
Automated foveal location detection on spectral-domain optical coherence tomography in geographic atrophy patients. Graefes Arch Clin Exp Ophthalmol 2022; 260:2261-2270. [PMID: 35044505 PMCID: PMC9203415 DOI: 10.1007/s00417-021-05520-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/06/2021] [Revised: 11/15/2021] [Accepted: 12/07/2021] [Indexed: 01/15/2023] Open
Abstract
PURPOSE To develop a fully automated algorithm for accurate detection of fovea location in atrophic age-related macular degeneration (AMD), based on spectral-domain optical coherence tomography (SD-OCT) scans. METHODS Image processing was conducted on a cohort of patients affected by geographic atrophy (GA). SD-OCT images (cube volume) from 55 eyes (51 patients) were extracted and processed with a layer segmentation algorithm to segment Ganglion Cell Layer (GCL) and Inner Plexiform Layer (IPL). Their en face thickness projection was convolved with a 2D Gaussian filter to find the global maximum, which corresponded to the detected fovea. The detection accuracy was evaluated by computing the distance between manual annotation and predicted location. RESULTS The mean total location error was 0.101±0.145mm; the mean error in horizontal and vertical en face axes was 0.064±0.140mm and 0.063±0.060mm, respectively. The mean error for foveal and extrafoveal retinal pigment epithelium and outer retinal atrophy (RORA) was 0.096±0.070mm and 0.107±0.212mm, respectively. Our method obtained a significantly smaller error than the fovea localization algorithm inbuilt in the OCT device (0.313±0.283mm, p <.001) or a method based on the thinnest central retinal thickness (0.843±1.221, p <.001). Significant outliers are depicted with the reliability score of the method. CONCLUSION Despite retinal anatomical alterations related to GA, the presented algorithm was able to detect the foveal location on SD-OCT cubes with high reliability. Such an algorithm could be useful for studying structural-functional correlations in atrophic AMD and could have further applications in different retinal pathologies.
Collapse
|
5
|
García G, Del Amor R, Colomer A, Verdú-Monedero R, Morales-Sánchez J, Naranjo V. Circumpapillary OCT-focused hybrid learning for glaucoma grading using tailored prototypical neural networks. Artif Intell Med 2021; 118:102132. [PMID: 34412848 DOI: 10.1016/j.artmed.2021.102132] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2021] [Revised: 06/21/2021] [Accepted: 06/23/2021] [Indexed: 12/22/2022]
Abstract
Glaucoma is one of the leading causes of blindness worldwide and Optical Coherence Tomography (OCT) is the quintessential imaging technique for its detection. Unlike most of the state-of-the-art studies focused on glaucoma detection, in this paper, we propose, for the first time, a novel framework for glaucoma grading using raw circumpapillary B-scans. In particular, we set out a new OCT-based hybrid network which combines hand-driven and deep learning algorithms. An OCT-specific descriptor is proposed to extract hand-crafted features related to the retinal nerve fibre layer (RNFL). In parallel, an innovative CNN is developed using skip-connections to include tailored residual and attention modules to refine the automatic features of the latent space. The proposed architecture is used as a backbone to conduct a novel few-shot learning based on static and dynamic prototypical networks. The k-shot paradigm is redefined giving rise to a supervised end-to-end system which provides substantial improvements discriminating between healthy, early and advanced glaucoma samples. The training and evaluation processes of the dynamic prototypical network are addressed from two fused databases acquired via Heidelberg Spectralis system. Validation and testing results reach a categorical accuracy of 0.9459 and 0.8788 for glaucoma grading, respectively. Besides, the high performance reported by the proposed model for glaucoma detection deserves a special mention. The findings from the class activation maps are directly in line with the clinicians' opinion since the heatmaps pointed out the RNFL as the most relevant structure for glaucoma diagnosis.
Collapse
Affiliation(s)
- Gabriel García
- Instituto de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, 46022 Valencia, Spain.
| | - Rocío Del Amor
- Instituto de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, 46022 Valencia, Spain
| | - Adrián Colomer
- Instituto de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, 46022 Valencia, Spain
| | - Rafael Verdú-Monedero
- Departamento de Tecnologías de la Información y las Comunicaciones, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain
| | - Juan Morales-Sánchez
- Departamento de Tecnologías de la Información y las Comunicaciones, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain
| | - Valery Naranjo
- Instituto de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, 46022 Valencia, Spain
| |
Collapse
|
6
|
Li J, Jin P, Zhu J, Zou H, Xu X, Tang M, Zhou M, Gan Y, He J, Ling Y, Su Y. Multi-scale GCN-assisted two-stage network for joint segmentation of retinal layers and discs in peripapillary OCT images. BIOMEDICAL OPTICS EXPRESS 2021; 12:2204-2220. [PMID: 33996224 PMCID: PMC8086482 DOI: 10.1364/boe.417212] [Citation(s) in RCA: 22] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/11/2020] [Revised: 03/15/2021] [Accepted: 03/16/2021] [Indexed: 05/03/2023]
Abstract
An accurate and automated tissue segmentation algorithm for retinal optical coherence tomography (OCT) images is crucial for the diagnosis of glaucoma. However, due to the presence of the optic disc, the anatomical structure of the peripapillary region of the retina is complicated and is challenging for segmentation. To address this issue, we develop a novel graph convolutional network (GCN)-assisted two-stage framework to simultaneously label the nine retinal layers and the optic disc. Specifically, a multi-scale global reasoning module is inserted between the encoder and decoder of a U-shape neural network to exploit anatomical prior knowledge and perform spatial reasoning. We conduct experiments on human peripapillary retinal OCT images. We also provide public access to the collected dataset, which might contribute to the research in the field of biomedical image processing. The Dice score of the proposed segmentation network is 0.820 ± 0.001 and the pixel accuracy is 0.830 ± 0.002, both of which outperform those from other state-of-the-art techniques.
