☆ 4.7 Article

Contextual Augmentation Based on Metric-Guided Features for Ocular Axial Length Prediction

MATHEMATICS (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Ophthalmology

Wide-field swept-source optical coherence tomography angiography in the assessment of retinal microvasculature and choroidal thickness in patients with myopia

Jade Y. Moon et al.

Summary: In this study, we used wide-field swept-source optical coherence tomography angiography to evaluate microvascular and chorioretinal changes in different stages of myopia. We found that high myopia was associated with a decrease in vessel density and vessel skeletonised density in all layers, as well as a decrease in retinal thickness and choroidal thickness. These findings provide insights into the progression of myopia and its potential vision-threatening complications.

BRITISH JOURNAL OF OPHTHALMOLOGY (2023)

添加到收藏夹

Article Mathematics

Designing the Architecture of a Convolutional Neural Network Automatically for Diabetic Retinopathy Diagnosis

Fahman Saeed et al.

Summary: Diabetic retinopathy (DR) is a leading cause of blindness in middle-aged diabetic patients, and regular screening using fundus imaging is crucial to detect complications and delay disease progression. To address the time-consuming and subjective nature of manual screening, a method for automatically customizing CNN models based on fundus image lesions is proposed, which outperforms existing pre-trained CNN models and other neural architecture search models.

MATHEMATICS (2023)

添加到收藏夹

Article Mathematics

Assisting Glaucoma Screening Process Using Feature Excitation and Information Aggregation Techniques in Retinal Fundus Images

Ali Raza et al.

Summary: The increasing prevalence of retinal diseases, specifically glaucoma, demands efficient automated methods for diagnosis. Current artificial intelligence-based approaches for glaucoma diagnosis have limitations in accuracy and efficiency due to challenges in segmentation caused by various factors. To address these issues, a novel feature excitation-based dense segmentation network (FEDS-Net) was developed. FEDS-Net utilizes feature excitation and information aggregation mechanisms to enhance the segmentation performance of optic cup (OC) and optic disc (OD). The proposed method achieved superior segmentation performance and computational efficiency compared to state-of-the-art methods.

MATHEMATICS (2023)

添加到收藏夹

Article Computer Science, Information Systems

DML-PL: Deep metric learning based pseudo-labeling framework for class imbalanced semi-supervised learning

Mi Yan et al.

Summary: This study proposes a deep metric learning-based pseudo-labeling (DML-PL) framework that addresses both class imbalance and insufficient labeled data problems. Through an iterative self-training strategy, a deep metric network is trained to learn compact feature representations of labeled and unlabeled data, generating reliable pseudo-labels and improving training accuracy.

INFORMATION SCIENCES (2023)

添加到收藏夹

Review Computer Science, Artificial Intelligence

Image Generation: A Review

Mohamed Elasri et al.

Summary: This paper presents the first comprehensive overview of existing image generation methods, describing the nature, data types, and objectives of each technique. It also discusses the approaches and datasets for each image generation category, and provides a comparison of performance and an insight into current challenges.

NEURAL PROCESSING LETTERS (2022)

添加到收藏夹

Article Computer Science, Information Systems

HistNet: Histogram-based convolutional neural network with Chi-squared deep metric learning for facial expression recognition

Hamid Sadeghi et al.

Summary: This paper proposes a deep histogram metric learning approach based on a Convolutional Neural Network (CNN) for facial expression recognition. By introducing a histogram calculation layer and a learnable matrix, the accuracy is improved and the proposed CNN outperforms state-of-the-art methods on multiple databases.

INFORMATION SCIENCES (2022)

添加到收藏夹

Article Mathematics

Deep Multi-Task Learning for an Autoencoder-Regularized Semantic Segmentation of Fundus Retina Images

Ge Jin et al.

Summary: This study proposes a novel encoder-decoder architecture based on the multi-task learning paradigm to address challenges in retinal blood vessel segmentation, including the lack of an effective framework to obtain and incorporate features with different spatial and semantic information at multiple levels, as well as the scarcity of high-quality blood vessel segmentation and edge region information. The model outperforms current state-of-the-art methods in extensive evaluations on three publicly accessible datasets.

