A5075800476- Retinal Imaging and Analysis
- Optical Coherence Tomography Applications
- Retinal Diseases and Treatments
- Computational Drug Discovery Methods
- Protein Structure and Dynamics
- Advanced Neural Network Applications
- Manufacturing Process and Optimization
- Additive Manufacturing Materials and Processes
- Advanced MRI Techniques and Applications
- Additive Manufacturing and 3D Printing Technologies
- Metallurgy and Material Forming
- Digital Imaging for Blood Diseases
- Machine Learning in Bioinformatics
- Medical Image Segmentation Techniques
- Advanced X-ray and CT Imaging
- Welding Techniques and Residual Stresses
- Medical Imaging Techniques and Applications
- Neonatal and fetal brain pathology
- Radiomics and Machine Learning in Medical Imaging
- Non-Invasive Vital Sign Monitoring
- EEG and Brain-Computer Interfaces
- Epilepsy research and treatment
- MRI in cancer diagnosis
- Mineral Processing and Grinding
- Aluminum Alloy Microstructure Properties
University of Isfahan
2021-2024
Duke University
2020-2024
Pratt Institute
2020-2021
Isfahan University of Medical Sciences
2017-2019
K.N.Toosi University of Technology
2017
Computer-aided diagnosis (CAD) of retinal pathologies is a current active area in medical image analysis. Due to the increasing use optical coherence tomography (OCT) imaging technique, CAD system OCT essential assist ophthalmologist early detection ocular diseases and treatment monitoring. This paper presents novel based on multi-scale convolutional mixture expert (MCME) ensemble model identify normal retina, two common types macular pathologies, namely, dry age-related degeneration,...
Anti-vascular endothelial growth factor (VEGF) agents are widely regarded as the first line of therapy for diabetic macular edema (DME) but not universally effective. An automatic method that can predict whether a patient is likely to respond anti-VEGF avoid unnecessary trial and error treatment strategies promote selection more effective first-line therapies. The objective this study automatically efficacy DME in individual patients based on optical coherence tomography (OCT) images. We...
Optical coherence tomography (OCT) helps ophthalmologists assess macular edema, accumulation of fluids, and lesions at microscopic resolution. Quantification retinal fluids is necessary for OCT-guided treatment management, which relies on a precise image segmentation step. As manual analysis time-consuming, subjective, error-prone task, there increasing demand fast robust automatic solutions. In this study, new convolutional neural architecture named RetiFluidNet proposed multi-class fluid...
The present research intends to propose a fully automatic algorithm for the classification of three-dimensional (3-D) optical coherence tomography (OCT) scans patients suffering from abnormal macula normal candidates. method proposed does not require any denoising, segmentation, retinal alignment processes assess intraretinal layers, as well abnormalities or lesion structures. To classify cases control group, two-stage scheme was utilized, which consists subsystems adaptive feature learning...
Macular disorders, such as diabetic macular edema (DME) and age-related degeneration (AMD) are among the major ocular diseases. Having one of these diseases can lead to vision impairments or even permanent blindness in a not-so-long time span. So, early diagnosis main goals for researchers field.This study is designed order present comparative analysis on recent convolutional mixture experts (CMoE) models distinguishing normal OCT from DME AMD. For this purpose, we considered three CMoE...
Background: The first step in developing new drugs is to find binding sites for a protein structure that can be used as starting point design antagonists and inhibitors. methods relying on convolutional neural network the prediction of have attracted much attention. This study focuses use optimized three-dimensional (3D) non-Euclidean data. Methods: A graph, which made from 3D structure, fed proposed GU-Net model based graph operation. features each atom are considered attributes node....
This paper presents a new fully automatic algorithm for classification of 3D Optical Coherence Tomography (OCT) images as Age-related Macular Degeneration (AMD), Diabetic Edema (DME), and healthy people. The proposed does not need to any retinal layer alignment also segmentation processes (e.g., intra-retinal layers lesion structures). utilizes Wavelet-based Convolutional Mixture Experts (WCME) model an adaptive feature extraction method. WCME benefits from spatial-frequency decomposition...
One of the critical aspects structure-based drug design is to choose important druggable binding sites in protein’s crystallography structures. As experimental processes are costly and time-consuming, computational using machine learning algorithms recommended. Over recent years, deep methods have been utilized a wide variety research applications such as site prediction. In this study, new combination attention blocks 3D U-Net model based on semantic segmentation used improve localization...
Accurate segmentation of the hippocampus head and body from MR images is routinely performed to examine link between deformation neurological diseases, such as Alzheimer's epilepsy. State-of-the-art seminal methods (including segmentation) are based on deep learning algorithms. Most studies focused developing robust algorithms achieve satisfactory performance in segmentation. A critical aspect that has been overlooked these strategy adopted train when there two or more target structures. In...