Article
Computer Science, Artificial Intelligence
Nitsa J. Herzog, George D. Magoulas
Summary: This paper introduces a computer-aided approach for early dementia diagnosis using deep learning models. The approach utilizes an MRI brain asymmetry biomarker and employs a convolutional neural network for image classification, achieving high accuracy.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2022)
Article
Engineering, Biomedical
Zhimin Shao, Weibei Dou, Di Ma, Xiaoxue Zhai, Quan Xu, Yu Pan
Summary: This study proposes a new method to more accurately estimate the influence of neuro-intervention on brain damage. By modeling left and right hemiplegia separately, the method shows a 5-15% improvement in accuracy compared to traditional methods, and reveals the common and unique recovery mechanisms after left and right strokes, assisting clinicians in formulating rehabilitation plans.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2023)
Article
Biology
U. Raghavendra, Anjan Gudigar, Aritra Paul, T. S. Goutham, Mahesh Anil Inamdar, Ajay Hegde, Aruna Devi, Chui Ping Ooi, Ravinesh C. Deo, Prabal Datta Barua, Filippo Molinari, Edward J. Ciaccio, U. Rajendra Acharya
Summary: A brain tumor is an abnormal mass inside the skull that can lead to significant health problems by putting pressure on the brain. Early detection of these tumors is crucial as malignant brain tumors grow rapidly and can result in higher mortality rates. Computer-aided diagnostic systems, combined with artificial intelligence techniques, play a vital role in the early detection of this disorder. This review highlights the challenges faced by CAD systems based on different modalities, current requirements in this field, and future prospects in research.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Review
Neurosciences
Parisa Moridian, Navid Ghassemi, Mahboobeh Jafari, Salam Salloum-Asfar, Delaram Sadeghi, Marjane Khodatars, Afshin Shoeibi, Abbas Khosravi, Sai Ho Ling, Abdulhamit Subasi, Roohallah Alizadehsani, Juan M. Gorriz, Sara A. Abdulla, U. Rajendra Acharya
Summary: Autism spectrum disorder is a brain condition that presents diverse signs and symptoms in early childhood. Magnetic resonance imaging plays a crucial role in accurately diagnosing ASD. AI techniques, particularly ML and DL, have been used to develop automated diagnostic models for ASD using MRI modalities.
FRONTIERS IN MOLECULAR NEUROSCIENCE
(2022)
Review
Radiology, Nuclear Medicine & Medical Imaging
Nikita Sushentsev, Nadia Moreira Da Silva, Michael Yeung, Tristan Barrett, Evis Sala, Michael Roberts, Leonardo Rundo
Summary: This study systematically reviewed the current literature to evaluate the ability of fully-automated deep learning (DL) and semi-automated traditional machine learning (TML) MRI-based artificial intelligence (AI) methods in differentiating clinically significant prostate cancer from indolent prostate cancer and benign conditions. The study found comparable performance of the two classes of AI methods and identified common methodological limitations and biases.
INSIGHTS INTO IMAGING
(2022)
Review
Medicine, General & Internal
Hamide Nematollahi, Masoud Moslehi, Fahimeh Aminolroayaei, Maryam Maleki, Daryoush Shahbazi-Gahrouei
Summary: Prostate cancer, the second leading cause of cancer-related death in men, can be effectively detected and graded using artificial intelligence and machine learning techniques, particularly with multiparametric MRI. This review study compares the diagnostic performance of different supervised machine learning algorithms and finds that deep learning, random forest, and logistic regression algorithms have the best performance in prostate cancer diagnosis and prediction. These findings highlight the potential of supervised machine learning in improving the accuracy and effectiveness of prostate cancer detection and prevention.
Article
Chemistry, Analytical
Francesco Mercaldo, Luca Brunese, Fabio Martinelli, Antonella Santone, Mario Cesarelli
Summary: This paper proposes a method for detecting and localizing brain cancer using deep learning techniques. The method utilizes convolutional neural networks and class activation mapping to highlight the areas of medical images related to brain cancer, providing explainability. The method is evaluated using 3000 magnetic resonance images, and achieves high accuracy ranging from 97.83% to 99.67% in brain cancer detection by exploiting four different models: VGG16, ResNet50, Alex_Net, and MobileNet, demonstrating the effectiveness of the proposed method.
