Article
Computer Science, Hardware & Architecture
Mahmoud Ragab, Wajdi H. Aljedaibi, Alaa F. Nahhas, Ibrahim R. Alzahrani
Summary: This paper presents a deep learning-based computer aided diagnosis model for diabetic retinopathy detection and grading. The model includes preprocessing, image segmentation, feature extraction, and classification, and achieves high accuracy according to the performance validation on benchmark data set.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Computer Science, Information Systems
Munish Khanna, Law Kumar Singh, Shankar Thawkar, Mayur Goyal
Summary: Diabetic retinopathy is a major cause of irreversible blindness among diabetics due to damage to the retina's blood vessel networks. Early detection and treatment are crucial, and this article proposes reformed networks based on deep learning to effectively detect and categorize diabetic retinopathy.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Qaisar Abbas, Mostafa E. A. Ibrahim, Abdul Rauf Baig
Summary: This paper proposes a computer-aided diagnosis (CAD) system for diagnosing diabetic retinopathy (DR). The system uses preprocessing and a pre-train transfer learning-based convolutional neural network (PCNN) to recognize the five stages of DR. The results demonstrate that the CAD-DR system outperforms other state-of-the-art methods in terms of sensitivity, specificity, and accuracy, making it suitable for DR screening.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Computer Science, Artificial Intelligence
Francisco J. Martinez-Murcia, Andres Ortiz, Javier Ramirez, Juan M. Gorriz, Ricardo Cruz
Summary: The evaluation and diagnosis of retina pathology are commonly done through retinography, which presents challenges due to differences in image quality. This study introduces a computer aided diagnosis tool based on deep learning, utilizing a deep residual convolutional neural network to extract discriminatory features for automated image analysis. Experiments with different convolutional architectures show promising results, with a ResNet50-based model achieving high AUC values for different disease grades and binary classification.
Article
Computer Science, Interdisciplinary Applications
S. Sudharson, Priyanka Kokil
Summary: A computer-aided diagnosis system is proposed for detecting multi-class kidney abnormalities from ultrasound images. Using a deep learning network to remove speckle noise significantly improves the classification performance of the CAD system.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Computer Science, Artificial Intelligence
Mohammad H. Alshayeji, Sa'ed Abed, Silpa ChandraBhasi Sindhu
Summary: Diabetic retinopathy (DR), a common cause of vision loss, lacks early symptoms, making diagnosis difficult. A reliable machine learning model is proposed for early diagnosis and disease-stage screening. The framework achieves high accuracy and identifies relevant features for accurate diagnosis.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Laxmi Math, Ruksar Fatima
Summary: A segment based learning approach is proposed to detect diabetic retinopathy, showing better performance compared to existing models.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Mathematics
Muhammad Nadeem Ashraf, Muhammad Hussain, Zulfiqar Habib
Summary: Diabetic retinopathy (DR) is a vision-threatening complication, and a deep convolutional neural network (CNN) can effectively diagnose and screen DR patients. Training deep models with minimal data is challenging, but fine-tuning pre-trained CNNs and making architectural amendments can improve performance. The modified model (DR-ResNet50) outperforms state-of-the-art methods in terms of various metrics and shows high sensitivity and low false-positive rate in testing, demonstrating its value and suitability for early screening.
Article
Computer Science, Artificial Intelligence
Srinivas Naik, Deepthi Kamidi, Sudeepthi Govathoti, Ramalingaswamy Cheruku, A. Mallikarjuna Reddy
Summary: Diabetic retinopathy is a major disease that causes vision loss worldwide. This paper discusses a novel model that uses fundus images to detect the stages of DR in patients and classify them into five stages. The ability to quickly identify people with DR is beneficial for doctors and researchers.
Article
Computer Science, Information Systems
Mohammad Shorfuzzaman, M. Shamim Hossain, Abdulmotaleb El Saddik
Summary: This article proposes an explainable deep learning ensemble model for extracting features from retinal fundus images to diagnose the severity of DR. The model is trained on APTOS dataset using cyclical learning rates strategy and offers state-of-the-art diagnosis performance with high precision, sensitivity, and AUC. The model utilizes gradient-weighted class activation mapping and shapely adaptive explanations to highlight indicative areas of fundus images for different DR stages, providing a way for ophthalmologists to understand the model's decision.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2021)
Review
Computer Science, Artificial Intelligence
Ganeshsree Selvachandran, Shio Gai Quek, Raveendran Paramesran, Weiping Ding, Le Hoang Son
Summary: The exponential increase in the number of diabetics has led to a rise in diabetic retinopathy cases. Developing automated DR detection methods is crucial to reduce the burden on ophthalmologists. This review summarizes the recent developments in automated DR detection using fundus images, with a focus on machine learning algorithms.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Computer Science, Information Systems
Mohamed M. Farag, Mariam Fouad, Amr T. Abdel-Hamid
Summary: This paper introduces a new deep-learning-based approach for automatic severity detection using a single Color Fundus photograph (CFP) and trains the model on the Kaggle Asia Pacific Tele-Ophthalmology Society's (APTOS) dataset. The method achieves excellent performance in binary classification tasks and severity grading, reducing time and space complexity, making it a promising candidate for autonomous diagnosis.
Article
Chemistry, Analytical
Muhammad Shoaib Farooq, Ansif Arooj, Roobaea Alroobaea, Abdullah M. Baqasah, Mohamed Yaseen Jabarulla, Dilbag Singh, Ruhama Sardar
Summary: Diabetic Retinopathy is a main cause of visual impairment and loss. This study focuses on diagnosing DR using deep learning approaches, analyzing algorithms and techniques, and examining publicly available datasets for real-time applications of DR diagnostics.
