Literature DB >> 29302382

Beyond Retinal Layers: A Deep Voting Model for Automated Geographic Atrophy Segmentation in SD-OCT Images.

Zexuan Ji1, Qiang Chen1, Sijie Niu2, Theodore Leng3, Daniel L Rubin4,5.   

Abstract

PURPOSE: To automatically and accurately segment geographic atrophy (GA) in spectral-domain optical coherence tomography (SD-OCT) images by constructing a voting system with deep neural networks without the use of retinal layer segmentation.
METHODS: An automatic GA segmentation method for SD-OCT images based on the deep network was constructed. The structure of the deep network was composed of five layers, including one input layer, three hidden layers, and one output layer. During the training phase, the labeled A-scans with 1024 features were directly fed into the network as the input layer to obtain the deep representations. Then a soft-max classifier was trained to determine the label of each individual pixel. Finally, a voting decision strategy was used to refine the segmentation results among 10 trained models.
RESULTS: Two image data sets with GA were used to evaluate the model. For the first dataset, our algorithm obtained a mean overlap ratio (OR) 86.94% ± 8.75%, absolute area difference (AAD) 11.49% ± 11.50%, and correlation coefficients (CC) 0.9857; for the second dataset, the mean OR, AAD, and CC of the proposed method were 81.66% ± 10.93%, 8.30% ± 9.09%, and 0.9952, respectively. The proposed algorithm was capable of improving over 5% and 10% segmentation accuracy, respectively, when compared with several state-of-the-art algorithms on two data sets.
CONCLUSIONS: Without retinal layer segmentation, the proposed algorithm could produce higher segmentation accuracy and was more stable when compared with state-of-the-art methods that relied on retinal layer segmentation results. Our model may provide reliable GA segmentations from SD-OCT images and be useful in the clinical diagnosis of advanced nonexudative AMD. TRANSLATIONAL RELEVANCE: Based on the deep neural networks, this study presents an accurate GA segmentation method for SD-OCT images without using any retinal layer segmentation results, and may contribute to improved understanding of advanced nonexudative AMD.

Entities:  

Keywords:  deep network; geographic atrophy; image segmentation; spectral-domain optical coherence tomography; voting

Year:  2018        PMID: 29302382      PMCID: PMC5749649          DOI: 10.1167/tvst.7.1.1

Source DB:  PubMed          Journal:  Transl Vis Sci Technol        ISSN: 2164-2591            Impact factor:   3.283


  35 in total

1.  Stochastic speckle noise compensation in optical coherence tomography using non-stationary spline-based speckle noise modelling.

Authors:  Andrew Cameron; Dorothy Lui; Ameneh Boroomand; Jeffrey Glaister; Alexander Wong; Kostadinka Bizheva
Journal:  Biomed Opt Express       Date:  2013-08-28       Impact factor: 3.732

2.  Sensitivity of fluid detection in patients with neovascular amd using spectral domain optical coherence tomography high-definition line scans.

Authors:  Jennifer E De Niro; H Richard McDonald; Robert N Johnson; J Michael Jumper; Arthur D Fu; Emmett T Cunningham; Brandon J Lujan
Journal:  Retina       Date:  2014-06       Impact factor: 4.256

3.  Automated geographic atrophy segmentation for SD-OCT images using region-based C-V model via local similarity factor.

Authors:  Sijie Niu; Luis de Sisternes; Qiang Chen; Theodore Leng; Daniel L Rubin
Journal:  Biomed Opt Express       Date:  2016-01-20       Impact factor: 3.732

Review 4.  GEOGRAPHIC ATROPHY: Semantic Considerations and Literature Review.

Authors:  Steffen Schmitz-Valckenberg; Srinivas Sadda; Giovanni Staurenghi; Emily Y Chew; Monika Fleckenstein; Frank G Holz
Journal:  Retina       Date:  2016-12       Impact factor: 4.256

5.  Segmentation of the foveal microvasculature using deep learning networks.

Authors:  Pavle Prentašic; Morgan Heisler; Zaid Mammo; Sieun Lee; Andrew Merkur; Eduardo Navajas; Mirza Faisal Beg; Marinko Šarunic; Sven Loncaric
Journal:  J Biomed Opt       Date:  2016-07-01       Impact factor: 3.170

6.  Evaluation of semiautomated measurement of geographic atrophy in age-related macular degeneration by fundus autofluorescence in clinical setting.

Authors:  Christophe Panthier; Giuseppe Querques; Nathalie Puche; Valérie Le Tien; Rocio B Garavito; Stephane Béchet; Nathalie Massamba; Eric H Souied
Journal:  Retina       Date:  2014-03       Impact factor: 4.256

7.  Interactive segmentation for geographic atrophy in retinal fundus images.

Authors:  Noah Lee; R Theodore Smith; Andrew F Laine
Journal:  Conf Rec Asilomar Conf Signals Syst Comput       Date:  2008-10

8.  Automatic Feature Learning to Grade Nuclear Cataracts Based on Deep Learning.

Authors:  Xinting Gao; Stephen Lin; Tien Yin Wong
Journal:  IEEE Trans Biomed Eng       Date:  2015-06-11       Impact factor: 4.538

Review 9.  Deep Learning in Medical Image Analysis.

