Journal
BIOMEDICINES
Volume 10, Issue 6, Pages -Publisher
MDPI
DOI: 10.3390/biomedicines10061269
Keywords
optical coherence tomography segmentation; deep learning; diabetic macular edema; visual acuity
Categories
Funding
- Ministry of Science and Technology (Taiwan) [108-2813-C-075-001-B]
- Brain Research Center of National Yang-Ming University [109BRC-B701]
- Ministry of Science and Technology, Taiwan [MOST110-2221-E-A49A-504MY3]
- National Yang Ming Chiao Tung University Brain Research Center [111W32701]
- National Health Research Institutes [NHRI-EX111-11021EI]
- National Yang Ming Chiao Tung University from the Featured Areas Research Center Program [MOST111-2823-8-A49-001]
Ask authors/readers for more resources
This study proposes a modified U-net deep learning algorithm to segment fluid and the ellipsoid zone (EZ) from OCT images of patients with diabetic macular edema (DME). The model achieves high performance in segmenting these features and correlates EZ disruption with best corrected visual acuity (BCVA).
Diabetic macular edema (DME) is a highly common cause of vision loss in patients with diabetes. Optical coherence tomography (OCT) is crucial in classifying DME and tracking the results of DME treatment. The presence of intraretinal cystoid fluid (IRC) and subretinal fluid (SRF) and the disruption of the ellipsoid zone (EZ), which is part of the photoreceptor layer, are three crucial factors affecting the best corrected visual acuity (BCVA). However, the manual segmentation of retinal fluid and the EZ from retinal OCT images is laborious and time-consuming. Current methods focus only on the segmentation of retinal features, lacking a correlation with visual acuity. Therefore, we proposed a modified U-net, a deep learning algorithm, to segment these features from OCT images of patients with DME. We also correlated these features with visual acuity. The IRC, SRF, and EZ of the OCT retinal images were manually labeled and checked by doctors. We trained the modified U-net model on these labeled images. Our model achieved Sorensen-Dice coefficients of 0.80 and 0.89 for IRC and SRF, respectively. The area under the receiver operating characteristic curve (ROC) for EZ disruption was 0.88. Linear regression indicated that EZ disruption was the factor most strongly correlated with BCVA. This finding agrees with that of previous studies on OCT images. Thus, we demonstrate that our segmentation network can be feasibly applied to OCT image segmentation and assist physicians in assessing the severity of the disease.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available