Collapse
Affiliation(s)
- Jiaxuan Li
- John Hopcroft Center for Computer Science, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Peiyao Jin
- Department of Preventative Ophthalmology, Shanghai Eye Disease Prevention and Treatment Center, Shanghai Eye Hospital, Shanghai 200040, China
- Department of Ophthalmology, Shanghai General Hospital, Shanghai Jiao Tong University, Shanghai 200080, China
| | - Jianfeng Zhu
- Department of Preventative Ophthalmology, Shanghai Eye Disease Prevention and Treatment Center, Shanghai Eye Hospital, Shanghai 200040, China
| | - Haidong Zou
- Department of Preventative Ophthalmology, Shanghai Eye Disease Prevention and Treatment Center, Shanghai Eye Hospital, Shanghai 200040, China
- Department of Ophthalmology, Shanghai General Hospital, Shanghai Jiao Tong University, Shanghai 200080, China
| | - Xun Xu
- Department of Preventative Ophthalmology, Shanghai Eye Disease Prevention and Treatment Center, Shanghai Eye Hospital, Shanghai 200040, China
- Department of Ophthalmology, Shanghai General Hospital, Shanghai Jiao Tong University, Shanghai 200080, China
| | - Min Tang
- Department of Ophthalmology, Shanghai General Hospital, Shanghai Jiao Tong University, Shanghai 200080, China
| | - Minwen Zhou
- Department of Ophthalmology, Shanghai General Hospital, Shanghai Jiao Tong University, Shanghai 200080, China
| | - Yu Gan
- Department of Electrical and Computer Engineering, The University of Alabama, AL 35487, USA
| | - Jiangnan He
- Department of Preventative Ophthalmology, Shanghai Eye Disease Prevention and Treatment Center, Shanghai Eye Hospital, Shanghai 200040, China
| | - Yuye Ling
- John Hopcroft Center for Computer Science, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Yikai Su
- State Key Lab of Advanced Optical Communication Systems and Networks, Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
| |
Collapse
|
7
|
Pfau M, von der Emde L, de Sisternes L, Hallak JA, Leng T, Schmitz-Valckenberg S, Holz FG, Fleckenstein M, Rubin DL. Progression of Photoreceptor Degeneration in Geographic Atrophy Secondary to Age-related Macular Degeneration. JAMA Ophthalmol 2021; 138:1026-1034. [PMID: 32789526 DOI: 10.1001/jamaophthalmol.2020.2914] [Citation(s) in RCA: 49] [Impact Index Per Article: 16.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/29/2022]
Abstract
Importance Sensitive outcome measures for disease progression are needed for treatment trials in geographic atrophy (GA) secondary to age-related macular degeneration (AMD). Objective To quantify photoreceptor degeneration outside regions of GA in eyes with nonexudative AMD, to evaluate its association with future GA progression, and to characterize its spatio-temporal progression. Design, Setting, and Participants Monocenter cohort study (Directional Spread in Geographic Atrophy [NCT02051998]) and analysis of data from a normative data study at a tertiary referral center. One hundred fifty-eight eyes of 89 patients with a mean (SD) age of 77.7 (7.1) years, median area of GA of 8.87 mm2 (IQR, 4.09-15.60), and median follow-up of 1.1 years (IQR, 0.52-1.7 years), as well as 93 normal eyes from 93 participants. Exposures Longitudinal spectral-domain optical coherence tomography (SD-OCT) volume scans (121 B-scans across 30° × 25°) were segmented with a deep-learning pipeline and standardized in a pointwise manner with age-adjusted normal data (z scores). Outer nuclear layer (ONL), photoreceptor inner segment (IS), and outer segment (OS) thickness were quantified along evenly spaced contour lines surrounding GA lesions. Linear mixed models were applied to assess the association between photoreceptor-related imaging features and GA progression rates and characterize the pattern of photoreceptor degeneration over time. Main Outcomes and Measures Association of ONL thinning with follow-up time (after adjusting for age, retinal topography [z score], and distance to the GA boundary). Results The study included 158 eyes of 89 patients (51 women and 38 men) with a mean (SD) age of 77.7 (7.1) years. The fully automated B-scan segmentation was accurate (dice coefficient, 0.82; 95% CI, 0.80-0.85; compared with manual markings) and revealed a marked interpatient variability in photoreceptor degeneration. The ellipsoid zone (EZ) loss-to-GA boundary distance and OS thickness were prognostic for future progression rates. Outer nuclear layer and IS thinning over time was significant even when adjusting for age and proximity to the GA boundary (estimates of -0.16 μm/y; 95% CI, -0.30 to -0.02; and -0.17 μm/y; 95% CI, -0.26 to -0.09). Conclusions and Relevance Distinct and progressive alterations of photoreceptor laminae (exceeding GA spatially) were detectable and quantifiable. The degree of photoreceptor degeneration outside of regions of retinal pigment epithelium atrophy varied markedly between eyes and was associated with future GA progression. Macula-wide photoreceptor laminae thinning represents a potential candidate end point to monitor treatment effects beyond mere GA lesion size progression.
Collapse
Affiliation(s)
- Maximilian Pfau
- Department of Biomedical Data Science, Stanford University, Stanford, California.,Department of Ophthalmology, University of Bonn, Bonn, Germany
| | | | - Luis de Sisternes
- Research and Development, Carl Zeiss Meditec Inc, Dublin, California
| | - Joelle A Hallak
- Department of Ophthalmology and Visual Sciences, University of Illinois at Chicago
| | - Theodore Leng
- Byers Eye Institute at Stanford, Stanford University School of Medicine, Palo Alto, California
| | - Steffen Schmitz-Valckenberg
- Department of Ophthalmology, University of Bonn, Bonn, Germany.,John A. Moran Eye Center, University of Utah, Salt Lake City
| | - Frank G Holz
- Department of Ophthalmology, University of Bonn, Bonn, Germany
| | - Monika Fleckenstein
- Department of Ophthalmology, University of Bonn, Bonn, Germany.,John A. Moran Eye Center, University of Utah, Salt Lake City
| | - Daniel L Rubin
- Department of Biomedical Data Science, Stanford University, Stanford, California
| |
Collapse
|
8
|
Devalla SK, Pham TH, Panda SK, Zhang L, Subramanian G, Swaminathan A, Yun CZ, Rajan M, Mohan S, Krishnadas R, Senthil V, De Leon JMS, Tun TA, Cheng CY, Schmetterer L, Perera S, Aung T, Thiéry AH, Girard MJA. Towards label-free 3D segmentation of optical coherence tomography images of the optic nerve head using deep learning. BIOMEDICAL OPTICS EXPRESS 2020; 11:6356-6378. [PMID: 33282495 PMCID: PMC7687952 DOI: 10.1364/boe.395934] [Citation(s) in RCA: 21] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/07/2020] [Revised: 08/17/2020] [Accepted: 08/19/2020] [Indexed: 05/06/2023]
Abstract
Recently proposed deep learning (DL) algorithms for the segmentation of optical coherence tomography (OCT) images to quantify the morphological changes to the optic nerve head (ONH) tissues during glaucoma have limited clinical adoption due to their device specific nature and the difficulty in preparing manual segmentations (training data). We propose a DL-based 3D segmentation framework that is easily translatable across OCT devices in a label-free manner (i.e. without the need to manually re-segment data for each device). Specifically, we developed 2 sets of DL networks: the 'enhancer' (enhance OCT image quality and harmonize image characteristics from 3 devices) and the 'ONH-Net' (3D segmentation of 6 ONH tissues). We found that only when the 'enhancer' was used to preprocess the OCT images, the 'ONH-Net' trained on any of the 3 devices successfully segmented ONH tissues from the other two unseen devices with high performance (Dice coefficients > 0.92). We demonstrate that is possible to automatically segment OCT images from new devices without ever needing manual segmentation data from them.
