Use of focus measure operators for characterization of flood illumination adaptive optics ophthalmoscopy image quality

Evaluation of focus and deep learning methods for automated image grading and factors influencing image quality in adaptive optics ophthalmoscopy

Adaptive optics flood illumination ophthalmoscopy (AO-FIO) is an established imaging tool in the investigation of retinal diseases. However, the clinical interpretation of AO-FIO images can be challenging due to varied image quality. Therefore, image quality assessment is essential before interpretation. An image assessment tool will also assist further work on improving the image quality, either during acquisition or post processing. In this paper, we describe, validate and compare two automated image quality assessment methods; the energy of Laplacian focus operator (LAPE; not commonly used but easily implemented) and convolutional neural network (CNN; effective but more complex approach). We also evaluate the effects of subject age, axial length, refractive error, fixation stability, disease status and retinal location on AO-FIO image quality. Based on analysis of 10,250 images of 50 × 50 μm size, at 41 retinal locations, from 50 subjects we demonstrate that CNN slightly outperforms LAPE in image quality assessment. CNN achieves accuracy of 89%, whereas LAPE metric achieves 73% and 80% (for a linear regression and random forest multiclass classifier methods, respectively) compared to ground truth. Furthermore, the retinal location, age and disease are factors that can influence the likelihood of poor image quality.

Measuring the spatial distribution of multiply scattered light using a de-scanned image sensor for examining retinal structure contrast

An optical platform is presented for examining intrinsic contrast detection strategies when imaging retinal structure using ex vivo tissue. A custom microscope was developed that scans intact tissue and collects scattered light distribution at every image pixel, allowing digital masks to be applied after image collection. With this novel approach at measuring the spatial distribution of multiply scattered light, known and novel methods of detecting intrinsic cellular contrast can be explored, compared, and optimized for retinal structures of interest.

Optical Incoherence Tomography: a method to generate tomographic retinal cross-sections with non-interferometric adaptive optics ophthalmoscopes

We present Optical Incoherence Tomography (OIT): a completely digital method to generate tomographic retinal cross-sections from en-face through-focus image stacks acquired by non-interferometric imaging systems, such as en-face adaptive optics (AO)-ophthalmoscopes. We demonstrate that OIT can be applied to different imaging modalities using back-scattered light, including systems without inherent optical sectioning and, for the first time, multiply-scattered light, revealing a distinctive cross-sectional view of the retina. The axial dimension of OIT cross-sections is given in terms of focus position rather than optical path, as in OCT. We explore this property to guide focus position in cases where the user is "blind" focusing, allowing precise plane selection for en-face imaging of retinal pigment epithelium, the vascular plexuses and translucent retinal neurons, such as photoreceptor inner segments and retinal ganglion cells, using respectively autofluorescence, motion contrast and split detection techniques.

Automatic Detection of Cone Photoreceptors With Fully Convolutional Networks

PURPOSE

To develop a fully automatic method, based on deep learning algorithms, for determining the locations of cone photoreceptors within adaptive optics scanning laser ophthalmoscope images and evaluate its performance against a dataset of manually segmented images.

METHODS

A fully convolutional network (FCN) based on U-Net architecture was used to generate prediction probability maps and then used a localization algorithm to reduce the prediction map to a collection of points. The proposed method was trained and tested on two publicly available datasets of different imaging modalities, with Dice overlap, false discovery rate, and true positive reported to assess performance.

RESULTS

The proposed method achieves a Dice coefficient of 0.989, true positive rate of 0.987, and false discovery rate of 0.009 on the first confocal dataset; and a Dice coefficient of 0.926, true positive rate of 0.909, and false discovery rate of 0.051 on the second split detector dataset. Results compare favorably with a previously proposed method, but this method provides quicker (25 times faster) evaluation performance.

CONCLUSIONS

The proposed FCN-based method demonstrates that deep learning algorithms can achieve accurate cone localizations, almost comparable to a human expert, while labeling the images.

TRANSLATIONAL RELEVANCE

Manual cone photoreceptor identification is a time-consuming task due to the large number of cones present within a single image; using the proposed FCN-based method could support the image analysis task, drastically reducing the need for manual assessment of the photoreceptor mosaic.