Authors:  Dinggang Shen; Guorong Wu; Heung-Il Suk
Journal:  Annu Rev Biomed Eng       Date:  2017-03-09       Impact factor: 9.590

10.  Fully Automated Prediction of Geographic Atrophy Growth Using Quantitative Spectral-Domain Optical Coherence Tomography Biomarkers.

Authors:  Sijie Niu; Luis de Sisternes; Qiang Chen; Daniel L Rubin; Theodore Leng
Journal:  Ophthalmology       Date:  2016-06-01       Impact factor: 12.079

View more
  16 in total

1.  Characterization of coronary artery pathological formations from OCT imaging using deep learning.

Authors:  Atefeh Abdolmanafi; Luc Duong; Nagib Dahdah; Ibrahim Ragui Adib; Farida Cheriet
Journal:  Biomed Opt Express       Date:  2018-09-21       Impact factor: 3.732

Review 2.  [Deep learning and neuronal networks in ophthalmology : Applications in the field of optical coherence tomography].

Authors:  M Treder; N Eter
Journal:  Ophthalmologe       Date:  2018-09       Impact factor: 1.059

3.  Deep learning approach for the detection and quantification of intraretinal cystoid fluid in multivendor optical coherence tomography.

Authors:  Freerk G Venhuizen; Bram van Ginneken; Bart Liefers; Freekje van Asten; Vivian Schreur; Sascha Fauser; Carel Hoyng; Thomas Theelen; Clara I Sánchez
Journal:  Biomed Opt Express       Date:  2018-03-07       Impact factor: 3.732

4.  Automatic geographic atrophy segmentation using optical attenuation in OCT scans with deep learning.

Authors:  Zhongdi Chu; Liang Wang; Xiao Zhou; Yingying Shi; Yuxuan Cheng; Rita Laiginhas; Hao Zhou; Mengxi Shen; Qinqin Zhang; Luis de Sisternes; Aaron Y Lee; Giovanni Gregori; Philip J Rosenfeld; Ruikang K Wang
Journal:  Biomed Opt Express       Date:  2022-02-07       Impact factor: 3.732

5.  Optical Coherence Tomography Measurements of the Retinal Pigment Epithelium to Bruch Membrane Thickness Around Geographic Atrophy Correlate With Growth.

Authors:  Zhongdi Chu; Yingying Shi; Xiao Zhou; Liang Wang; Hao Zhou; Rita Laiginhas; Qinqin Zhang; Yuxuan Cheng; Mengxi Shen; Luis de Sisternes; Mary K Durbin; William Feuer; Giovanni Gregori; Philip J Rosenfeld; Ruikang K Wang
Journal:  Am J Ophthalmol       Date:  2021-11-13       Impact factor: 5.258

6.  Beyond Performance Metrics: Automatic Deep Learning Retinal OCT Analysis Reproduces Clinical Trial Outcome.

Authors:  Jessica Loo; Traci E Clemons; Emily Y Chew; Martin Friedlander; Glenn J Jaffe; Sina Farsiu
Journal:  Ophthalmology       Date:  2019-12-23       Impact factor: 12.079

7.  Automatic Detection of Cone Photoreceptors With Fully Convolutional Networks.

Authors:  Jared Hamwood; David Alonso-Caneiro; Danuta M Sampson; Michael J Collins; Fred K Chen
Journal:  Transl Vis Sci Technol       Date:  2019-11-12       Impact factor: 3.283

8.  Expert-level Automated Biomarker Identification in Optical Coherence Tomography Scans.

Authors:  Thomas Kurmann; Siqing Yu; Pablo Márquez-Neila; Andreas Ebneter; Martin Zinkernagel; Marion R Munk; Sebastian Wolf; Raphael Sznitman
Journal:  Sci Rep       Date:  2019-09-19       Impact factor: 4.379

9.  Ensemble Deep Learning for Diabetic Retinopathy Detection Using Optical Coherence Tomography Angiography.

Authors:  Morgan Heisler; Sonja Karst; Julian Lo; Zaid Mammo; Timothy Yu; Simon Warner; David Maberley; Mirza Faisal Beg; Eduardo V Navajas; Marinko V Sarunic
Journal:  Transl Vis Sci Technol       Date:  2020-04-13       Impact factor: 3.283

10.  Microvasculature Segmentation and Intercapillary Area Quantification of the Deep Vascular Complex Using Transfer Learning.

Authors:  Julian Lo; Morgan Heisler; Vinicius Vanzan; Sonja Karst; Ivana Zadro Matovinović; Sven Lončarić; Eduardo V Navajas; Mirza Faisal Beg; Marinko V Šarunić
Journal:  Transl Vis Sci Technol       Date:  2020-07-10       Impact factor: 3.283

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.