Collapse
Affiliation(s)
- Sripad Krishna Devalla
- Ophthalmic Engineering & Innovation Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore
| | - Tan Hung Pham
- Ophthalmic Engineering & Innovation Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
| | - Satish Kumar Panda
- Ophthalmic Engineering & Innovation Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore
| | - Liang Zhang
- Ophthalmic Engineering & Innovation Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore
| | - Giridhar Subramanian
- Ophthalmic Engineering & Innovation Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore
| | - Anirudh Swaminathan
- Ophthalmic Engineering & Innovation Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore
| | - Chin Zhi Yun
- Ophthalmic Engineering & Innovation Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore
| | | | | | | | | | - John Mark S De Leon
- Department of Health Eye Center, East Avenue Medical Center, Quezon City, Philippines
| | - Tin A Tun
- Ophthalmic Engineering & Innovation Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
| | - Ching-Yu Cheng
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
- Ophthalmology & Visual Sciences Academic Clinical Program (Eye ACP), Duke-NUS Medical School, Singapore
| | - Leopold Schmetterer
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
- Nanyang Technological University, Singapore
- Department of Clinical Pharmacology, Medical University of Vienna, Austria
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Austria
- Institute of Clinical and Molecular Ophthalmology, Basel, Switzerland
| | - Shamira Perera
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
- Duke-NUS Graduate Medical School, 8 College Rd, Singapore 169857, Singapore
| | - Tin Aung
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
- Duke-NUS Graduate Medical School, 8 College Rd, Singapore 169857, Singapore
| | - Alexandre H Thiéry
- Department of Statistics and Applied Probability, National University of Singapore, Singapore
| | - Michaël J A Girard
- Ophthalmic Engineering and Innovation Laboratory (OEIL), Singapore Eye Research Institute, 20 College Road, Singapore 169856, Singapore
| |
Collapse
|
9
|
Raja H, Hassan T, Akram MU, Werghi N. Clinically Verified Hybrid Deep Learning System for Retinal Ganglion Cells Aware Grading of Glaucomatous Progression. IEEE Trans Biomed Eng 2020; 68:2140-2151. [PMID: 33044925 DOI: 10.1109/tbme.2020.3030085] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
Abstract
OBJECTIVE Glaucoma is the second leading cause of blindness worldwide. Glaucomatous progression can be easily monitored by analyzing the degeneration of retinal ganglion cells (RGCs). Many researchers have screened glaucoma by measuring cup-to-disc ratios from fundus and optical coherence tomography scans. However, this paper presents a novel strategy that pays attention to the RGC atrophy for screening glaucomatous pathologies and grading their severity. METHODS The proposed framework encompasses a hybrid convolutional network that extracts the retinal nerve fiber layer, ganglion cell with the inner plexiform layer and ganglion cell complex regions, allowing thus a quantitative screening of glaucomatous subjects. Furthermore, the severity of glaucoma in screened cases is objectively graded by analyzing the thickness of these regions. RESULTS The proposed framework is rigorously tested on publicly available Armed Forces Institute of Ophthalmology (AFIO) dataset, where it achieved the F1 score of 0.9577 for diagnosing glaucoma, a mean dice coefficient score of 0.8697 for extracting the RGC regions and an accuracy of 0.9117 for grading glaucomatous progression. Furthermore, the performance of the proposed framework is clinically verified with the markings of four expert ophthalmologists, achieving a statistically significant Pearson correlation coefficient of 0.9236. CONCLUSION An automated assessment of RGC degeneration yields better glaucomatous screening and grading as compared to the state-of-the-art solutions. SIGNIFICANCE An RGC-aware system not only screens glaucoma but can also grade its severity and here we present an end-to-end solution that is thoroughly evaluated on a standardized dataset and is clinically validated for analyzing glaucomatous pathologies.
Collapse
|
10
|
HyCAD-OCT: A Hybrid Computer-Aided Diagnosis of Retinopathy by Optical Coherence Tomography Integrating Machine Learning and Feature Maps Localization. APPLIED SCIENCES-BASEL 2020. [DOI: 10.3390/app10144716] [Citation(s) in RCA: 14] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Optical Coherence Tomography (OCT) imaging has major advantages in effectively identifying the presence of various ocular pathologies and detecting a wide range of macular diseases. OCT examinations can aid in the detection of many retina disorders in early stages that could not be detected in traditional retina images. In this paper, a new hybrid computer-aided OCT diagnostic system (HyCAD) is proposed for classification of Diabetic Macular Edema (DME), Choroidal Neovascularization (CNV) and drusen disorders, while separating them from Normal OCT images. The proposed HyCAD hybrid learning system integrates the segmentation of Region of Interest (RoI), based on central serious chorioretinopathy (CSC) in Spectral Domain Optical Coherence Tomography (SD-OCT) images, with deep learning architectures for effective diagnosis of retinal disorders. The proposed system assimilates a range of techniques including RoI localization and feature extraction, followed by classification and diagnosis. An efficient feature fusion phase has been introduced for combining the OCT image features, extracted by Deep Convolutional Neural Network (CNN), with the features extracted from the RoI segmentation phase. This fused feature set is used to predict multiclass OCT retina disorders. The proposed segmentation phase of retinal RoI regions adds substantial contribution as it draws attention to the most significant areas that are candidate for diagnosis. A new modified deep learning architecture (Norm-VGG16) is introduced integrating a kernel regularizer. Norm-VGG16 is trained from scratch on a large benchmark dataset and used in RoI localization and segmentation. Various experiments have been carried out to illustrate the performance of the proposed system. Large Dataset of Labeled Optical Coherence Tomography (OCT) v3 benchmark is used to validate the efficiency of the model compared with others in literature. The experimental results show that the proposed model achieves relatively high-performance in terms of accuracy, sensitivity and specificity. An average accuracy, sensitivity and specificity of 98.8%, 99.4% and 98.2% is achieved, respectively. The remarkable performance achieved reflects that the fusion phase can effectively improve the identification ratio of the urgent patients’ diagnostic images and clinical data. In addition, an outstanding performance is achieved compared to others in literature.
Collapse
|
11
|
Bontzos G, Kabanarou SA, Garnavou-Xirou C, Gkizis I, Kontou E, Triantafyllou D, Xirou T. Segmentation errors and motion artifacts in OCT-A associated with epiretinal membranes. Can J Ophthalmol 2020; 55:293-300. [PMID: 32253013 DOI: 10.1016/j.jcjo.2019.12.007] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2019] [Revised: 11/27/2019] [Accepted: 12/31/2019] [Indexed: 12/13/2022]
Abstract
OBJECTIVE To explore segmentation errors, image quality, and motion-associated artifacts in eyes with idiopathic epiretinal membrane (ERM). METHODS This is a prospective observational study. We included 39 eyes affected by ERM and 40 eyes from age-matched healthy subjects. Optical coherence tomography-angiography (OCT-A) was performed in both groups. Segmentation was automatically performed by intergraded software. Segmentation was regarded as inaccurate if either border deviated from the correct plane by more than 50 μm. Presence of motion artifacts (blink lines, displacement, stretch artifacts, quilting, vessel doubling) and image quality index were reported. RESULTS Quality index score was 7.2 ± 0.9 for the ERM patients. Phakic eyes with ERM had quality index score of 7.71 ± 1.06, and pseudo-phakic eyes with ERM had a quality index score of 7.32 ± 0.85 (p = 0.22). Motion artifacts were 1.22 ± 0.7 in the study cohort. Segmentation was accurate in all healthy subjects (n = 40). Segmentation errors occurred in 64.1% of ERM patients. The inner plexiform layer was the segmentation boundary most prone to inaccurate segmentation, followed by the internal limiting membrane. Segmentation of retinal pigment epithelial layer was accurate in 96.7% of all cases. CONCLUSIONS OCT-A image quality cannot be accurately reproduced in pathological conditions, such as in ERM patients, and is prone to motion artifacts and segmentation errors. Incorrect segmentation results in anatomically incorrect en-face OCT-A images and subsequently in false quantification measures.
