Article
Engineering, Biomedical
Ivo Soares, Miguel Castelo-Branco, Antonio Pinheiro
Summary: This paper proposes a new multi-scale algorithm for the automatic detection of microaneurysms in retinal fundus images. The method consists of three stages and achieves competitive results in microaneurysms detection and diabetic retinopathy detection.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Medicine, General & Internal
K. K. Mujeeb Rahman, Mohamed Nasor, Ahmed Imran
Summary: Diabetic retinopathy is a vision impairment caused by degeneration of blood vessels in the retina. It can lead to blindness and is associated with diabetes. Using pre-recorded digital fundus images and machine learning models, accurate predictions of diabetic retinopathy can be made.
Article
Health Care Sciences & Services
Usharani Bhimavarapu, Gopi Battineni
Summary: In this study, fuzzy logic techniques were incorporated into digital image processing for early detection of diabetic retinopathy (DR). The digital fundus images were segmented using particle swarm optimization, and probability-based clustering algorithms were compared with other fuzzy models. The proposed PSO algorithm achieved an accuracy of 99.9% in early detection of DR.
JOURNAL OF PERSONALIZED MEDICINE
(2022)
Article
Multidisciplinary Sciences
Summiya Batool, Syed Omer Gilani, Asim Waris, Khawaja Fahad Iqbal, Niaz B. Khan, M. Ijaz Khan, Sayed M. Eldin, Fuad A. Awwad
Summary: Diabetic retinopathy is a major cause of blindness worldwide. Efficient diabetic retinopathy detecting systems are urgently needed for early diagnosis and treatment. This study improves the accuracy and F1 score of the detection models by utilizing deep learning techniques and features extracted from fundus images.
SCIENTIFIC REPORTS
(2023)
Article
Engineering, Biomedical
Ghulam Ali, Aqsa Dastgir, Muhammad Waseem Iqbal, Muhammad Anwar, Muhammad Faheem
Summary: In this study, a novel approach using a convolutional neural network (CNN) model is proposed to detect diabetic retinopathy. The model extracts features using two different deep learning (DL) models, Resnet50 and Inceptionv3, and concatenates them before classification. Experimental results demonstrate that the proposed CNN model achieves higher accuracy, sensitivity, specificity, precision, and f1 score compared to state-of-the-art methods, with respective scores of 96.85%, 99.28%, 98.92%, 96.46%, and 98.65%.
IEEE JOURNAL OF TRANSLATIONAL ENGINEERING IN HEALTH AND MEDICINE
(2023)
Article
Computer Science, Information Systems
P. Saranya, R. Pranati, Sneha Shruti Patro
Summary: Diabetic retinopathy is an eye disease caused by diabetes mellitus that can lead to vision loss if not treated early. Manual diagnosis requires physical tests, which are time-consuming and costly. This study aims to develop an automated model using retinal images to detect early-stage diabetic retinopathy based on red lesions.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Ophthalmology
Prasanna Lakshmi Akella, R. Kumar
Summary: This article presents a computerized system for the analysis and assessment of diabetic retinopathy (DR) based on retinal fundus photographs. The researchers utilized the deep learning model YOLO V3 to recognize and classify DR. The results indicate that the suggested model performs better than existing models in terms of accuracy and implementation time.
GRAEFES ARCHIVE FOR CLINICAL AND EXPERIMENTAL OPHTHALMOLOGY
(2023)
Article
Chemistry, Analytical
Vidas Raudonis, Arturas Kairys, Rasa Verkauskiene, Jelizaveta Sokolovska, Goran Petrovski, Vilma Jurate Balciuniene, Vallo Volke
Summary: This study presents a novel method for automatically detecting microaneurysms in color fundus images. The proposed method consists of three main steps: image breakdown into smaller patches, inference to segmentation models, and reconstruction of the predicted segmentation map. The proposed segmentation method utilizes an ensemble of three different deep networks, including U-Net, ResNet34-UNet, and UNet++. The performance evaluation is based on Dice score and IoU values, and the ensemble-based model achieves higher scores compared to other network architectures. The proposed ensemble-based model demonstrates high potential for the practical application of early-stage diabetic retinopathy detection in color fundus images.
Article
Health Care Sciences & Services
Muhammad Arsalan, Adnan Haider, Jiho Choi, Kang Ryoung Park
Summary: Retinal blood vessels are important biomarkers for retinal disorders, and this paper proposes two shallow deep learning architectures for accurate detection. The proposed method utilizes semantic segmentation in raw color fundus images and achieves superior performance on multiple datasets.
JOURNAL OF PERSONALIZED MEDICINE
(2022)
Article
Biology
Muwei Jian, Hongyu Chen, Chen Tao, Xiaoguang Li, Gaige Wang
Summary: This article proposes a triple-cascade network model (Triple-DRNet) for efficient grading of diabetic retinopathy. The model uses three cascade networks to classify five types of diabetic retinopathy, and achieves improved classification performance.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Medicine, General & Internal
Sudhakar Tummala, Venkata Sainath Gupta Thadikemalla, Seifedine Kadry, Mohamed Sharaf, Hafiz Tayyab Rauf
Summary: Diabetic retinopathy (DR) is a major complication of diabetes and can be identified from retinal fundus images. This study proposes an automated method for quality estimation (QE) of digital fundus images using an ensemble of state-of-the-art EfficientNetV2 deep neural network models. The ensemble method achieves a test accuracy of 75% on the Deep Diabetic Retinopathy Image Dataset (DeepDRiD), outperforming existing methods. This proposed method could serve as a potential tool for automated QE of fundus images and be useful for ophthalmologists.
