Edinburgh Imaging

Menu

02 Feb 21. SINAPSE Image of the Month

Edinburgh Imaging is delighted to see that an image courtesy of Ylenia Giarratano, Dr Tom MacGillivray & Dr Miguel Bernabeu, from a recent paper, was featured as the SINAPSE Image of the Month for February 2021.

An original retinal image acquired using optical coherence tomography angiography (OCTA) technology, followed by the best segmentation approaches obtained applying three different vessel enhancement methods: optimally oriented flux (OOF), & two neural network architectures, U-Net & CS-Net.
An original retinal image acquired using optical coherence tomography angiography (OCTA) technology, followed by the best segmentation approaches obtained applying three different vessel enhancement methods: optimally oriented flux (OOF), & two neural network architectures, U-Net & CS-Net.

Courtesy of Ylenia Giarratano, Dr Tom MacGillivray & Dr Miguel Bernabeu, this image shows an original optical coherence tomography angiography (OCTA) image of the retina (left panel) acquired with the RTVue-XR Avanti OCT system, & the performance of three automated image segmentation methods used to perform vessel enhancement & binarization (right panels): an optimally oriented flux (OOF) handcrafted filter & two deep learning architectures, U-Net & CS-Net.

Evaluation metrics applied to automated segmentation results for retinal scan subimages from 11 individuals found the best performance was achieved by U-Net & CS-Net architectures, & identified OOF as the best handcrafted filter for applications where manually segmented data are not available to retrain those approaches.

The source code & the image dataset with associated ground truth manual segmentations have been made openly available to support standardization efforts in OCTA image segmentation.

 

The image is taken from a recent study published in Translational Vision Science & Technology:

Giarratano Y, Bianchi E, Gray C, Morris A, MacGillivray T, Dhillon B, Bernabeu MO. Automated Segmentation of Optical Coherence Tomography Angiography Images: Benchmark Data and Clinically Relevant Metrics. Transl Vis Sci Technol 2020; 9(13):5.

 

 

Social media tags & titles

Edinburgh Imaging is delighted to see that an image courtesy of Ylenia Giarratano, Dr Tom MacGillivray & Dr Miguel Bernabeu, from a recent paper, was featured as the SINAPSE Image of the Month for February 2021. #OCTA

@giaylenia @mobernabeu @SINAPSECENTRE