Collapse
Affiliation(s)
- Georgios Bontzos
- Department of Ophthalmology, "Korgialenio-Benakio" General Hospital, Athens, Greece.
| | | | | | - Ilias Gkizis
- Department of Ophthalmology, "Korgialenio-Benakio" General Hospital, Athens, Greece
| | - Evgenia Kontou
- Department of Ophthalmology, "Korgialenio-Benakio" General Hospital, Athens, Greece
| | | | - Tina Xirou
- Department of Ophthalmology, "Korgialenio-Benakio" General Hospital, Athens, Greece
| |
Collapse
|
12
|
Montolío A, Cegoñino J, Orduna E, Sebastian B, Garcia-Martin E, Pérez del Palomar A. A mathematical model to predict the evolution of retinal nerve fiber layer thinning in multiple sclerosis patients. Comput Biol Med 2019; 111:103357. [DOI: 10.1016/j.compbiomed.2019.103357] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2019] [Revised: 07/12/2019] [Accepted: 07/13/2019] [Indexed: 01/10/2023]
|
13
|
Ruan Y, Xue J, Li T, Liu D, Lu H, Chen M, Liu T, Niu S, Li D. Multi-phase level set algorithm based on fully convolutional networks (FCN-MLS) for retinal layer segmentation in SD-OCT images with central serous chorioretinopathy (CSC). BIOMEDICAL OPTICS EXPRESS 2019; 10:3987-4002. [PMID: 31452990 PMCID: PMC6701532 DOI: 10.1364/boe.10.003987] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/18/2019] [Revised: 06/13/2019] [Accepted: 06/13/2019] [Indexed: 06/10/2023]
Abstract
As a function of the spatial position of the optical coherence tomography (OCT) image, retinal layer thickness is an important diagnostic indicator for many retinal diseases. Reliable segmentation of the retinal layer is necessary for extracting useful clinical information. However, manual segmentation of these layers is time-consuming and prone to bias. Furthermore, due to speckle noise, low image contrast, retinal detachment, and also irregular morphological features make the automatic segmentation task challenging. To alleviate these challenges, in this paper, we propose a new coarse-fine framework combining the full convolutional network (FCN) with a multiphase level set (named FCN-MLS) for automatic segmentation of nine boundaries in retinal spectral OCT images. In the coarse stage, FCN is used to learn the characteristics of specific retinal layer boundaries and achieve classification of four retinal layers. The boundaries are then extracted and the remaining boundaries are initialized based on a priori information about the thickness of the retinal layer. In order to prevent the overlapping of the segmentation interfaces, a regional restriction technique is used in the multi-phase level to evolve the boundaries to achieve fine nine retinal layers segmentation. Experimental results on 1280 B-scans show that the proposed method can segment nine retinal boundaries accurately. Compared with the manual delineation, the overall mean absolute boundary location difference and the overall mean absolute thickness difference were 5.88 ± 2.38μm and 5.81 ± 2.19μm, which showed a good consistency with manual segmentation by the physicians. Our experimental results also outperform state-of-the-art methods.
Collapse
Affiliation(s)
- Yanan Ruan
- Shandong Key Laboratory of Medical Physics and Image Processing, Shandong Provincial Engineering and Technical Center of Light Manipulation, School of Physics and Electronics, Shandong Normal University, Jinan, 250014, China
- These authors have contributed equally to this work
| | - Jie Xue
- Shandong Key Laboratory of Medical Physics and Image Processing, Shandong Provincial Engineering and Technical Center of Light Manipulation, School of Physics and Electronics, Shandong Normal University, Jinan, 250014, China
- Business School, Shandong Normal University, Jinan, Shandong, 250014, China
- These authors have contributed equally to this work
| | - Tianlai Li
- Shandong Key Laboratory of Medical Physics and Image Processing, Shandong Provincial Engineering and Technical Center of Light Manipulation, School of Physics and Electronics, Shandong Normal University, Jinan, 250014, China
| | - Danhua Liu
- Shandong Key Laboratory of Medical Physics and Image Processing, Shandong Provincial Engineering and Technical Center of Light Manipulation, School of Physics and Electronics, Shandong Normal University, Jinan, 250014, China
| | - Hua Lu
- Shandong Key Laboratory of Medical Physics and Image Processing, Shandong Provincial Engineering and Technical Center of Light Manipulation, School of Physics and Electronics, Shandong Normal University, Jinan, 250014, China
| | - Meirong Chen
- Affiliated Hospital of Shandong University of Traditional Chinese Medicine, Jinan, Shandong 250014, P. R. China
| | - Tingting Liu
- Shandong Eye Hospital, Shandong Eye Institute, Shandong Academy of Medical Science, Jinan, Shandong 250014, China
| | - Sijie Niu
- School of Information Science and Engineering, University of Jinan, Jinan, 250022, China
| | - Dengwang Li
- Shandong Key Laboratory of Medical Physics and Image Processing, Shandong Provincial Engineering and Technical Center of Light Manipulation, School of Physics and Electronics, Shandong Normal University, Jinan, 250014, China
| |
Collapse
|
14
|
Pettenkofer M, Scherm P, Feucht N, Wehrmann K, Lohmann CP, Maier M. Choriocapillaris Flow Density Negatively Correlates With Advancing Age on Spectral-Domain Optical Coherence Tomography Angiography. Ophthalmic Surg Lasers Imaging Retina 2019; 50:302-308. [DOI: 10.3928/23258160-20190503-07] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2018] [Accepted: 01/03/2019] [Indexed: 11/20/2022]
|
15
|
Prevalences of segmentation errors and motion artifacts in OCT-angiography differ among retinal diseases. Graefes Arch Clin Exp Ophthalmol 2018; 256:1807-1816. [PMID: 29982897 DOI: 10.1007/s00417-018-4053-2] [Citation(s) in RCA: 62] [Impact Index Per Article: 10.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2017] [Revised: 06/12/2018] [Accepted: 06/18/2018] [Indexed: 10/28/2022] Open
Abstract
PURPOSE To assess the prevalences of segmentation errors and motion artifacts in optical coherence tomography angiography (OCT-A) in different retinal diseases METHODS: In a retrospective analysis, multimodal retinal imaging including OCT-A was performed in one eye of 57 healthy controls (50.96 ± 22.4 years) and 149 patients (66.42 ± 14.1 years) affected by different chorioretinal diseases: early/intermediate age-related macular degeneration (AMD; n = 26), neovascular AMD (nAMD; n = 22), geographic atrophy due to AMD (GA; n = 6), glaucoma (n = 28), central serous chorioretinopathy (CSC; n = 14), epiretinal membrane (EM; n = 26), retinal vein occlusion (RVO; n = 11), and retinitis pigmentosa (RP; n = 16). Central 3 × 3 mm2 OCT-A imaging was performed with active eye-tracking (AngioVue, Optovue). Best-corrected visual acuity (BCVA) and signal strength index (SSI) were recorded. Images were independently evaluated by two graders using the OCT-A motion artifact score (MAS; scores I-IV) as well as a newly introduced segmentation accuracy score (SAS; score I-IIB). RESULTS Mean SSI was 63.67 ± 9.2 showing a negative correlation with increasing age (rSp = - 0.42, p < 0.001, n = 206). In the healthy cohort, mean MAS was 1.45 ± 0.8 and segmentation was accurate (SAS I) in all eyes. In eyes with retinal pathologies, mean MAS was 2.1 ± 0.9 (p < 0.001). Lowest MAS was observed in GA (2.67 ± 0.5) and RVO (2.45 ± 1.1). Compared to an accurate segmentation in 100% in healthy subjects, 34.2% (n = 51) of all patients showed highest segmentation quality (p < 0.001). 63.8% showed segmentation errors in more than 5% of all single b-scans in one (SAS IIA, n = 58) or at least two (SAS IIB, n = 40) segmentation boundaries. Highest percentages of inaccurate segmentation (SAS IIA or IIB) were observed in the nAMD group (90.1%). The inner plexiform layer was the segmentation boundary most prone to inaccurate segmentation in all pathologies compared to the inner limiting membrane (ILM) and retinal pigment epithelium (RPE) segmentation layer. Incorrect ILM segmentation was only seen in patients with EM. CONCLUSIONS Prior to both qualitative and quantitative analysis, OCT-A images must be carefully reviewed as motion artifacts and segmentation errors in current OCT-A technology are frequent particularly in pathologically altered maculae.
