98%
921
2 minutes
20
Deep learning-based approaches, which learn pixel-to-pixel mapping from input to output images, have demonstrated exceptional performance in enhancing low-quality fundus images. However, due to the ambiguous definition of the ground-truth high-quality image, the pixel-to-pixel mapping encounters an ill-posed problem arising from the complex one-to-many relationship between low-quality fundus images and their corresponding high-quality versions. To address this problem, this work proposes a PCFlow, the first normalizing flow method that learns the complex distributions of high-quality fundus images rather than a pixel-to-pixel mapping. Unlike the existing image natural enhancement methods that aim to restore images with comfortable visual quality, PCFlow enhances fundus images by prioritizing clinically significant information. To this end, we design a condition module that utilizes retinal structure as a conditioning factor to constrain the optimization of PCFlow, and then build an invertible coupling layer that employs a pyramid structure for identifying each frequency component of retinal features. With the cooperation and interactions of these key components, the proposed PCFlow preserves the retinal structures and pathological characteristics essential for clinical applications. Extensive experiments on the real and synthetic fundus datasets demonstrate that our method achieves better performance.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1109/JBHI.2025.3600277 | DOI Listing |
Ann Anat
September 2025
Division of Anatomy, Department 1, Faculty of Dentistry, "Carol Davila" University of Medicine and Pharmacy, 050474 Bucharest, Romania. Electronic address:
Purpose: This study aimed to investigate the prevalence and anatomical patterns of temporal bone pneumatisation surrounding the internal acoustic meatus (IAM), specifically across its three anatomical regions: the porus acusticus internus (medial opening), the proper IAM (tubular midportion), and the fundus (lateral end). A secondary objective was to evaluate the association between pneumatisation and the thickness of the overlying tegmen in each region.
Methods: A total of 160 IAMs (80 patients, bilateral assessment) were analyzed using cone-beam computed tomography (CBCT).
Surv Ophthalmol
September 2025
University of Pittsburgh School of Medicine, Department of Medical Retina and Vitreoretinal Surgery, 203 Lothrop Street, Suite 800, Pittsburg, PA 15213.
Fundus tessellation (FT)-also referred to as tigroid or mosaic fundus-is characterized by increased visibility of underlying choroidal vessels. While often a physiological finding, FT may also signal early pathology in conditions such as high myopia, choroidal atrophy, or pigmentary disorders. We synthesize current understanding of the anatomical, optical, and imaging factors influencing FT appearance, including the roles of axial elongation, melanin distribution, and media clarity.
View Article and Find Full Text PDFPhotodiagnosis Photodyn Ther
September 2025
Department of Ophthalmology, People's Hospital of Feng Jie, Chongqing, 404600, China. Electronic address:
Objective: This study aims to develop a robust, multi-task deep learning framework that integrates vessel segmentation and radiomic analysis for the automated classification of four retinal conditions- diabetic retinopathy (DR), hypertensive retinopathy (HR), papilledema, and normal fundus-using fundus images.
Materials: AND.
Methods: A total of 2,165 patients from eight medical centers were enrolled.
Photodiagnosis Photodyn Ther
September 2025
State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular Diseases, Guangzhou, China. Electronic address:
Purpose: To characterize the cavity hyperreflective-content and septum's motion artifact (CHASMA) in en face optical coherence tomography angiography (OCTA) across multiple ocular fundus abnormalities.
Methods: This was a cross-sectional, observational study. Subjects with extravascular OCTA signals arising from the cavity's hyperreflective-content and/or septum were enrolled.
Int Ophthalmol
September 2025
Beijing Tongren Eye Center, Beijing Tongren Hospital, Beijing key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology and Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technolog
Purpose: To analyze macular microvascular networks and investigate correlations between visual acuity and quantitative parameters in patients with Leber's hereditary optic neuropathy (LHON) using optical coherence tomography angiography (OCTA).
Methods: An observational, cross-sectional study was conducted, including 25 eyes from 25 genetically confirmed chronic LHON patients and 25 eyes from 25 age-matched healthy controls. Images were obtained using a spectral domain OCTA system.