MATHEMATICS (2022)

添加到收藏夹

Article Computer Science, Information Systems

Assessing the impact of data augmentation and a combination of CNNs on leukemia classification

Maila L. Claro et al.

Summary: This article evaluates the impact of widely applied techniques, including data augmentation and multilevel and ensemble configurations, in deep learning-based computer-aided diagnosis systems. The findings suggest that data augmentation techniques improve the performance of convolutional neural networks, and a combination of CNNs also enhances the classification results.

INFORMATION SCIENCES (2022)

添加到收藏夹

Review Chemistry, Analytical

Deep Learning for Diabetic Retinopathy Analysis: A Review, Research Challenges, and Future Directions

Muhammad Waqas Nadeem et al.

Summary: Deep learning has been widely applied in various fields, especially in image processing and bioinformatics. This article provides a comprehensive review of the development of deep learning in the analysis of diabetic retinopathy, including screening, segmentation, prediction, classification, and validation. It critically analyzes the relevant techniques, highlights their advantages and limitations, and identifies research gaps and future challenges.

SENSORS (2022)

添加到收藏夹

Review Computer Science, Artificial Intelligence

Custom Hardware Architectures for Deep Learning on Portable Devices: A Review

Kh Shahriya Zaman et al.

Summary: Recent advancements in deep learning applications have prompted researchers to reconsider hardware architecture to meet the demands of fast and efficient application-specific computations. The emergence of specialized DL processors has reduced reliance on cloud servers, improved privacy, reduced latency, and alleviated bandwidth congestion. As researchers explore various application-specific hardware architectures, new technologies and design considerations are being developed to enhance the performance and efficiency of DL tasks.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022)

添加到收藏夹

Article Ophthalmology

Myopia-related stepwise and quadrant retinal microvascular alteration and its correlation with axial length

Mingming Liu et al.

Summary: The study investigated retinal vascular alterations in patients with different degrees of myopia, finding a stepwise and quadrant alteration of retinal microvascular density from mild to extreme myopia, with axial length playing a stronger role in influencing microvascular density than spherical equivalent.

EYE (2021)

添加到收藏夹

Review Radiology, Nuclear Medicine & Medical Imaging

A review on medical imaging synthesis using deep learning and its clinical applications

Tonghe Wang et al.

Summary: This paper reviewed the recent developments of deep learning-based methods for medical imaging synthesis and its clinical applications, highlighting the challenges among the reviewed studies and providing discussions on them.

JOURNAL OF APPLIED CLINICAL MEDICAL PHYSICS (2021)

添加到收藏夹

Article Computer Science, Information Systems

A negative transfer approach to person re-identification via domain augmentation

Feng Chen et al.

Summary: This paper proposes an end-to-end joint representation learning framework for person re-identification (ReID) based on a novel data augmentation strategy. By generating augmented domains through image channel shuffling, a symmetric classification network is designed for ReID learning. Experimental results demonstrate the effectiveness and robustness of the proposed approach.

INFORMATION SCIENCES (2021)

添加到收藏夹

Article Computer Science, Information Systems

Multi-subject data augmentation for target subject semantic decoding with deep multi-view adversarial learning

Dan Li et al.

Summary: This study proposes a multi-subject fMRI data augmentation method that utilizes multiple subject-specific encoders, decoders, and discriminators to transform information, addressing feature mismatch and distribution mismatch issues, thereby enhancing the decoding accuracy of the target subject.

INFORMATION SCIENCES (2021)

添加到收藏夹

Article Mathematical & Computational Biology

RF-GANs: A Method to Synthesize Retinal Fundus Images Based on Generative Adversarial Network

Yu Chen et al.

Summary: This study introduces a method based on generative adversarial networks to address the issue of data imbalance in diabetic retinopathy, leading to improved accuracy of DR grading models.

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Ocular Axial Length Prediction Based on Visual Interpretation of Retinal Fundus Images via Deep Neural Network

Yeonwoo Jeong et al.