Collapse
|
16
|
Devalla SK, Renukanand PK, Sreedhar BK, Subramanian G, Zhang L, Perera S, Mari JM, Chin KS, Tun TA, Strouthidis NG, Aung T, Thiéry AH, Girard MJA. DRUNET: a dilated-residual U-Net deep learning network to segment optic nerve head tissues in optical coherence tomography images. BIOMEDICAL OPTICS EXPRESS 2018; 9:3244-3265. [PMID: 29984096 PMCID: PMC6033560 DOI: 10.1364/boe.9.003244] [Citation(s) in RCA: 90] [Impact Index Per Article: 15.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/29/2018] [Revised: 06/06/2018] [Accepted: 06/11/2018] [Indexed: 05/18/2023]
Abstract
Given that the neural and connective tissues of the optic nerve head (ONH) exhibit complex morphological changes with the development and progression of glaucoma, their simultaneous isolation from optical coherence tomography (OCT) images may be of great interest for the clinical diagnosis and management of this pathology. A deep learning algorithm (custom U-NET) was designed and trained to segment 6 ONH tissue layers by capturing both the local (tissue texture) and contextual information (spatial arrangement of tissues). The overall Dice coefficient (mean of all tissues) was 0.91 ± 0.05 when assessed against manual segmentations performed by an expert observer. Further, we automatically extracted six clinically relevant neural and connective tissue structural parameters from the segmented tissues. We offer here a robust segmentation framework that could also be extended to the 3D segmentation of the ONH tissues.
Collapse
Affiliation(s)
- Sripad Krishna Devalla
- Ophthalmic Engineering & Innovation Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore
| | - Prajwal K Renukanand
- Ophthalmic Engineering & Innovation Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore
| | - Bharathwaj K Sreedhar
- Ophthalmic Engineering & Innovation Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore
| | - Giridhar Subramanian
- Ophthalmic Engineering & Innovation Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore
| | - Liang Zhang
- Ophthalmic Engineering & Innovation Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore
| | - Shamira Perera
- Duke-NUS, Graduate Medical School, Singapore
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
| | - Jean-Martial Mari
- GePaSud, Université de la Polynésie française, Tahiti, French Polynesia
| | - Khai Sing Chin
- Department of Statistics and Applied Probability, National University of Singapore, Singapore
| | - Tin A Tun
- Ophthalmic Engineering & Innovation Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
| | - Nicholas G Strouthidis
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
- NIHR Biomedical Research Centre at Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology, London, UK
- Discipline of Clinical Ophthalmology and Eye Health, University of Sydney, Sydney, New South Wales, Australia
| | - Tin Aung
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
| | - Alexandre H Thiéry
- Department of Statistics and Applied Probability, National University of Singapore, Singapore
| | - Michaël J A Girard
- Ophthalmic Engineering & Innovation Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
| |
Collapse
|
17
|
Samani NN, Proudlock FA, Siram V, Suraweera C, Hutchinson C, Nelson CP, Al-Uzri M, Gottlob I. Retinal Layer Abnormalities as Biomarkers of Schizophrenia. Schizophr Bull 2018; 44:876-885. [PMID: 29272501 PMCID: PMC6007436 DOI: 10.1093/schbul/sbx130] [Citation(s) in RCA: 55] [Impact Index Per Article: 9.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/02/2023]
Abstract
OBJECTIVE Schizophrenia is associated with several brain deficits, as well as visual processing deficits, but clinically useful biomarkers are elusive. We hypothesized that retinal layer changes, noninvasively visualized using spectral-domain optical coherence tomography (SD-OCT), may represent a possible "window" to these abnormalities. METHODS A Leica EnvisuTM SD-OCT device was used to obtain high-resolution central foveal B-scans in both eyes of 35 patients with schizophrenia and 50 demographically matched controls. Manual retinal layer segmentation was performed to acquire individual and combined layer thickness measurements in 3 macular regions. Contrast sensitivity was measured at 3 spatial frequencies in a subgroup of each cohort. Differences were compared using adjusted linear models and significantly different layer measures in patients underwent Spearman Rank correlations with contrast sensitivity, quantified symptoms severity, disease duration, and antipsychotic medication dose. RESULTS Total retinal and photoreceptor complex thickness was reduced in all regions in patients (P < .0001). Segmentation revealed consistent thinning of the outer nuclear layer (P < .001) and inner segment layer (P < .05), as well as a pattern of parafoveal ganglion cell changes. Low spatial frequency contrast sensitivity was reduced in patients (P = .002) and correlated with temporal parafoveal ganglion cell complex thinning (R = .48, P = .01). Negative symptom severity was inversely correlated with foveal photoreceptor complex thickness (R = -.54, P = .001) and outer nuclear layer thickness (R = -.47, P = .005). CONCLUSIONS Our novel findings demonstrate considerable retinal layer abnormalities in schizophrenia that are related to clinical features and visual function. With time, SD-OCT could provide easily-measurable biomarkers to facilitate clinical assessment and further our understanding of the disease.