Article
Computer Science, Information Systems
Al-Omaisi Asia, Cheng-Zhang Zhu, Sara A. Althubiti, Dalal Al-Alimi, Ya-Long Xiao, Ping-Bo Ouyang, Mohammed A. A. Al-Qaness
Summary: This study uses a deep learning approach with a convolutional neural network to detect and classify diabetic retinopathy. Preprocessing, regularization, and augmentation techniques are used to prepare the dataset. Different residual neural network structures are utilized to achieve accurate classification of DR images, with ResNet-101 showing the highest accuracy.
Article
Computer Science, Interdisciplinary Applications
Eman AbdelMaksoud, Sherif Barakat, Mohammed Elmogy
Summary: Diabetic retinopathy (DR) is a serious disease that can be diagnosed using deep learning techniques. This study proposes a hybrid deep learning technique, E-DenseNet model, for accurately diagnosing different DR grades on color retinal fundus images.
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING
(2022)
Biographical-Item
Entomology
Mayank Gupta, Varun Gupta
Article
Engineering, Biomedical
Nitigya Sambyal, Poonam Saini, Rupali Syal, Varun Gupta
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
(2020)
Article
Computer Science, Information Systems
Saksham Gupta, Paras Sharma, Dakshraj Sharma, Varun Gupta, Nitigya Sambyal
MULTIMEDIA TOOLS AND APPLICATIONS
(2020)
Article
Engineering, Electrical & Electronic
Nitigya Sambyal, Poonam Saini, Rupali Syal, Varun Gupta
Summary: In this study, an aggregated residual transformation-based model is proposed for automatic multistage classification of diabetic retinopathy, achieving high overall accuracy, sensitivity, specificity, and precision without overfitting. The model outperforms existing methods and achieves state-of-the-art results in the field.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2021)
Review
Biochemistry & Molecular Biology
Surya Nath Pandey, Naresh Kumar Rangra, Sima Singh, Saahil Arora, Varun Gupta
Summary: Alzheimer's disease is a prevalent neurodegenerative disease that causes dementia, with limited clinical treatment effectiveness due to unknown origin and blood-brain barrier restrictions. Plants offer potential avenues for new drug discovery, but further research is needed to validate their efficacy in alternative therapies.
ACS CHEMICAL NEUROSCIENCE
(2021)
Article
Engineering, Electrical & Electronic
Gagandeep Mangat, Divya Divya, Varun Gupta, Nitigya Sambyal
Summary: The paper presents a deep learning-based solution for automated detection of power theft using consumer consumption data. The study demonstrates that residual networks provide better results than other methods, with ResNet34 outperforming existing methods in the literature. The proposed system has high potential to help authorities reduce non-technical losses in the power sector.
ELECTRIC POWER COMPONENTS AND SYSTEMS
(2021)
Article
Computer Science, Information Systems
Ritika Dhiman, Gurkanwal Singh Kang, Varun Gupta
Summary: The study proposes a new method for emotion recognition through speech, using a modified dense convolutional network to detect emotions in speech with great success.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Review
Computer Science, Information Systems
Vanita Jain, Fadi Al-Turjman, Gopal Chaudhary, Devang Nayar, Varun Gupta, Aayush Kumar
Summary: This paper presents a survey on the state of art techniques of various video captioning methods and evaluates and compares methods used from 2015 to 2019. The survey shows that there are still many problems in the field of video captioning.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Yukti Aparna, Yukti Bhatia, Rachna Rai, Varun Gupta, Naveen Aggarwal, Aparna Akula
Summary: Potholes on roads are a major cause of accidents and vehicle wear and tear. Current pothole detection techniques have drawbacks, so this study aims to analyze the feasibility and accuracy of thermal imaging for pothole detection. Deep learning using convolutional neural networks approach is adopted, and a comparison between self-built and pre-trained models is conducted. The results show that thermal imaging achieved a highest accuracy of 97.08% with one of the pre-trained models. This study is important for guiding future research in the field of pothole detection.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Varun Gupta, Ekta Gupta
Summary: This paper proposes a novel method for multiclassification of Punjabi news articles using a pretrained language generation model. The method shows superior performance in text classification compared to other direct methods that do not utilize pretrained language generation models.
Article
Computer Science, Information Systems
Praveen Kumar, Varun Gupta
Summary: Ancient and contemporary artworks are important representatives of culture, heritage, and history. However, they tend to deteriorate over time, requiring restoration treatments. Traditional restoration methods are costly and time-consuming, and preserving the artistic style and features of the artwork is challenging. This paper proposes a generative adversarial network-based artwork restoration method that digitally restores damaged artworks, aiding in physical restoration. The proposed network outperforms existing restoration methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Biomedical
Varun Gupta, Megha Vasudev, Amit Doegar, Nitigya Sambyal
Summary: Researchers propose a breast cancer detection method based on a modified residual neural network, which performs well and provides high accuracy diagnosis at various magnification factors.
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Varun Gupta, Nitigya Sambyal, Akhil Sharma, Praveen Kumar
Summary: This paper presents a method for virtual restoration of digitized artworks based on deep neural networks, incorporating automatic mask generation and image inpainting techniques. The proposed approach is qualitatively and quantitatively evaluated, showing significant effectiveness in virtual restoration.
Article
Multidisciplinary Sciences
Rajwinder Singh, Harshita Puri, Naveen Aggarwal, Varun Gupta
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2020)
