[en] The foveola, the central region of the human retina, plays a crucial role in sharp color vision and is challenging to study due to its unique anatomy and technical limitations in imaging. We present ConeMapper, an open-source MATLAB software that integrates a fully convolutional neural network (FCN) for the automatic detection and analysis of cone photoreceptors in confocal adaptive optics scanning light ophthalmoscopy (AOSLO) images of the foveal center. The FCN was trained on a dataset of 49 healthy retinas and showed improved performance over previously published neural networks, particularly in the central fovea, achieving an [Formula: see text] score of 0.9769 across the validation set, critically reducing analysis time. In addition to automatic cone detection, ConeMapper provides efficient manual annotation tools, visualizations and topographical analysis, offering users detailed metrics for further analysis. ConeMapper is freely available, with ongoing development aimed at enhancing functionality and adaptability to different retinal imaging modalities.
Disciplines :
Computer science
Author, co-author :
Gutnikov, Aleksandr; Department of Ophthalmology, University Hospital Bonn, Bonn, 53127, Germany
Hähn-Schumacher, Patrick; b-it and Computer Science Department, University of Bonn, Bonn, 53115, Germany
Ameln, Julius; Department of Ophthalmology, University Hospital Bonn, Bonn, 53127, Germany
GORGI ZADEH, Shekoufeh ; University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > AI in Biomedical Imaging
Schultz, Thomas; b-it and Computer Science Department, University of Bonn, Bonn, 53115, Germany ; Lamarr Institute for Machine Learning and Artificial Intelligence
Harmening, Wolf; Department of Ophthalmology, University Hospital Bonn, Bonn, 53127, Germany. wolf.harmening@ukbonn.de
External co-authors :
yes
Language :
English
Title :
Neural network assisted annotation and analysis tool to study in-vivo foveolar cone photoreceptor topography.
Open Access funding enabled and organized by Projekt DEAL. Open Access funding enabled and organized by Projekt DEAL. Funded by the German Research Foundation (funding code 399370883), and by the Federal Ministry of Education and Research within the project \u201CBNTrAinee\u201D (funding code 16DHBK1022). This work was supported by the Open Access Publication Fund of the University of Bonn.
M. Poletti M. Rucci M. Carrasco Selective attention within the foveola Nat. Neurosci. 20 1413 1417 1:CAS:528:DC%2BC2sXhtlKjtbvN 10.1038/nn.4622 28805816 5929472
R. Sinha et al. Cellular and circuit mechanisms shaping the perceptual properties of the primate fovea Cell 168 413 426.e12 1:CAS:528:DC%2BC2sXhslaqsLg%3D 10.1016/j.cell.2017.01.005 28129540 5298833
Y. Wang et al. Human foveal cone photoreceptor topography and its dependence on eye length Elife 8 10.7554/eLife.47148 31348002 6660219 e47148
A. Bucci et al. Synchronization of visual perception within the human fovea Nat. Neurosc. 43 127 143
C. Yuodelis A. Hendrickson A qualitative and quantitative analysis of the human fovea during development Vision. Res. 26 847 855 1:STN:280:DyaL28zhslOntQ%3D%3D 10.1016/0042-6989(86)90143-4 3750868
M.A. Cohen T.L. Botch C.E. Robertson The limits of color awareness during active, real-world vision Proc. Natl. Acad. Sci. 117 13821 13827 2020PNAS.11713821C 1:CAS:528:DC%2BB3cXhtF2jtLrJ 10.1073/pnas.1922294117 32513698 7306755
C.A. Curcio O. Packer R.E. Kalina A whole mount method for sequential analysis of photoreceptor and ganglion cell topography in a single retina Vision. Res. 27 9 15 1:STN:280:DyaL2s3ptl2ksQ%3D%3D 10.1016/0042-6989(87)90137-4 3303679
A. Roorda J.L. Duncan Adaptive optics ophthalmoscopy Annual Review of Vision Science 1 19 50 10.1146/annurev-vision-082114-035357 26973867 4786023
S.A. Burns A.E. Elsner K.A. Sapoznik R.L. Warner T.J. Gast Adaptive optics imaging of the human retina Prog. Retin. Eye Res. 68 1 30 10.1016/j.preteyeres.2018.08.002 30165239