Collapse
Affiliation(s)
| | - Frank A Proudlock
- Ulverscroft Eye Unit, University of Leicester, Leicester, UK,Department of Neuroscience, Psychology and Behaviour, University of Leicester, Robert Kilpatrick Clinical Sciences Building, Leicester Royal Infirmary, UK
| | - Vasantha Siram
- Leicestershire Partnership NHS Trust, Bradgate Unit, Glenfield Hospital, Leicester, UK
| | - Chathurie Suraweera
- Leicestershire Partnership NHS Trust, Bradgate Unit, Glenfield Hospital, Leicester, UK
| | - Claire Hutchinson
- Department of Neuroscience, Psychology and Behaviour, University of Leicester, Robert Kilpatrick Clinical Sciences Building, Leicester Royal Infirmary, UK
| | - Christopher P Nelson
- NIHR Leicester Cardiovascular Biomedical Research Unit, Glenfield Hospital, Leicester, UK
| | - Mohammed Al-Uzri
- Leicestershire Partnership NHS Trust, Bradgate Unit, Glenfield Hospital, Leicester, UK,Adult Social and Epidemiological Psychiatry and Disability Research Group, Department of Health Sciences, University of Leicester, Leicester General Hospital, Leicester, UK
| | - Irene Gottlob
- Department of Neuroscience, Psychology and Behaviour, University of Leicester, Robert Kilpatrick Clinical Sciences Building, Leicester Royal Infirmary, UK,To whom correspondence should be addressed; Robert Kilpatrick Clinical Sciences Building, Leicester Royal Infirmary, PO Box 65, Leicester LE2 7LX, UK; tel: +44-116-252-3268, e-mail:
| |
Collapse
|
18
|
Invernizzi A, Pellegrini M, Acquistapace A, Benatti E, Erba S, Cozzi M, Cigada M, Viola F, Gillies M, Staurenghi G. Normative Data for Retinal-Layer Thickness Maps Generated by Spectral-Domain OCT in a White Population. Ophthalmol Retina 2018; 2:808-815.e1. [PMID: 31047534 DOI: 10.1016/j.oret.2017.12.012] [Citation(s) in RCA: 47] [Impact Index Per Article: 7.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/27/2017] [Revised: 12/07/2017] [Accepted: 12/21/2017] [Indexed: 12/28/2022]
Abstract
PURPOSE (1) To collect a dataset of normative Early Treatment Diabetic Retinopathy Study (ETDRS) thickness map values for single retinal layers automatically segmented by Spectralis (Heidelberg Engineering, Heidelberg, Germany) spectral-domain OCT (SD-OCT) in a healthy white population. (2) To test the effect of age, sex, and axial length (AXL) on such values. DESIGN Cross-sectional study. SUBJECTS Healthy adult emmetropic white subjects with no history of ongoing or past conditions known to affect retinal anatomy. METHODS SD-OCT scans (30 × 25-degree volume) centered on the fovea were collected. Retinal-layer automatic segmentation was performed. Mean thickness values of 9 ETDRS sectors were calculated for each layer in 1 eye from each subject. The effect of age, sex, and AXL on the thickness of the central subfield, inner ring (IR), and outer ring (OR) of the ETDRS grid was tested. Scans were performed twice on a subset of patients to assess the repeatability of measurements. MAIN OUTCOME MEASURES Retinal-layer thickness. RESULTS Two hundred eyes from 200 subjects (110 females, mean age 39.9±13.9 years [range 20-74 years]) were used for this study. The mean AXL was 24.30±1.07 mm (range 22.23-27.14 mm). Full retinal thickness was higher in males regardless of the subfield (all P < 0.05). Ganglion cell layer thickness correlated positively with AXL in the C (P = 0.02) but negatively in the OR (P = 0.0001). The inner plexiform layer was thicker in males in the IR (P = 0.01) and thinner in longer eyes in the OR (P = 0.002). The inner nuclear layer was thicker in males in the C and the IR (P = 0.002 and P = 0.0009, respectively). The outer plexiform layer thickness did not change with age and gender but correlated positively with AXL in the C (P = 0.009). Males had thicker outer nuclear layers in all subfields (all P < 0.05). The thickness of the nerve fiber layer and retinal pigment epithelium was not affected by the studied variables in any subfield. The intraclass correlation coefficient ranged from 0.872 for the outer plexiform layer to 0.990 for the retinal nerve fiber layer and the ganglion cell layer. CONCLUSIONS The thickness values of each retinal layer in a large white population are provided. The thickness of retinal layers is influenced by gender, sex, and AXL, with a variable extent depending on the analyzed ETDRS map ring.
Collapse
Affiliation(s)
- Alessandro Invernizzi
- Eye Clinic, Department of Biomedical and Clinical Science "Luigi Sacco," Luigi Sacco Hospital, University of Milan, Milan, Italy; Save Sight Institute, Sydney Eye Hospital, University of Sydney, Sydney, New South Wales, Australia.
| | - Marco Pellegrini
- Eye Clinic, Department of Biomedical and Clinical Science "Luigi Sacco," Luigi Sacco Hospital, University of Milan, Milan, Italy
| | - Alessandra Acquistapace
- Eye Clinic, Department of Biomedical and Clinical Science "Luigi Sacco," Luigi Sacco Hospital, University of Milan, Milan, Italy
| | - Eleonora Benatti
- Department of Clinical Sciences and Community Health, University of Milan, Ophthalmological Unit, IRCCS-Cà Granda Foundation-Ospedale Maggiore Policlinico, Milan, Italy
| | - Stefano Erba
- Eye Clinic, Department of Biomedical and Clinical Science "Luigi Sacco," Luigi Sacco Hospital, University of Milan, Milan, Italy
| | - Mariano Cozzi
- Eye Clinic, Department of Biomedical and Clinical Science "Luigi Sacco," Luigi Sacco Hospital, University of Milan, Milan, Italy
| | - Mario Cigada
- Eye Clinic, Department of Biomedical and Clinical Science "Luigi Sacco," Luigi Sacco Hospital, University of Milan, Milan, Italy
| | - Francesco Viola
- Department of Clinical Sciences and Community Health, University of Milan, Ophthalmological Unit, IRCCS-Cà Granda Foundation-Ospedale Maggiore Policlinico, Milan, Italy
| | - Mark Gillies
- Save Sight Institute, Sydney Eye Hospital, University of Sydney, Sydney, New South Wales, Australia
| | - Giovanni Staurenghi
- Eye Clinic, Department of Biomedical and Clinical Science "Luigi Sacco," Luigi Sacco Hospital, University of Milan, Milan, Italy
| |
Collapse
|
19
|
Niu S, Chen Q, de Sisternes L, Leng T, Rubin DL. Automated detection of foveal center in SD-OCT images using the saliency of retinal thickness maps. Med Phys 2017; 44:6390-6403. [DOI: 10.1002/mp.12614] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2016] [Revised: 09/19/2017] [Accepted: 09/23/2017] [Indexed: 11/12/2022] Open
Affiliation(s)
- Sijie Niu
- School of Information Science and Engineering; University of Jinan; Jinan 250022 China
- School of Computer Science and Engineering; Nanjing University of Science and Technology; Nanjing 210094 China
| | - Qiang Chen
- School of Computer Science and Engineering; Nanjing University of Science and Technology; Nanjing 210094 China
- Fujian Provincial Key Laboratory of Information Processing and Intelligent Control; Minjiang University; Fuzhou 350121 China
| | | | - Theodore Leng
- Byers Eye Institute at Stanford; Stanford University School of Medicine; Palo Alto CA 94303 USA
| | - Daniel L. Rubin
- Department of Radiology; Stanford University; Stanford CA 94305 USA
| |
Collapse
|
20
|
Alten F, Lauermann JL, Clemens CR, Heiduschka P, Eter N. Signal reduction in choriocapillaris and segmentation errors in spectral domain OCT angiography caused by soft drusen. Graefes Arch Clin Exp Ophthalmol 2017; 255:2347-2355. [PMID: 28983695 DOI: 10.1007/s00417-017-3813-8] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2017] [Revised: 09/05/2017] [Accepted: 09/18/2017] [Indexed: 12/19/2022] Open
Abstract
PURPOSE To analyze signal reduction in choriocapillaris (CC) and segmentation errors in spectral domain optical coherence tomography angiography (OCT-A) caused by soft drusen due to age-related macular degeneration (AMD). METHODS Twenty-four eyes of 24 patients underwent multimodal retinal imaging including central 3 × 3mm2 OCT-A (AngioVue, Optovue). Three drusen per study eye were randomly chosen and evaluated regarding drusen height, diameter, and accuracy of OCT-A layer segmentation in lesion proximity. Structural en-face OCT CC images were graded qualitatively and quantitatively regarding signal loss underneath the individual drusen area. Those drusen that showed no distinct signal loss in structural en-face OCT CC images were further evaluated in OCT-A. CC decorrelation signal index was measured within a 30-μm OCT-A CC slab in the exact area of drusen affection. Data were compared to healthy age-matched control subjects. Accuracy of layer segmentation, OCT CC data, and OCT-A CC data were correlated to morphological drusen parameters. RESULTS Mean drusen height and diameter were 91.57 ± 19.5μm and 315.17 ± 116.7μm. OCT-A layer segmentation of the inner plexiform layer (IPL) was disturbed by more than 50 μm in proximity to 26 drusen (36.1%). In these patients, drusen height was significantly higher compared to those with accurate IPL segmentation (p = 0.0126). Sixty-six out of 72 drusen (91.7%) caused a distinct signal loss in the structural en-face OCT CC image. Drusen height and drusen diameter were significantly higher in this group compared to the six drusen with a sufficient signal (p = 0.0276, p = 0.0025). CC decorrelation signal index measured in the area of these six drusen without OCT signal loss (8.3%) was reduced compared to age-matched healthy controls (73.6 vs. 100.1; p = 0.001). CONCLUSIONS Signal attenuation in CC slabs and segmentation errors of the IPL depend on drusen morphology. Both are frequent artifacts in OCT-A imaging in patients with soft drusen and must be considered during image analysis.
