Related references
Note: Only part of the references are listed.
Article
Medicine, General & Internal
Ameer Hamza et al.
Summary: In this study, we proposed a novel framework for COVID-19 classification using deep Bayesian optimization and improved canonical correlation analysis (ICCA). The framework utilized data augmentation and transfer learning to train two pre-trained deep models, and fused their features using ICCA. The fused features were further optimized and classified using an optimization algorithm and a neural network classifier, achieving very high accuracy.
Article
Computer Science, Artificial Intelligence
Joaquim de Moura et al.
Summary: In this study, 4 fully automatic approaches were proposed for chest X-ray image classification into 3 categories: Covid-19, pneumonia, and healthy cases. Extensive differentiation analysis was conducted between Covid-19 and pneumonia due to their similar lung pathological impacts during early stages. Six representative deep network architectures were evaluated on 3 public datasets to achieve global accuracy values benefiting clinicians in the diagnosis and early treatment of Covid-19.
APPLIED SOFT COMPUTING
(2022)
Article
Biology
J. L. Gayathri et al.
Summary: This paper presents a computer-aided detection model utilizing chest X-ray images for combating the COVID-19 pandemic. By utilizing pre-trained networks, sparse autoencoder, and a Feed Forward Neural Network (FFNN), the model achieves accurate detection of COVID-19.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Anatomy & Morphology
Tahira Nazir et al.
Summary: The COVID-19 pandemic is spreading rapidly with a high mortality rate. This study proposes a model that can accurately segment and classify COVID-19, as well as predict its growth over a certain period. Evaluation results confirm the effectiveness of the proposed method in segmentation, classification, and infection growth prediction.
MICROSCOPY RESEARCH AND TECHNIQUE
(2022)
Article
Chemistry, Analytical
Marriam Nawaz et al.
Summary: This article introduces an automated framework based on deep learning for the identification and classification of glaucoma. By using EfficientNet-B0 as the backbone network and EfficientDet-D0 for feature extraction and keypoint fusion, the framework is able to accurately localize and classify glaucomatous lesions, and its performance is validated through experiments to be superior to other frameworks.
Article
Computer Science, Artificial Intelligence
Waleed Albattah et al.
Summary: The agricultural production rate is crucial for economic development, but plant diseases pose a significant challenge. Automated approaches are needed to efficiently detect and categorize plant diseases, due to issues like low-intensity information in images. The introduced Custom CenterNet framework with DenseNet-77 has shown to be more proficient and reliable in identifying and classifying plant diseases compared to other latest approaches.
COMPLEX & INTELLIGENT SYSTEMS
(2022)
Article
Engineering, Biomedical
Aleka Melese Ayalew et al.
Summary: This paper presents a unique approach for quick diagnosis of COVID-19 using chest X-ray images. A hybrid model combining a convolutional neural network (CNN) and histogram of oriented gradients (HOG) method achieved high accuracy in detecting and classifying COVID-19. This method can help reduce inaccurate diagnosis and treatment of COVID-19, leading to improved patient outcomes.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Anatomy & Morphology
Marriam Nawaz et al.
Summary: This study presents a fully automated method for segmenting melanoma skin cancer using deep learning and fuzzy k-means clustering, aiming to aid in the early diagnosis and treatment of this disease. Evaluation on three standard datasets shows that the method outperforms state-of-the-art approaches in skin lesion recognition and segmentation, demonstrating robustness.
MICROSCOPY RESEARCH AND TECHNIQUE
(2022)
Article
Computer Science, Information Systems
Arman Haghanifar et al.
Summary: This study focuses on efficiently detecting imaging features of novel coronavirus pneumonia using deep convolutional neural networks. The proposed COVID-CXNet model is capable of precise localization based on relevant and meaningful features, which is a step towards a fully automated and robust COVID-19 detection system.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Tao Tan et al.
Summary: Computed tomography (CT) and X-ray are important imaging modalities for triaging COVID patients. This study proposes an AI model for triaging and monitoring COVID patients using X-ray images. The AI model is trained on both X-ray and CT data, and the multi-modal training process improves the performance of the solution. A reader study shows good consistency between the AI model and radiologists. Comparative analysis and generalization studies demonstrate the superiority of the proposed method.
Article
Medicine, General & Internal
Sungyeup Kim et al.
Summary: This paper proposes a deep learning method with transfer learning to classify lung diseases on chest X-ray images, aiming to improve the efficiency and accuracy of computer-aided diagnostic systems. The experiments on different datasets have achieved promising results in terms of the accuracy and specificity of disease classification.
Article
Computer Science, Information Systems
Saleh Albahli et al.
Summary: Accurate detection of chest diseases is necessary in the healthcare department to identify different types of pneumonia. Existing studies often only detect the presence of COVID-19, while the proposed study provides a method to detect COVID-19 and other chest diseases effectively.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Yan Han et al.