Article
Medicine, General & Internal
Usharani Bhimavarapu, Nalini Chintalapudi, Gopi Battineni
Summary: Diabetic retinopathy is a diabetes-related eye disease that can lead to blindness. Early diagnosis is crucial for avoiding blindness in diabetic patients. Deep learning, specifically the improved CNN model in this study, plays a significant role in automating the diagnosis of diabetic retinopathy from fundus images.
Article
Computer Science, Information Systems
Fahman Saeed, Muhammad Hussain, Hatim A. Aboalsamh
Summary: By employing transfer learning with a pre-trained CNN model, this study successfully conducted automatic DR screening on fundus images, effectively avoiding overfitting and improving screening efficiency.
Article
Computer Science, Artificial Intelligence
Yanfei Guo, Yanjun Peng
Summary: Diabetic retinopathy is a major cause of blindness in the working population. This study proposes a cascade attentive RefineNet (CARNet) for automatic and accurate lesion segmentation. CARNet utilizes both global and local information, attention mechanism, and multi-scale information fusion to achieve accurate predictions and preserve details and shape features.
COMPLEX & INTELLIGENT SYSTEMS
(2022)
Article
Engineering, Biomedical
Guanghui Yue, Yuan Li, Tianwei Zhou, Xiaoyan Zhou, Yun Liu, Tianfu Wang
Summary: This paper proposes an end-to-end Attention-Driven Cascaded Network (ADCNet) for automatic grading of diabetic retinopathy (DR) from retinal fundus images. It extracts lesion-aware information using a hybrid attention module and an attention-driven aggregation strategy, achieving accurate DR grading.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Artificial Intelligence
Bedour Alrayes, Ozgur Kafali, Kostas Stathis
KNOWLEDGE AND INFORMATION SYSTEMS
(2018)
Article
Chemistry, Analytical
I. Gonzalez-Reolid, J. Carlos Molina-Molina, A. Guerrero-Gonzalez, F. J. Ortiz, D. Alonso
Article
Computer Science, Artificial Intelligence
Nikos Dipsis, Kostas Stathis
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
(2020)
Article
Chemistry, Multidisciplinary
Pedro Sanchez, Diego Alonso
Summary: Quantum programming is considered one of the most promising areas in computer science, with a significant growth in quantum programming languages in recent years. The software engineering community is adapting quickly to the new paradigm, developing tailored tools and methods for quantum programming. The conceptual differences between classical and quantum computing require careful consideration in establishing a solid framework for quantum software engineering.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Interdisciplinary Applications
Diego Alonso, Pedro Sanchez, Francisco Sanchez-Rubio
Summary: The development of quantum programs has become reality as a result of rapid advances in quantum computing. This paper introduces a systematic approach using Model-Driven Engineering techniques to simplify the generation of quantum programs for solving the satisfiability problem. A metamodel for representing quantum circuits and a model-to-text transformation for generating IBM Qiskit code are proposed. Formulas for calculating the number of required quantum elements from SAT equations are also provided, which is crucial given the current limited quantum resources.
ADVANCES IN ENGINEERING SOFTWARE
(2022)
Article
Chemistry, Multidisciplinary
Tanya Suarez, Andres Iborra, Diego Alonso, Barbara alvarez
Summary: Like many other economic sectors, start-up accelerators have been heavily impacted by the COVID-19 crisis, leading them to find urgent and innovative solutions to adapt to the new environment. The challenges brought by this enforced change have been exacerbated by the sudden economic slowdown, but it has also become clear that the accelerated digital transformation has opened up new opportunities for accelerators to enhance their programs.
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Multidisciplinary
Diego Alonso, Pedro Sanchez, Barbara Alvarez
Summary: The article focuses on the crucial task of defining a unified metamodel for modeling quantum circuits, which is essential for further developing model-driven quantum software development frameworks. It proposes five strategies for using the metamodel and provides examples of its application, along with an analysis of their suitability and constraints.
APPLIED SCIENCES-BASEL
(2023)
Article
Quantum Science & Technology
Mathieu Kessler, Diego Alonso, Pedro Sanchez
Summary: This paper studies the distribution of the required number of shots to find solutions in Grover's quantum search algorithm. It presents formulas to compute the number of shots needed and derives a probability mass function to assess the validity of the asymptotic approximations. A rule of thumb is proposed for choosing between the two approaches.
EPJ QUANTUM TECHNOLOGY
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Benedict Wilkins, Chris Watkins, Kostas Stathis
2020 IEEE CONFERENCE ON GAMES (IEEE COG 2020)
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Quentin Baert, Anne-Cecile Caron, Maxime Morge, Jean-Christophe Routier, Kostas Stathis
2019 IEEE 31ST INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2019)
(2019)
Proceedings Paper
Computer Science, Theory & Methods
Quentin Baert, Anne-Cecile Caron, Maxime Morge, Jean-Christophe Routier, Kostas Stathis
AAMAS '19: PROCEEDINGS OF THE 18TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS
(2019)
Article
Business
Jack Hopkins, Ozgur Kafali, Bedour Alrayes, Kostas Stathis
ELECTRONIC MARKETS
(2019)
Proceedings Paper
Engineering, Electrical & Electronic
Andres Iborra, Pedro Sanchez, Juan A. Pastor, Diego Alonso, Tanya Suarez
2017 IEEE 26TH INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE)
(2017)
Article
Computer Science, Artificial Intelligence
Ozgur Kafali, Alfonso E. Romero, Kostas Stathis
COMPUTATIONAL INTELLIGENCE
(2017)
Proceedings Paper
Education & Educational Research
Diego Alonso, Andres Iborra, Pedro Sanchez, Francisco Requena
PROCEEDINGS OF 2017 IEEE GLOBAL ENGINEERING EDUCATION CONFERENCE (EDUCON2017)
(2017)