Retina layer segmentation using kernel graph cuts and continuous max-flow

Abstract

Circular scan Spectral-Domain Optic Coherence Tomography imaging (SD-OCT) is one of the best tools for diagnosis of retinal diseases. This technique provides more comprehensive detail of the retinal morphology and layers around the optic disc nerve head (ONH). Since manual labelling of the retinal layers can be tedious and time consuming, accurate and robust automated segmentation methods are needed to provide the thickness evaluation of these layers in retinal disorder assessments such as glaucoma. The proposed method serves this purpose by performing the segmentation of retinal layers boundaries in circular SD-OCT scans acquired around the ONH. The layers are detected by adapting a graph cut segmentation technique that includes a kernel-induced space and a continuous multiplier based max-flow algorithm. Results from scan images acquired with Spectralis (Heidelberg Engineering, Germany) prove that the proposed method is robust and efficient in detecting the retinal layers boundaries in images. With a mean root-mean-square error (RMSE) of 0.0835 ± 0.0495 and an average Dice coefficient of 0.9468 ± 0.0705 pixels for the retinal nerve fibre layer thickness, the proposed method demonstrated effective agreement with manual annotations.

Nephroblastoma Analysis in Mri Images

“…to apply constraints on the segmentation algorithms. These constraints can lead to segmentation errors when the algorithms are used on different image modalities (Kaba et al, 2015). Our segmentation method addresses these issues by using a prior knowledge including intensities variation of the tumour, which is manually selected by the user.…”

Automatic airway wall segmentation and thickness measurement for long-range optical coherence tomography images

“…The major feature of this algorithm when applied to edge detection is that it can preserved the continuity of the boundary, which means that it is less affected by outliers. Also, compared to other graph-based edge detection methods [25], the DP algorithm is an efficient graph solving method that has a quadratic time complexity.…”

Segmentation of thin corrugated layers in high-resolution OCT images

“…The first step of our algorithm, is based on an initial coarse segmentation with a conventional segmentation algorithm. We use GBS, which is a popular methodology for image segmentation in medical imaging [22][23][24], due to its uncomplicated implementation. The initial segmentation is used as an initialization for our second step, the matching layer attenuation coefficient segmentation (MLAS).…”