Summary: Accurate classification and localization of abnormalities in chest X-rays are crucial for clinical diagnosis and treatment planning. This paper proposes a semi-supervised knowledge-augmented contrastive learning framework that leverages radiomic features to improve disease classification and localization tasks. Experiment results on the NIH Chest X-ray dataset demonstrate its superiority over existing baselines.
2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022)
(2022)
Article
Computer Science, Interdisciplinary Applications
Xi Ouyang et al.
Summary: This work addresses the problem of abnormality localization in clinical applications using a new attention-driven weakly supervised algorithm that combines activation- and gradient-based visual attention in a holistic manner. Key algorithmic innovations include explicit ordinal attention constraints for model training in a weakly-supervised fashion and the generation of visual-attention-driven model explanations through localization cues. The proposed method demonstrates significant improvements in localization performance on two large-scale chest X-ray datasets while maintaining competitive classification performance.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Health Care Sciences & Services
Saleh Albahli et al.
Summary: This study proposes a diagnostic technique using deep learning to achieve fast and accurate diagnosis of COVID-19 and 14 other chest diseases based on X-ray images. By dividing the classification task into multiple steps rather than classifying them collectively, the technique showed improved accuracy in disease detection.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2021)
Article
Biology
Dina M. Ibrahim et al.
Summary: COVID-19 has been declared a pandemic, early detection is crucial to protect infected individuals. A deep learning model for diagnosing COVID-19, pneumonia, and lung cancer from chest x-ray and CT images was proposed, with the VGG19+CNN model showing the best performance in experiments.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Medicine, General & Internal
Marriam Nawaz et al.
Summary: Brain tumors are deadly diseases that require timely and accurate detection to assist in surgical planning. A novel approach based on DenseNet-41 and CornerNet framework is proposed for precise localization and categorization of brain tumors. Experimental results show that the proposed method is more proficient and consistent in detecting and classifying various types of brain tumors.
Article
Computer Science, Artificial Intelligence
Jing Xu et al.
Summary: The study presented a new multi-label chest disease image classification scheme based on a multi-scale attention network. By iteratively fusing multi-scale information to focus on regions with a high probability of disease, it achieved higher classification accuracy.
PEERJ COMPUTER SCIENCE
(2021)
Article
Computer Science, Information Systems
Marriam Nawaz et al.
Summary: Melanoma is a lethal skin cancer disease with high mortality rates, requiring early detection. A proposed method for melanoma detection utilizes image preprocessing, Faster-RCNN for localization, and SVM for classification, demonstrating effectiveness in accurately localizing and classifying melanoma lesions compared to existing techniques.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Chemistry, Analytical
Tahira Nazir et al.
Summary: Diabetic retinopathy (DR) is a disease that affects the blood vessels in the eyes of diabetic patients, with diabetic macular edema (DME) being a common complication. Traditional screening methods require manual analysis by experts, but automated systems are being developed to improve efficiency. A new method using deep learning-based CenterNet model shows promising results in accurately classifying eye disease lesions.
Letter
Computer Science, Information Systems
Momina Masood et al.
FRONTIERS OF COMPUTER SCIENCE
(2021)
Article
Multidisciplinary Sciences
Saleh Albahli et al.
Summary: This paper introduces an effective and efficient system for hand-written digit recognition, utilizing a faster regional convolutional neural network. Experimental evaluations on the MNIST database demonstrate that this method is more competitive than other recent methods.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2021)
Article
Computer Science, Information Systems
Zongyuan Ge et al.
MULTIMEDIA TOOLS AND APPLICATIONS
(2020)
Article
Computer Science, Artificial Intelligence
Abhir Bhandary et al.
PATTERN RECOGNITION LETTERS
(2020)
Article
Computer Science, Artificial Intelligence
Goncalo Marques et al.
APPLIED SOFT COMPUTING
(2020)
Article
Radiology, Nuclear Medicine & Medical Imaging
Ian Pan et al.
JOURNAL OF DIGITAL IMAGING
(2019)
Article
Environmental Sciences
Yuanyuan Wang et al.
Article
Multidisciplinary Sciences
Ivo M. Baltruschat et al.
SCIENTIFIC REPORTS
(2019)
Article
Chemistry, Multidisciplinary
Thi Kieu Khanh Ho et al.
APPLIED SCIENCES-BASEL
(2019)
Article
Computer Science, Artificial Intelligence
Zifeng Wu et al.
PATTERN RECOGNITION
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Jingyu Liu et al.
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Congbo Ma et al.
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2019, PT VI
(2019)
Article
Health Care Sciences & Services
Rahib H. Abiyev et al.
JOURNAL OF HEALTHCARE ENGINEERING
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Ross Girshick
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2015)