Open source software for automatic detection of cone photoreceptors in adaptive optics ophthalmoscopy using convolutional neural networks
Abstract Imaging with an adaptive optics scanning light ophthalmoscope (AOSLO) enables direct visualization of the cone photoreceptor mosaic in the living human retina. Quantitative analysis of AOSLO images typically requires manual grading, which is time consuming, and subjective; thus, automated a...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2017-07-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-017-07103-0 |
| _version_ | 1818840728650907648 |
|---|---|
| author | David Cunefare Leyuan Fang Robert F. Cooper Alfredo Dubra Joseph Carroll Sina Farsiu |
| author_facet | David Cunefare Leyuan Fang Robert F. Cooper Alfredo Dubra Joseph Carroll Sina Farsiu |
| author_sort | David Cunefare |
| collection | DOAJ |
| description | Abstract Imaging with an adaptive optics scanning light ophthalmoscope (AOSLO) enables direct visualization of the cone photoreceptor mosaic in the living human retina. Quantitative analysis of AOSLO images typically requires manual grading, which is time consuming, and subjective; thus, automated algorithms are highly desirable. Previously developed automated methods are often reliant on ad hoc rules that may not be transferable between different imaging modalities or retinal locations. In this work, we present a convolutional neural network (CNN) based method for cone detection that learns features of interest directly from training data. This cone-identifying algorithm was trained and validated on separate data sets of confocal and split detector AOSLO images with results showing performance that closely mimics the gold standard manual process. Further, without any need for algorithmic modifications for a specific AOSLO imaging system, our fully-automated multi-modality CNN-based cone detection method resulted in comparable results to previous automatic cone segmentation methods which utilized ad hoc rules for different applications. We have made free open-source software for the proposed method and the corresponding training and testing datasets available online. |
| first_indexed | 2024-12-19T04:14:48Z |
| format | Article |
| id | doaj.art-e9741e0bd1954ed1a093b2300dddbf58 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-19T04:14:48Z |
| publishDate | 2017-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-e9741e0bd1954ed1a093b2300dddbf582022-12-21T20:36:20ZengNature PortfolioScientific Reports2045-23222017-07-017111110.1038/s41598-017-07103-0Open source software for automatic detection of cone photoreceptors in adaptive optics ophthalmoscopy using convolutional neural networksDavid Cunefare0Leyuan Fang1Robert F. Cooper2Alfredo Dubra3Joseph Carroll4Sina Farsiu5Department of Biomedical Engineering, Duke UniversityDepartment of Biomedical Engineering, Duke UniversityDepartment of Ophthalmology, Scheie Eye Institute, University of PennsylvaniaDepartment of Ophthalmology, Stanford UniversityDepartment of Biomedical Engineering, Marquette UniversityDepartment of Biomedical Engineering, Duke UniversityAbstract Imaging with an adaptive optics scanning light ophthalmoscope (AOSLO) enables direct visualization of the cone photoreceptor mosaic in the living human retina. Quantitative analysis of AOSLO images typically requires manual grading, which is time consuming, and subjective; thus, automated algorithms are highly desirable. Previously developed automated methods are often reliant on ad hoc rules that may not be transferable between different imaging modalities or retinal locations. In this work, we present a convolutional neural network (CNN) based method for cone detection that learns features of interest directly from training data. This cone-identifying algorithm was trained and validated on separate data sets of confocal and split detector AOSLO images with results showing performance that closely mimics the gold standard manual process. Further, without any need for algorithmic modifications for a specific AOSLO imaging system, our fully-automated multi-modality CNN-based cone detection method resulted in comparable results to previous automatic cone segmentation methods which utilized ad hoc rules for different applications. We have made free open-source software for the proposed method and the corresponding training and testing datasets available online.https://doi.org/10.1038/s41598-017-07103-0 |
| spellingShingle | David Cunefare Leyuan Fang Robert F. Cooper Alfredo Dubra Joseph Carroll Sina Farsiu Open source software for automatic detection of cone photoreceptors in adaptive optics ophthalmoscopy using convolutional neural networks Scientific Reports |
| title | Open source software for automatic detection of cone photoreceptors in adaptive optics ophthalmoscopy using convolutional neural networks |
| title_full | Open source software for automatic detection of cone photoreceptors in adaptive optics ophthalmoscopy using convolutional neural networks |
| title_fullStr | Open source software for automatic detection of cone photoreceptors in adaptive optics ophthalmoscopy using convolutional neural networks |
| title_full_unstemmed | Open source software for automatic detection of cone photoreceptors in adaptive optics ophthalmoscopy using convolutional neural networks |
| title_short | Open source software for automatic detection of cone photoreceptors in adaptive optics ophthalmoscopy using convolutional neural networks |
| title_sort | open source software for automatic detection of cone photoreceptors in adaptive optics ophthalmoscopy using convolutional neural networks |
| url | https://doi.org/10.1038/s41598-017-07103-0 |
| work_keys_str_mv | AT davidcunefare opensourcesoftwareforautomaticdetectionofconephotoreceptorsinadaptiveopticsophthalmoscopyusingconvolutionalneuralnetworks AT leyuanfang opensourcesoftwareforautomaticdetectionofconephotoreceptorsinadaptiveopticsophthalmoscopyusingconvolutionalneuralnetworks AT robertfcooper opensourcesoftwareforautomaticdetectionofconephotoreceptorsinadaptiveopticsophthalmoscopyusingconvolutionalneuralnetworks AT alfredodubra opensourcesoftwareforautomaticdetectionofconephotoreceptorsinadaptiveopticsophthalmoscopyusingconvolutionalneuralnetworks AT josephcarroll opensourcesoftwareforautomaticdetectionofconephotoreceptorsinadaptiveopticsophthalmoscopyusingconvolutionalneuralnetworks AT sinafarsiu opensourcesoftwareforautomaticdetectionofconephotoreceptorsinadaptiveopticsophthalmoscopyusingconvolutionalneuralnetworks |