Abstract: A method of generating a segmentation confidence map by processing classification values each indicating a respective classification of a respective voxel of a retinal C-scan into a respective retinal layer class of a predefined set of retinal layer classes, the method comprising: generating, for each voxel, a respective confidence value which indicates a level of confidence in the classification of the voxel; for a retinal layer class of the predefined set, identifying a subset of the voxels such that the classification value generated for each voxel indicates a classification of the voxel into the retinal layer class; calculating, for each A-scan having voxels in the identified subset, a respective average of the confidence indicator values generated for the voxels; and using the calculated averages to generate the map, which indicates a spatial distribution of a level of confidence in the classification of the voxels.

Abstract: Aspects of the present invention relate to a method of detecting clipping of retinal image content in an optical coherence tomography, OCT, image of a patient’s retina. The method comprises detecting a boundary of the retinal image content in the OCT image and calculating a distance between the boundary and an edge of the OCT image. The method further comprises determining if clipping of the retinal image content in the OCT image has occurred by comparing the calculated distance between the boundary and the edge of the OCT image with a clipping threshold distance. Clipping of the retinal image content is determined to have occurred when the calculated distance between the boundary and the edge of the OCT image is equal to, or less than, the clipping threshold distance.

Abstract: An apparatus for generating an alert indicating an unreliability in a location of a landmark feature in a retinal image predicted by a machine learning algorithm, comprising: a receiver module which receives the predicted location; a probability indication determining module which uses the predicted location and a mixture model, which comprises a probability distribution of a landmark feature location and is based on determined locations of the landmark feature in retinal images having a plurality of retinal image classes, to determine, for each class, a respective probability indication indicating a probability that the retinal image belongs to the class; an outlier detector module which uses the probability indications to determine whether the retinal image is an outlier belonging to none of the classes; and an alert generator module which generates, when the retinal image belongs to none of the classes, an alert indicating unreliability of the predicted location.

Abstract: A method of generating a segmentation confidence map by processing classification values each indicating a respective classification of a respective voxel of a retinal C-scan into a respective retinal layer class of a predefined set of retinal layer classes, the method comprising: generating, for each voxel, a respective confidence value which indicates a level of confidence in the classification of the voxel; for a retinal layer class of the predefined set, identifying a subset of the voxels such that the classification value generated for each voxel indicates a classification of the voxel into the retinal layer class; calculating, for each A-scan having voxels in the identified subset, a respective average of the confidence indicator values generated for the voxels; and using the calculated averages to generate the map, which indicates a spatial distribution of a level of confidence in the classification of the voxels.

Abstract: An ocular imaging system comprising: an image acquisition module which acquires a retinal image; a landmark location prediction module which predicts locations of at least two landmarks in the retinal image; and an apparatus for alerting a user to an unreliability in at least one of the predicted locations. The apparatus receives the predicted first locations; uses the predicted locations to evaluate a distance metric indicative of a distance between the landmark features; use data indicative of a probability distribution of a distance between the landmark features obtained from measurements of the distance in retinal images different from the retinal image to determine an indication of whether the evaluated distance metric lies outside a predetermined interval about a peak the probability distribution; and generates an alert indicating the unreliability when the determined indication indicates that the evaluated distance metric lies outside the predetermined interval.