A. Dubra Y. Sulai Reflective afocal broadband adaptive optics scanning ophthalmoscope Biomed. Opt. Express 2 1757 1768 10.1364/BOE.2.001757 21698035 3114240
J. Ameln J.L. Reiniger K. Hess F.G. Holz W.M. Harmening Supernormal foveal photoreceptor density in alport syndrome: A case report Eur. J. Ophthalmol. 33 NP51 NP54 10.1177/11206721221093197 35410511
J. Kreis J. Carroll Applications of adaptive optics imaging for studying conditions affecting the fovea Annual Rev. Vis. Sci. 10 239 262 10.1146/annurev-vision-102122-100022
B. Moon et al. Alignment, calibration, and validation of an adaptive optics scanning laser ophthalmoscope for high-resolution human foveal imaging Appl. Opt. 63 730 742 2024ApOpt.63.730M 10.1364/AO.504283 38294386 11062499
A. Roorda Adaptive optics for studying visual function: A comprehensive review J. Vis. 11 6 10.1167/11.5.6 21680646
W.S. Tuten et al. Spatial summation in the human fovea: Do normal optical aberrations and fixational eye movements have an effect? J. Vis. 18 6 10.1167/18.8.6 30105385 6091889
J.L. Reiniger N. Domdei F.G. Holz W.M. Harmening Human gaze is systematically offset from the center of cone topography Curr. Biol. 31 4188 4193.e3 1:CAS:528:DC%2BB3MXhs12js77N 10.1016/j.cub.2021.07.005 34343479
J.L. Witten V. Lukyanova W.M. Harmening Sub-cone visual resolution by active, adaptive sampling in the human foveola Elife 13 RP98648 10.7554/eLife.98648 39468921 11521370
E. Yamada Some Structural Features of the Fovea Centralis in the Human Retina Arch. Ophthalmol. 82 151 159 1:STN:280:DyaF1M3ktVSksA%3D%3D 10.1001/archopht.1969.00990020153002 4183671
N. Domdei et al. Cone density is correlated to outer segment length and retinal thickness in the human foveola Invest. Ophthalmol. Vis. Sci. 64 11 10.1167/iovs.64.15.11 38064229 10709802
F.W. Campbell D.G. Green Optical and retinal factors affecting visual resolution J. Physiol. 181 576 593 1:STN:280:DyaF287it12hsg%3D%3D 10.1113/jphysiol.1965.sp007784 5880378 1357668
C.A. Curcio K.R. Sloan Packing geometry of human cone photoreceptors: Variation with eccentricity and evidence for local anisotropy Vis. Neurosci. 9 169 180 1:STN:280:DyaK38zmvFShsg%3D%3D 10.1017/S0952523800009639 1504026
D. Pum P.K. Ahnelt M. Grasl Iso-orientation areas in the foveal cone mosaic Vis. Neurosci. 5 511 523 1:STN:280:DyaK3M7pslOksQ%3D%3D 10.1017/S0952523800000687 2085468
N.M. Putnam D.X. Hammer Y. Zhang D. Merino A. Roorda Modeling the foveal cone mosaic imaged with adaptive optics scanning laser ophthalmoscopy Opt. Express 18 24902 24916 2010OExpr.1824902P 10.1364/OE.18.024902 21164835 3408900
A. Pallikaris D.R. Williams H. Hofer The reflectance of single cones in the living human eye Invest. Ophthalmol. Vis. Sci. 44 4580 4592 10.1167/iovs.03-0094 14507907
K.S. Bruce et al. Normal perceptual sensitivity arising from weakly reflective cone photoreceptors Invest. Ophthalmol. Vis. Sci. 56 4431 4438 10.1167/iovs.15-16547 26193919 4509056
A. Meadway L.C. Sincich Light reflectivity and interference in cone photoreceptors Biomed. Opt. Express 10 6531 6554 10.1364/BOE.10.006531 31853415 6913404
E. Bensinger Y. Wang A. Roorda Patches of dysflective cones in eyes with no known disease Invest. Ophthalmol. Vis. Sci. 63 29 29 10.1167/iovs.63.1.29 35072690 8802026
B. Xue S.S. Choi N. Doble J.S. Werner Photoreceptor counting and montaging of en-face retinal images from an adaptive optics fundus camera J. Opt. Soc. Am. A 24 1364 1372 2007JOSAA.24.1364X 10.1364/JOSAA.24.001364
Turpin, A, Morrow, P, Scotney, B, Anderson, R. & Wolsley, C. Automated identification of photoreceptor cones using multi-scale modelling and normalized cross-correlation. In Image Analysis and Processing - ICIAP 2011, 494–503 (Springer (eds Maino, G. & Foresti, G. L.) (Berlin Heidelberg, Berlin, Heidelberg, 2011).