Collapse
Affiliation(s)
- F Alten
- Department of Ophthalmology, University of Muenster Medical Center, Domagkstrasse 15, 48149, Muenster, Germany.
| | - J L Lauermann
- Department of Ophthalmology, University of Muenster Medical Center, Domagkstrasse 15, 48149, Muenster, Germany
| | - C R Clemens
- Department of Ophthalmology, University of Muenster Medical Center, Domagkstrasse 15, 48149, Muenster, Germany
| | - P Heiduschka
- Department of Ophthalmology, University of Muenster Medical Center, Domagkstrasse 15, 48149, Muenster, Germany
| | - N Eter
- Department of Ophthalmology, University of Muenster Medical Center, Domagkstrasse 15, 48149, Muenster, Germany
| |
Collapse
|
21
|
Yadav SK, Motamedi S, Oberwahrenbrock T, Oertel FC, Polthier K, Paul F, Kadas EM, Brandt AU. CuBe: parametric modeling of 3D foveal shape using cubic Bézier. BIOMEDICAL OPTICS EXPRESS 2017; 8:4181-4199. [PMID: 28966857 PMCID: PMC5611933 DOI: 10.1364/boe.8.004181] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/15/2017] [Revised: 07/26/2017] [Accepted: 07/27/2017] [Indexed: 06/07/2023]
Abstract
Optical coherence tomography (OCT) allows three-dimensional (3D) imaging of the retina, and is commonly used for assessing pathological changes of fovea and macula in many diseases. Many neuroinflammatory conditions are known to cause modifications to the fovea shape. In this paper, we propose a method for parametric modeling of the foveal shape. Our method exploits invariant features of the macula from OCT data and applies a cubic Bézier polynomial along with a least square optimization to produce a best fit parametric model of the fovea. Additionally, we provide several parameters of the foveal shape based on the proposed 3D parametric modeling. Our quantitative and visual results show that the proposed model is not only able to reconstruct important features from the foveal shape, but also produces less error compared to the state-of-the-art methods. Finally, we apply the model in a comparison of healthy control eyes and eyes from patients with neuroinflammatory central nervous system disorders and optic neuritis, and show that several derived model parameters show significant differences between the two groups.
Collapse
Affiliation(s)
- Sunil Kumar Yadav
- NeuroCure Clinical Research Center, Charité - Universitätsmedizin Berlin,
Germany
- Mathematical Geometry Processing Group, Freie Universität Berlin,
Germany
| | | | - Timm Oberwahrenbrock
- NeuroCure Clinical Research Center, Charité - Universitätsmedizin Berlin,
Germany
| | | | - Konrad Polthier
- Mathematical Geometry Processing Group, Freie Universität Berlin,
Germany
| | - Friedemann Paul
- NeuroCure Clinical Research Center, Charité - Universitätsmedizin Berlin,
Germany
- Department of Neurology, Charité - Universitätsmedizin Berlin,
Germany
- Experimental and Clinical Research Center, Max Delbrück Center for Molecular Medicine and Charité - Universitätsmedizin Berlin,
Germany
| | - Ella Maria Kadas
- NeuroCure Clinical Research Center, Charité - Universitätsmedizin Berlin,
Germany
| | - Alexander U. Brandt
- NeuroCure Clinical Research Center, Charité - Universitätsmedizin Berlin,
Germany
| |
Collapse
|
22
|
The Edge Detectors Suitable for Retinal OCT Image Segmentation. JOURNAL OF HEALTHCARE ENGINEERING 2017; 2017:3978410. [PMID: 29065594 PMCID: PMC5585566 DOI: 10.1155/2017/3978410] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/04/2017] [Accepted: 07/19/2017] [Indexed: 11/18/2022]
Abstract
Retinal layer thickness measurement offers important information for reliable diagnosis of retinal diseases and for the evaluation of disease development and medical treatment responses. This task critically depends on the accurate edge detection of the retinal layers in OCT images. Here, we intended to search for the most suitable edge detectors for the retinal OCT image segmentation task. The three most promising edge detection algorithms were identified in the related literature: Canny edge detector, the two-pass method, and the EdgeFlow technique. The quantitative evaluation results show that the two-pass method outperforms consistently the Canny detector and the EdgeFlow technique in delineating the retinal layer boundaries in the OCT images. In addition, the mean localization deviation metrics show that the two-pass method caused the smallest edge shifting problem. These findings suggest that the two-pass method is the best among the three algorithms for detecting retinal layer boundaries. The overall better performance of Canny and two-pass methods over EdgeFlow technique implies that the OCT images contain more intensity gradient information than texture changes along the retinal layer boundaries. The results will guide our future efforts in the quantitative analysis of retinal OCT images for the effective use of OCT technologies in the field of ophthalmology.
