Unsupervised identification of cone photoreceptors in non-confocal adaptive optics scanning light ophthalmoscope images

Bergeles, Christos; Dubis, Adam M.; Davidson, Benjamin; Kasilian, Melissa; Kalitzeos, Angelos; Carroll, Joseph; Dubra, Alfredo; Michaelides, Michel; Ourselin, Sébastien

doi:10.1364/boe.8.003081

Cited by 29 publications

(26 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 1 – 3 Quantitative assessment of the mosaic through metrics on AO retinal images, such as cone density and spacing, has shown potential for clinical application 2 , 4 with substantial efforts already realized toward assembling normative databases. 5 – 12 To overcome the tedious task of manually identifying cones and to remove the variability of human graders, various automated algorithms have been developed for two types of AO modalities: confocal 13 – 16 and nonconfocal 17 – 19 AO scanning light ophthalmoscopy (AOSLO). However, most quantitative metrics have been based on representing each cone as a point.…”

mentioning

confidence: 99%

Cone Photoreceptor Cell Segmentation and Diameter Measurement on Adaptive Optics Images Using Circularly Constrained Active Contour Model

Liu

Jung

Dubra

et al. 2018

Invest. Ophthalmol. Vis. Sci.

Self Cite

View full text Add to dashboard Cite

PurposeCone photoreceptor cells can be noninvasively imaged in the living human eye by using nonconfocal adaptive optics scanning ophthalmoscopy split detection. Existing metrics, such as cone density and spacing, are based on simplifying cone photoreceptors to single points. The purposes of this study were to introduce a computer-aided approach for segmentation of cone photoreceptors, to apply this technique to create a normal database of cone diameters, and to demonstrate its use in the context of existing metrics.MethodsCone photoreceptor segmentation is achieved through a circularly constrained active contour model (CCACM). Circular templates and image gradients attract active contours toward cone photoreceptor boundaries. Automated segmentation from in vivo human subject data was compared to ground truth established by manual segmentation. Cone diameters computed from curated data (automated segmentation followed by manual removal of errors) were compared with histology and published data.ResultsOverall, there was good agreement between automated and manual segmentations and between diameter measurements (n = 5191 cones) and published histologic data across retinal eccentricities ranging from 1.35 to 6.35 mm (temporal). Interestingly, cone diameter was correlated to both cone density and cone spacing (negatively and positively, respectively; P < 0.01 for both). Application of the proposed automated segmentation to images from a patient with late-onset retinal degeneration revealed the presence of enlarged cones above individual reticular pseudodrusen (average 23.0% increase, P < 0.05).ConclusionsCCACM can accurately segment cone photoreceptors on split detection images across a range of eccentricities. Metrics derived from this automated segmentation of adaptive optics retinal images can provide new insights into retinal diseases.

show abstract

mentioning

confidence: 99%

Cone Photoreceptor Cell Segmentation and Diameter Measurement on Adaptive Optics Images Using Circularly Constrained Active Contour Model

Liu

Jung

Dubra

et al. 2018

Invest. Ophthalmol. Vis. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…There has already been extensive research on automating cone localisation in images of healthy retinas, with state-of-the-art algorithms obtaining similar-to-human performance 4 – 7 . Only recently, however, have researchers attempted to tackle the problem of automatically detecting photoreceptors in images acquired from retinas afflicted with pathologies.…”

Section: Introductionmentioning

confidence: 99%

Automatic Cone Photoreceptor Localisation in Healthy and Stargardt Afflicted Retinas Using Deep Learning

Davidson

Kalitzeos

Carroll

et al. 2018

Sci Rep

Self Cite

View full text Add to dashboard Cite

We present a robust deep learning framework for the automatic localisation of cone photoreceptor cells in Adaptive Optics Scanning Light Ophthalmoscope (AOSLO) split-detection images. Monitoring cone photoreceptors with AOSLO imaging grants an excellent view into retinal structure and health, provides new perspectives into well known pathologies, and allows clinicians to monitor the effectiveness of experimental treatments. The MultiDimensional Recurrent Neural Network (MDRNN) approach developed in this paper is the first method capable of reliably and automatically identifying cones in both healthy retinas and retinas afflicted with Stargardt disease. Therefore, it represents a leap forward in the computational image processing of AOSLO images, and can provide clinical support in on-going longitudinal studies of disease progression and therapy. We validate our method using images from healthy subjects and subjects with the inherited retinal pathology Stargardt disease, which significantly alters image quality and cone density. We conduct a thorough comparison of our method with current state-of-the-art methods, and demonstrate that the proposed approach is both more accurate and appreciably faster in localizing cones. As further validation to the method’s robustness, we demonstrate it can be successfully applied to images of retinas with pathologies not present in the training data: achromatopsia, and retinitis pigmentosa.

show abstract

“…Aside from difficulties in accurate cone identification, the impracticality of manual image grading by observers and its poor repeatability can also render metric applications as unreliable [95]. Recent efforts to produce automated analytic tools for AO images have shown promise in both confocal and non-confocal settings [119,120], with the latter being used in achromatopsia and Stargardt disease [121,122]. Although further work is needed to characterise the performance of these algorithms in relation to different metrics [123], this AO-FIO AOSLO Canal-like foveal schisis cavities seen, with a spoke wheel pattern of inner retinal folds.…”

Section: Limitations and Future Prospectsmentioning

confidence: 99%

Cellular imaging of inherited retinal diseases using adaptive optics

Gill¹,

Moosajee

Dubis

2019

Eye

Self Cite

View full text Add to dashboard Cite

Adaptive optics (AO) is an insightful tool that has been increasingly applied to existing imaging systems for viewing the retina at a cellular level. By correcting for individual optical aberrations, AO offers an improvement in transverse resolution from 10-15 μm to~2 μm, enabling assessment of individual retinal cell types. One of the settings in which its utility has been recognised is that of the inherited retinal diseases (IRDs), the genetic and clinical heterogeneity of which warrants better cellular characterisation. In this review, we provide a summary of the basic principles of AO, its integration into multiple retinal imaging modalities and its clinical applications, focusing primarily on IRDs. Furthermore, we present a comprehensive summary of AO-based cellular findings in IRDs according to their associated disease-causing genes.

show abstract

Unsupervised identification of cone photoreceptors in non-confocal adaptive optics scanning light ophthalmoscope images

Cited by 29 publications

References 23 publications

Cone Photoreceptor Cell Segmentation and Diameter Measurement on Adaptive Optics Images Using Circularly Constrained Active Contour Model

Cone Photoreceptor Cell Segmentation and Diameter Measurement on Adaptive Optics Images Using Circularly Constrained Active Contour Model

Automatic Cone Photoreceptor Localisation in Healthy and Stargardt Afflicted Retinas Using Deep Learning

Cellular imaging of inherited retinal diseases using adaptive optics

Contact Info

Product

Resources

About