R.F. Cooper G.K. Aguirre J.I.W. Morgan Fully automated estimation of spacing and density for retinal mosaics Translational Vision Science & Technology 8 26 10.1167/tvst.8.5.26
D. Cunefare et al. Open source software for automatic detection of cone photoreceptors in adaptive optics ophthalmoscopy using convolutional neural networks Sci. Rep. 7 6620 2017NatSR..7.6620C 1:CAS:528:DC%2BC1cXhtlemt7bP 10.1038/s41598-017-07103-0 28747737 5529414
B. Davidson et al. Automatic cone photoreceptor localisation in healthy and stargardt afflicted retinas using deep learning Sci. Rep. 8 7911 2018NatSR..8.7911D 1:CAS:528:DC%2BC1cXhslCmu7vL 10.1038/s41598-018-26350-3 29784939 5962538
J. Hamwood D. Alonso-Caneiro D.M. Sampson M.J. Collins F.K. Chen Automatic detection of cone photoreceptors with fully convolutional networks Translational Vision Science & Technology 8 10 10.1167/tvst.8.6.10
K. Li Q. Yin J. Ren H. Song J. Zhang Automatic quantification of cone photoreceptors in adaptive optics scanning light ophthalmoscope images using multi-task learning Biomed. Opt. Express 13 5187 5201 10.1364/BOE.471426 36425624 9664876
S. Wooning et al. Automated cone photoreceptor detection in adaptive optics flood illumination ophthalmoscopy Ophthalmology Science 5 10.1016/j.xops.2024.100675 40114708 100675
J.A. Cava et al. Assessing interocular symmetry of the foveal cone mosaic Investigative Ophthalmology & Visual Science 61 23 10.1167/iovs.61.14.23
J.I.W. Morgan M. Chen A.M. Huang Y.Y. Jiang R.F. Cooper Cone identification in choroideremia: Repeatability, reliability, and automation through use of a convolutional neural network Translational Vision Science & Technology 9 40 10.1167/tvst.9.2.40
N. Wynne et al. Intergrader agreement of foveal cone topography measured using adaptive optics scanning light ophthalmoscopy Biomed. Opt. Express 13 4445 4454 10.1364/BOE.460821 36032569 9408252
J. Ameln et al. In-vivo cone photoreceptor topography of the normal human foveola Investigative Ophthalmology & Visual Science 64 1040
N. Domdei et al. Ultra-high contrast retinal display system for single photoreceptor psychophysics Biomed. Opt. Express 9 157 172 1:CAS:528:DC%2BC1MXjt1ejsbg%3D 10.1364/BOE.9.000157 29359094
N. Domdei M. Linden J.L. Reiniger F.G. Holz W.M. Harmening Eye tracking-based estimation and compensation of chromatic offsets for multi-wavelength retinal microstimulation with foveal cone precision Biomed. Opt. Express 10 4126 4141 10.1364/BOE.10.004126 31452999 6701545
Stevenson, S. B, Roorda, A. & Kumar, G. Eye tracking with the adaptive optics scanning laser ophthalmoscope. In Proceedings of the 2010, Symposium on Eye-Tracking Research & Applications, ETRA ’10195–198, https://doi.org/10.1145/1743666.1743714 (Association for Computing Machinery, New York, NY, USA, 2010).
M. Chen et al. Multi-modal automatic montaging of adaptive optics retinal images Biomed. Opt. Express 7 4899 4918 1:CAS:528:DC%2BC1cXkslOhtLg%3D 10.1364/BOE.7.004899 28018714 5175540
Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Navab, N., Hornegger, J., Wells, W. M. & Frangi, A. F. (eds.) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, 234–241 (Springer International Publishing, Cham, 2015).
K. He, X. Zhang, S. Ren & J. Sun. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778, https://doi.org/10.1109/CVPR.2016.90(2016).
R.F. Cooper S. Kalaparambath G.K. Aguirre J.I.W. Morgan Morphology of the normative human cone photoreceptor mosaic and a publicly available adaptive optics montage repository Sci. Rep. 14 23166 1:CAS:528:DC%2BB2cXitFyltrjP 10.1038/s41598-024-74274-y 39369063 11455974
D. Scoles et al. In vivo imaging of human cone photoreceptor inner segments Investigative Ophthalmology & Visual Science 55 4244 4251 10.1167/iovs.14-14542
F. Felberer et al. Adaptive optics slo/oct for 3d imaging of human photoreceptors in vivo Biomed. Opt. Express 5 439 456 10.1364/BOE.5.000439 24575339 3920875