Collapse
|
23
|
Novosel J, Vermeer KA, de Jong JH, van Vliet LJ. Joint Segmentation of Retinal Layers and Focal Lesions in 3-D OCT Data of Topologically Disrupted Retinas. IEEE TRANSACTIONS ON MEDICAL IMAGING 2017; 36:1276-1286. [PMID: 28186886 DOI: 10.1109/tmi.2017.2666045] [Citation(s) in RCA: 34] [Impact Index Per Article: 4.9] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/24/2023]
Abstract
Accurate quantification of retinal structures in 3-D optical coherence tomography data of eyes with pathologies provides clinically relevant information. We present an approach to jointly segment retinal layers and lesions in eyes with topology-disrupting retinal diseases by a loosely coupled level set framework. In the new approach, lesions are modeled as an additional space-variant layer delineated by auxiliary interfaces. Furthermore, the segmentation of interfaces is steered by local differences in the signal between adjacent retinal layers, thereby allowing the approach to handle local intensity variations. The accuracy of the proposed method of both layer and lesion segmentation has been evaluated on eyes affected by central serous retinopathy and age-related macular degeneration. In addition, layer segmentation of the proposed approach was evaluated on eyes without topology-disrupting retinal diseases. Good agreement between the segmentation performed manually by a medical doctor and results obtained from the automatic segmentation was found for all data types. The mean unsigned error for all interfaces varied between 2.3 and 11.9 μm (0.6-3.1 pixels). Furthermore, lesion segmentation showed a Dice coefficient of 0.68 for drusen and 0.89 for fluid pockets. Overall, the method provides a flexible and accurate solution to jointly segment lesions and retinal layers.
Collapse
|
24
|
Tan J, Yang Y, Jiang H, Liu C, Deng Z, Lam BL, Hu L, Oakley J, Wang J. The measurement repeatability using different partition methods of intraretinal tomographic thickness maps in healthy human subjects. Clin Ophthalmol 2016; 10:2403-2415. [PMID: 27942202 PMCID: PMC5136365 DOI: 10.2147/opth.s117494] [Citation(s) in RCA: 19] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/16/2022] Open
Abstract
Purpose To determine the repeatability and profiles with different partition methods in intraretinal thickness layers in healthy human subjects, using optical coherence tomography (OCT). Methods A custom-built ultrahigh-resolution OCT was used to acquire three-dimensional volume of the macula in 20 healthy subjects. The dataset was acquired twice using the macular cube 512×128 protocol in an area of 6×6 mm2 centered on the fovea. Commercially available segmentation software (Orion™) was used to segment the dataset into thickness maps of six intraretinal layers. The coefficient of repeatability and intraclass coefficient of correlation (ICC) were analyzed using hemispheric zoning and sectors defined by the Early Treatment Diabetic Retinopathy Study (ETDRS). Results All datasets were successfully segmented to create six thickness maps of individual intraretinal layers. Coefficients of repeatabilities of these layers in hemispheric zones ranged from 0.9 to 6.6 µm, with an average of 3.6 µm (standard deviation [SD] 1.4), which was not significantly different compared to ETDRS sectors (P>0.05). ICCs of these layers in hemispheric zones ranged from 0.68 to 0.99, with an average of 0.91 (SD 0.07). There were no significant differences in ICCs between two zoning methods (P>0.05). Significant variations of tomographic intraretinal thicknesses were found between the inner and outer annuli and among the quadrantal sectors within the inner and outer annuli (P<0.05). Significant variations of the quadrantal sectors including both inner and outer annuli were evident in intraretinal layers (P<0.05) except for the outer plexiform layer. Conclusion The measurement repeatabilities of tomographic thicknesses of intraretinal layers are comparable using both hemispheric and ETDRS partitions in volumetric data combined with the commercially available segmentation software. In keeping with known, normal anatomical variation, significant differences in tomographic thickness in various intraretinal layers were apparent in both hemispheric and ETDRS sectors.
Collapse
Affiliation(s)
- Jia Tan
- Department of Ophthalmology, Xiangya Hospital, Changsha, Hunan, People's Republic of China; Bascom Palmer Eye Institute, University of Miami, Miami, FL, USA
| | - Ye Yang
- Bascom Palmer Eye Institute, University of Miami, Miami, FL, USA; School of Ophthalmology and Optometry, Wenzhou Medical University, Wenzhou, Zhejiang, People's Republic of China
| | - Hong Jiang
- Bascom Palmer Eye Institute, University of Miami, Miami, FL, USA; Department of Neurology, University of Miami, Miami, FL
| | - Che Liu
- Bascom Palmer Eye Institute, University of Miami, Miami, FL, USA
| | - Zhihong Deng
- Department of Ophthalmology, Xiangya Hospital, Changsha, Hunan, People's Republic of China; Bascom Palmer Eye Institute, University of Miami, Miami, FL, USA
| | - Byron L Lam
- Bascom Palmer Eye Institute, University of Miami, Miami, FL, USA
| | - Liang Hu
- School of Ophthalmology and Optometry, Wenzhou Medical University, Wenzhou, Zhejiang, People's Republic of China
| | | | - Jianhua Wang
- Bascom Palmer Eye Institute, University of Miami, Miami, FL, USA
| |
Collapse
|
25
|
Fu D, Tong H, Zheng S, Luo L, Gao F, Minar J. Retinal status analysis method based on feature extraction and quantitative grading in OCT images. Biomed Eng Online 2016; 15:87. [PMID: 27449218 PMCID: PMC4957358 DOI: 10.1186/s12938-016-0206-x] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2016] [Accepted: 07/10/2016] [Indexed: 11/18/2022] Open
Abstract
Background Optical coherence tomography (OCT) is widely used in ophthalmology for viewing the morphology of the retina, which is important for disease detection and assessing therapeutic effect. The diagnosis of retinal diseases is based primarily on the subjective analysis of OCT images by trained ophthalmologists. This paper describes an OCT images automatic analysis method for computer-aided disease diagnosis and it is a critical part of the eye fundus diagnosis. Methods This study analyzed 300 OCT images acquired by Optovue Avanti RTVue XR (Optovue Corp., Fremont, CA). Firstly, the normal retinal reference model based on retinal boundaries was presented. Subsequently, two kinds of quantitative methods based on geometric features and morphological features were proposed. This paper put forward a retinal abnormal grading decision-making method which was used in actual analysis and evaluation of multiple OCT images. Results This paper showed detailed analysis process by four retinal OCT images with different abnormal degrees. The final grading results verified that the analysis method can distinguish abnormal severity and lesion regions. This paper presented the simulation of the 150 test images, where the results of analysis of retinal status showed that the sensitivity was 0.94 and specificity was 0.92.The proposed method can speed up diagnostic process and objectively evaluate the retinal status. Conclusions This paper aims on studies of retinal status automatic analysis method based on feature extraction and quantitative grading in OCT images. The proposed method can obtain the parameters and the features that are associated with retinal morphology. Quantitative analysis and evaluation of these features are combined with reference model which can realize the target image abnormal judgment and provide a reference for disease diagnosis.
Collapse
Affiliation(s)
- Dongmei Fu
- School of Automation and Electrical Engineering, University of Science and Technology Beijing, Xueyuan Road 30, Haidian District, Beijing, China.
| | - Hejun Tong
- School of Automation and Electrical Engineering, University of Science and Technology Beijing, Xueyuan Road 30, Haidian District, Beijing, China
| | - Shuang Zheng
- School of Automation and Electrical Engineering, University of Science and Technology Beijing, Xueyuan Road 30, Haidian District, Beijing, China
| | - Ling Luo
- The 306th Hospital of People's Liberation Army, Beijing, China
| | - Fulin Gao
- The 306th Hospital of People's Liberation Army, Beijing, China
| | - Jiri Minar
- Dept. of Telecommunications, Faculty of Electrical Engineering and Communication, Brno University of Technology, Czech, Brno, Czech Republic
| |
Collapse
|