23 December 2013 in Biomedical Optics Express
We present a method, based on a single scattering model, to calculate the attenuation coefficient of each pixel in optical coherence tomography (OCT) depth profiles. Numerical simulations were used to determine the model’s response to different depths and attenuation coefficients. Experiments were performed on uniform and layered phantoms with varying attenuation coefficients. They were measured by a 1300 nm OCT system and their attenuation coefficients were evaluated by our proposed method and by fitting the OCT slope as the gold standard. Both methods showed largely consistent results for the uniform phantoms. On the layered phantom, only our proposed method accurately estimated the attenuation coefficients. For all phantoms, the proposed method largely reduced the variability of the estimated attenuation coefficients. The method was illustrated on an in-vivo retinal OCT scan, effectively removing common imaging artifacts such as shadowing. By providing localized, per-pixel attenuation coefficients, this method enables tissue characterization based on attenuation coefficient estimates from OCT data.
27 May 2011 in Biomedical Optics Express
Current OCT devices provide three-dimensional (3D) in-vivo images of the human retina. The resulting very large data sets are difficult to manually assess. Automated segmentation is required to automatically process the data and produce images that are clinically useful and easy to interpret. In this paper, we present a method to segment the retinal layers in these images. Instead of using complex heuristics to define each layer, simple features are defined and machine learning classifiers are trained based on manually labeled examples. When applied to new data, these classifiers produce labels for every pixel. After regularization of the 3D labeled volume to produce a surface, this results in consistent, three-dimensionally segmented layers that match known retinal morphology. Six labels were defined, corresponding to the following layers: Vitreous, retinal nerve fiber layer (RNFL), ganglion cell layer & inner plexiform layer, inner nuclear layer & outer plexiform layer, photoreceptors & retinal pigment epithelium and choroid. For both normal and glaucomatous eyes that were imaged with a Spectralis (Heidelberg Engineering) OCT system, the five resulting interfaces were compared between automatic and manual segmentation. RMS errors for the top and bottom of the retina were between 4 and 6 μm, while the errors for intra-retinal interfaces were between 6 and 15 μm. The resulting total retinal thickness maps corresponded with known retinal morphology. RNFL thickness maps were compared to GDx (Carl Zeiss Meditec) thickness maps. Both maps were mostly consistent but local defects were better visualized in OCT-derived thickness maps.
1 April 2004 in Computers in Biology and Medicine
15 September 2023 in IEEE Transactions on Medical Imaging
The early detection of glaucoma is essential in preventing visual impairment. Artificial intelligence (AI) can be used to analyze color fundus photographs (CFPs) in a cost-effective manner, making glaucoma screening more accessible. While AI models for glaucoma screening from CFPs have shown promising results in laboratory settings, their performance decreases significantly in real-world scenarios due to the presence of out-of-distribution and low-quality images. To address this issue, we propose the Artificial Intelligence for Robust Glaucoma Screening (AIROGS) challenge. This challenge includes a large dataset of around 113,000 images from about 60,000 patients and 500 different screening centers, and encourages the development of algorithms that are robust to ungradable and unexpected input data. We evaluated solutions from 14 teams in this paper and found that the best teams performed similarly to a set of 20 expert ophthalmologists and optometrists. The highest-scoring team achieved an area under the receiver operating characteristic curve of 0.99 (95% CI: 0.98-0.99) for detecting ungradable images on-the-fly. Additionally, many of the algorithms showed robust performance when tested on three other publicly available datasets. These results demonstrate the feasibility of robust AI-enabled glaucoma screening.
1 September 2012 in Investigative Ophthalmology & Visual Science
Purpose. We present spatial retinal nerve fiber layer (RNFL) attenuation coefficient maps for healthy and glaucomatous eyes based on optical coherence tomography (OCT) measurements. Quantitative analyses of differences between healthy and glaucomatous eyes were performed. Methods. Peripapillary volumetric images of 10 healthy and 8 glaucomatous eyes were acquired by a Spectralis OCT system. Per A-line, the attenuation coefficient of the RNFL was determined based on a method that uses the retinal pigment epithelium as a reference layer. The attenuation coefficient describes the attenuation of light in tissue due to scattering and absorption. En-face maps were constructed and visually inspected. Differences between healthy and glaucomatous eyes were analyzed (Mann-Whitney U test), both globally (average values) and spatially (concentric and per segment). Results. RNFL attenuation coefficient maps of healthy eyes showed relatively high and uniform values. For glaucomatous eyes, the attenuation coefficients were much lower and showed local defects. Normal and glaucomatous average RNFL attenuation coefficients were highly significantly different (P < 0.0001) and fully separable. The RNFL attenuation coefficient decreased with increasing optic nerve head distance for both groups, with highly significant differences for all distances (P < 0.001). The angular dependency showed high superio- and inferiotemporal and low nasal values, with most significant differences superio- and inferiotemporally. Conclusions. Maps of RNFL attenuation coefficients provide a novel way of assessing the health of the RNFL and are relatively insensitive to imaging artifacts affecting signal intensity. The highly significant difference between normal and glaucomatous eyes suggests using RNFL attenuation coefficient maps as a new clinical tool for diagnosing and monitoring glaucoma.
15 September 2017 in IEEE Transactions on Biomedical Engineering
People with diabetes mellitus need annual screening to check for the development of diabetic retinopathy. Tracking small retinal changes due to early diabetic retinopathy lesions in longitudinal fundus image sets is challenging due to intra- and inter-visit variability in illumination and image quality, the required high registration accuracy, and the subtle appearance of retinal lesions compared to other retinal features. This paper presents a robust and flexible approach for automated detection of longitudinal retinal changes due to small red lesions by exploiting normalized fundus images that significantly reduce illumination variations and improve the contrast of small retinal features. To detect spatio-temporal retinal changes, the absolute difference between the extremes of the multiscale blobness responses of fundus images from two time-points is proposed as a simple and effective blobness measure. DR related changes are then identified based on several intensity and shape features by a support vector machine classifier. The proposed approach was evaluated in the context of a regular diabetic retinopathy screening program involving subjects ranging from healthy (no retinal lesion) to moderate (with clinically relevant retinal lesions) DR levels. Evaluation shows that the system is able to detect retinal changes due to small red lesions with a sensitivity of 80% at an average false positive rate of 1 and 2.5 lesions per eye on small and large fields-of-view of the retina, respectively.