Enhanced OCT chorio-retinal segmentation in low-data settings with semi-supervised GAN augmentation using cross-localisation

Article Biochemical Research Methods

Retinal layer segmentation in optical coherence tomography (OCT) using a 3D deep-convolutional regression network for patients with age-related macular degeneration

Ouvick Mukherjee et al.

Summary: Retinal layer segmentation in OCT images is an important method for disease detection and prognosis. This study proposes a semantic segmentation algorithm that utilizes the 3D spatial context from image volumes, achieving favorable results even for eyes with severe retinal diseases. The proposed method outperforms some state-of-the-art algorithms in terms of error metrics.

BIOMEDICAL OPTICS EXPRESS (2022)

添加到收藏夹

Article Ophthalmology

A review of generative adversarial network applications in optical coherence tomography image analysis

Jason Kugelman et al.

Summary: Optical coherence tomography (OCT) has revolutionized ophthalmic clinical practice and research with its ability to capture high-resolution images in a fast and non-invasive manner. Quantitative and automatic analysis of OCT images is crucial for providing clinicians with relevant metrics for best practice. Generative adversarial networks (GANs) have shown potential in providing more accurate and robust analyses for OCT image processing.

JOURNAL OF OPTOMETRY (2022)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Feasibility study to improve deep learning in OCT diagnosis of rare retinal diseases with few-shot classification

Tae Keun Yoo et al.

Summary: The study demonstrated the improvement of applying deep learning (DL) in diagnosing rare ophthalmic diseases through few-shot learning (FSL) using generative adversarial network (GAN). Synthetic images helped extract rare disease features and the DL model showed significant enhancement in OCT diagnosis, outperforming traditional models and reducing diagnosis delay.

MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Data augmentation for patch-based OCT chorio-retinal segmentation using generative adversarial networks

Jason Kugelman et al.

Summary: This study proposes using GANs to augment data for OCT chorio-retinal boundary segmentation, showing that models trained on synthetic data can perform comparably to those trained on real data. Data augmentation capabilities are demonstrated with improved classification performance realized on sparse datasets, highlighting the potential use of GANs in future work with chorio-retinal OCT images.

NEURAL COMPUTING & APPLICATIONS (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Automatic segmentation of retinal layers in OCT images with intermediate age-related macular degeneration using U-Net and DexiNed

Jefferson Alves Sousa et al.

Summary: This study focuses on patients with age-related macular degeneration, using optical coherence tomography and CAD systems, along with deep neural networks for segmentation of the inner limiting membrane, retinal pigment epithelium, and Bruch's membrane. Promising results were achieved with an average absolute error of 0.49 pixels for ILM, 0.57 for RPE, and 0.66 for BM.

PLOS ONE (2021)

添加到收藏夹

Article Biochemical Research Methods