VMseg: Using spatial variance to automatically segment retinal non-perfusion on OCT-angiography

• Published in: PloS one Vol. 19; no. 8; p. e0306794
• Main Authors: LE BOITE, Hugo, COUTURIER, Aude, TADAYONI, Ramin, LAMARD, Mathieu, QUELLEC, Gwenolé
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 07.08.2024
• Subjects: Aged; Algorithms; Angiography; Angiography - methods; Biology and Life Sciences; Cataracts; Computer and Information Sciences; Convolution; Diabetes; Diabetes mellitus; Diabetic retinopathy; Diabetic Retinopathy - diagnostic imaging; Diabetics; Engineering and Technology; Engineering Sciences; Female; Fluorescein Angiography - methods; Humans; Image acquisition; Image processing; Image Processing, Computer-Assisted - methods; Image segmentation; Inference; Information processing; Ischemia; Life Sciences; Male; Medical imaging; Medical research; Medicine and Health Sciences; Medicine, Experimental; Methods; Middle Aged; Morphology; Parameters; Performance indices; Perfusion; Photomontage; Physical Sciences; Python; Research and Analysis Methods; Retina; Retina - diagnostic imaging; Retina - pathology; Retinal Vessels - diagnostic imaging; Retinopathy; Segmentation; Software; Technology application; Test sets; Testing; Tomography, Optical Coherence - methods; France
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0306794

To develop and test VMseg, a new image processing algorithm performing automatic segmentation of retinal non-perfusion in widefield OCT-Angiography images, in order to estimate the non-perfusion index in diabetic patients. We included diabetic patients with severe non-proliferative or proliferative diabetic retinopathy. We acquired images using the PlexElite 9000 OCT-A device with a photomontage of 5 images of size 12 x 12 mm. We then developed VMseg, a Python algorithm for non-perfusion detection, which binarizes a variance map calculated through convolution and morphological operations. We used 70% of our data set (development set) to fine-tune the algorithm parameters (convolution and morphological parameters, binarization thresholds) and evaluated the algorithm performance on the remaining 30% (test set). The obtained automatic segmentations were compared to a ground truth corresponding to manual segmentation from a retina expert and the inference processing time was estimated. We included 51 eyes of 30 patients (27 severe non-proliferative, 24 proliferative diabetic retinopathy). Using the optimal parameters found on the development set to tune the algorithm, the mean dice for the test set was 0.683 (sd = 0.175). We found a higher dice coefficient for images with a higher area of retinal non-perfusion (rs = 0.722, p < 10-4). There was a strong correlation (rs = 0.877, p < 10-4) between VMseg estimated non-perfusion indexes and indexes estimated using the ground truth segmentation. The Bland-Altman plot revealed that 3 eyes (5.9%) were significantly under-segmented by VMseg. We developed VMseg, an automatic algorithm for retinal non-perfusion segmentation on 12 x 12 mm OCT-A widefield photomontages. This simple algorithm was fast at inference time, segmented images in full-resolution and for the OCT-A format, was accurate enough for automatic estimation of retinal non-perfusion index in diabetic patients with diabetic retinopathy.