Summary: Ocular axial length (AL) is crucial for eye health and surgery preparation, and a deep learning method using fundus images to predict AL has shown high accuracy in experiments. By visualizing discriminative regions on input images, the study paves the way for future research by linking AL to the biological structure of eyes.

IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep metric learning for otitis media classification

Josefine Vilsboll Sundgaard et al.

Summary: This study proposes an automatic diagnostic algorithm for detecting otitis media based on deep metric learning, comparing different distance-based metric loss functions. The results are comparable to the best clinical experts, paving the way for more accurate and operator-independent diagnosis of otitis media.

MEDICAL IMAGE ANALYSIS (2021)

添加到收藏夹

Review Computer Science, Information Systems

Retinal Vessel Segmentation Using Deep Learning: A Review

Chunhui Chen et al.

Summary: This paper provides a comprehensive review of retinal blood vessel segmentation based on deep learning, emphasizing the importance of this field and the advantages of deep learning algorithms. It also offers insights into future research directions.

IEEE ACCESS (2021)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

Incorporating prior knowledge via volumetric deep residual network to optimize the reconstruction of sparsely sampled MRI

Yan Wu et al.

MAGNETIC RESONANCE IMAGING (2020)

添加到收藏夹

Article Computer Science, Information Systems

Arterial Spin Labeling Image Synthesis From Structural MRI Using Improved Capsule-Based Networks

Wei Huang et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Computer Science, Information Systems

Deep Metric Learning Based Citrus Disease Classification With Sparse Data

Sivasubramaniam Janarthan et al.

IEEE ACCESS (2020)

添加到收藏夹

Review Ophthalmology

The Complications of Myopia: A Review and Meta-Analysis

Annechien E. G. Haarman et al.

INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE (2020)

添加到收藏夹

Review Computer Science, Artificial Intelligence

An Introductory Review of Deep Learning for Prediction Models With Big Data

Frank Emmert-Streib et al.

FRONTIERS IN ARTIFICIAL INTELLIGENCE (2020)

添加到收藏夹

Review Computer Science, Information Systems

A State-of-the-Art Review on Image Synthesis With Generative Adversarial Networks

Lei Wang et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

Generation of PET Attenuation Map for Whole-Body Time-of-Flight 18F-FDG PET/MRI Using a Deep Neural Network Trained with Simultaneously Reconstructed Activity and Attenuation Maps

Donghwi Hwang et al.

JOURNAL OF NUCLEAR MEDICINE (2019)

添加到收藏夹

Article Ophthalmology

A Deep Learning Algorithm to Quantify Neuroretinal Rim Loss From Optic Disc Photographs

Atalie C. Thompson et al.

AMERICAN JOURNAL OF OPHTHALMOLOGY (2019)

添加到收藏夹

Article Engineering, Biomedical

Whole-body PET estimation from low count statistics using cycle-consistent generative adversarial networks

Yang Lei et al.

PHYSICS IN MEDICINE AND BIOLOGY (2019)

添加到收藏夹

Article Computer Science, Information Systems

Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening

Tao Li et al.

INFORMATION SCIENCES (2019)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

Deep-Neural-Network-Based Sinogram Synthesis for Sparse-View CT Image Reconstruction

Hoyeon Lee et al.

IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES (2019)

添加到收藏夹

Article Computer Science, Theory & Methods

A survey on Image Data Augmentation for Deep Learning

Connor Shorten et al.

JOURNAL OF BIG DATA (2019)

添加到收藏夹

Article Computer Science, Information Systems

Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images

U. Raghavendra et al.

INFORMATION SCIENCES (2018)

添加到收藏夹

Article Computer Science, Information Systems

Automated segmentation of exudates, haemorrhages, microaneurysms using single convolutional neural network

Jen Hong Tan et al.

INFORMATION SCIENCES (2017)

添加到收藏夹

Article Ophthalmology

Retinal Microvasculature Alteration in High Myopia

Ye Yang et al.

INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE (2016)

添加到收藏夹

Article Ophthalmology

Long axial length as risk factor for normal tension glaucoma

Yoshiko Oku et al.

GRAEFES ARCHIVE FOR CLINICAL AND EXPERIMENTAL OPHTHALMOLOGY (2009)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.