The noise and redundant information are the main reasons for the performance bottleneck of medical image segmentation algorithms based on the deep learning. To this end, we propose a deep network embedded with rough fuzzy discretization (RFDDN) for OCT fundus image segmentation. Firstly, we establish the information decision table of OCT fundus image segmentation, and regard each category of segmentation region as a fuzzy set. Then, we use the fuzzy c-means clustering to get the membership degrees of pixels to each segmentation region. According to membership functions and the equivalence relation generated by the brightness attribute, we design the individual fitness function based on the rough fuzzy set, and use a genetic algorithm to search for the best breakpoints to discretize the features of OCT fundus images. Finally, we take the feature discretization based on the rough fuzzy set as the pre-module of the deep neural network, and introduce the deep supervised attention mechanism to obtain the important multi-scale information. We compare RFDDN with U-Net, ReLayNet, CE-Net, MultiResUNet, and ISCLNet on the two groups of 3D retinal OCT data. RFDDN is superior to the other five methods on all evaluation indicators. The results obtained by ISCLNet are the second only inferior to those obtained by RFDDN. DSC, sensitivity, and specificity of RFDDN are evenly 3.3%, 2.6%, and 7.1% higher than those of ISCLNet, respectively. HD95 and ASD of RFDDN are evenly 6.6% and 19.7% lower than those of ISCLNet, respectively. The experimental results show that our method can effectively eliminate the noise and redundant information in Oct fundus images, and greatly improve the accuracy of OCT fundus image segmentation while taking into account the interpretability and computational efficiency.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9822971 | PMC |
http://dx.doi.org/10.1038/s41598-023-27479-6 | DOI Listing |
Am J Ophthalmol Case Rep
December 2024
California Pacific Medical Center Department of Ophthalmology, 711 Van Ness, Suite 250, San Francisco, CA, 94102, USA.
Purpose: To report the case of a woman in her fifties whose presenting symptom of idiopathic intracranial hypertension was engorgement of the eyelid veins.
Observations: Bilateral engorged palpebral veins were visible through the skin. Dilated fundus examination revealed bilateral optic disc edema.
Eye (Lond)
January 2025
Save Sight Institute, Faculty of Medicine and Health, The University of Sydney, Sydney, NSW, Australia.
Purpose: To determine how Hardy-Rand-Rittler (HRR) colour vision testing correlates with visual functional and structural assessments in Cone and Cone-Rod Dystrophy.
Methods: Thirty-four Cone and 69 Cone-Rod Dystrophy patients diagnosed by electroretinography (ERG) at the Save Sight Institute in Sydney were included in a retrospective analysis. Each patient's HRR colour vision test scores were compared with markers of cone and rod system function including visual acuity (VA), ERG responses, changes on Spectral Domain Optical Coherence Tomography (OCT) and Fundus Autofluorescence.
Retin Cases Brief Rep
January 2025
New England Eye Center, Tufts Medical Center, Boston, MA.
Purpose: To describe a case of stellate multiform amelanotic choroidopathy (SMACH) with focal hyperfluorescence on indocyanine green angiography (ICGA).
Methods: Case report.
Results: A 19-year-old Caucasian woman was seen for an asymptomatic choroidal lesion.
Retin Cases Brief Rep
January 2025
Eye Clinic, Department of Biomedical and Clinical Sciences, Ospedale Luigi Sacco, University of Milan, Milan, Italy.
Purpose: To describe a rare complication in a patient with extensive macular atrophy with pseudodrusen-like appearance (EMAP), suggesting immune dysregulation in advanced stages of the disease.
Methods: Case Report. Multimodal imaging -including true-color fundus photography, blue autofluorescence, high-resolution optical coherence tomography (Hi-Res OCT), swept-source OCT angiography, and dye-based angiography- was used to evaluate retinal alterations.
Biomed Opt Express
January 2025
Department of Biomedical Engineering, University of Illinois Chicago, Chicago, IL 60607, USA.
The choroid, a critical vascular layer beneath the retina, is essential for maintaining retinal function and monitoring chorioretinal disorders. Existing imaging methods, such as indocyanine green angiography (ICGA) and optical coherence tomography (OCT), face significant limitations, including contrast agent requirements, restricted field of view (FOV), and high costs, limiting accessibility. To address these challenges, we developed a nonmydriatic, contrast agent-free fundus camera utilizing transcranial near-infrared (NIR) illumination.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!