Article
Computer Science, Hardware & Architecture
Ilhan Firat Kilincer, Fatih Ertam, Abdulkadir Sengur
Summary: The study reviewed literature studies using widely used data sets to develop IDS systems, and found that more successful results were obtained in some studies when using classification with support vector machine (SVM), K-Nearest neighbor (KNN), and Decision Tree (DT) algorithms among other classical machine learning approaches. This study is considered useful for developing IDS systems based on artificial intelligence utilizing machine learning approaches.
Article
Computer Science, Information Systems
Chetan Swarup, Ankit Kumar, Kamred Udham Singh, Teekam Singh, Linesh Raja, Abhishek Kumar, Ramu Dubey
Summary: Image segmentation is increasingly important in medical image analysis, particularly in the detection of brain tumors. This paper proposes a method that uses fundamental image processing techniques, such as noise reduction and morphological functions, to provide tumor-specific information. The method achieves a high accuracy rate of 97.5% in determining tumor size, shape, and location, aiding in the understanding of the tumor's severity.
HUMAN-CENTRIC COMPUTING AND INFORMATION SCIENCES
(2022)
Review
Computer Science, Information Systems
Huseyin Ahmetoglu, Resul Das
Summary: The development of network technologies and the increasing amount of data transferred on networks have led to a rise in cyber threats and attacks. Machine learning offers tools and techniques for automating the detection and analysis of these attacks. This study discusses the different machine learning approaches used to detect and analyze attacks, including anomaly detection, classification, and analysis. The study also examines the performance and results of different methods, as well as the datasets used in the research.
INTERNET OF THINGS
(2022)
Article
Medicine, General & Internal
Juntuo Zhou, Nan Ji, Guangxi Wang, Yang Zhang, Huajie Song, Yuyao Yuan, Chunyuan Yang, Yan Jin, Zhe Zhang, Liwei Zhang, Yuxin Yin
Summary: This study demonstrates the potential of utilizing a machine learning algorithm to analyze lipidomic data for the non-invasive diagnosis of malignant brain gliomas. A panel of 11 plasma lipids was identified as reliable biomarkers, providing a potential method for early detection of MBGs.
Review
Clinical Neurology
Rajan Hossain, Roliana Binti Ibrahim, Haslina Binti Hashim
Summary: In this study, a systematic review and bibliometric analysis were conducted to provide a research overview of brain tumor classification using machine learning. The analysis included 1747 studies from the past 5 years, involving 679 sources and 6632 investigators. Various metrics were used to determine the most productive institutes, reports, journals, and countries, and the trends and focuses in brain tumor classification research were identified.
WORLD NEUROSURGERY
(2023)
Article
Plant Sciences
Suiyan Tan, Jingbin Liu, Henghui Lu, Maoyang Lan, Jie Yu, Guanzhong Liao, Yuwei Wang, Zehua Li, Long Qi, Xu Ma
Summary: This paper presents automatic approaches to detect three critical growth stages of rice seedlings, utilizing both traditional machine learning algorithms and deep learning algorithms. The best performance was achieved by the EfficientnetB4 model in the deep learning algorithm, highlighting its potential in detecting rice seedling growth stages.
FRONTIERS IN PLANT SCIENCE
(2022)
Article
Biology
Delaram Sadeghi, Afshin Shoeibi, Navid Ghassemi, Parisa Moridian, Ali Khadem, Roohallah Alizadehsani, Mohammad Teshnehlab, Juan M. Gorriz, Fahime Khozeimeh, Yu-Dong Zhang, Saeid Nahavandi, U. Rajendra Acharya
Summary: Schizophrenia (SZ) is a psychiatric disorder that often occurs in late adolescence or early adulthood, characterized by abnormal behavior, perception of emotions, social relationships, and reality perception. Past studies have shown that SZ affects the temporal and anterior lobes of the hippocampus, and leads to increased volume of cerebrospinal fluid and decreased volume of white and gray matter. Magnetic resonance imaging (MRI) is a widely used neuroimaging technique for exploring structural and functional brain abnormalities in SZ. Artificial intelligence (AI) techniques, combined with advanced image/signal processing methods, have been employed for accurate diagnosis of SZ using MRI modalities.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Information Systems
Yajuvendra Pratap Singh, D. K. Lobiyal
Summary: This paper presents a study on the classification and segmentation of brain tumors using machine learning and deep learning techniques. The results show that deep learning models have better accuracy in classification and segmentation, and a modified model is proposed to improve performance.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Alan Mosca, George D. Magoulas
Article
Computer Science, Information Systems
C. Stamate, G. D. Magoulas, S. Kueppers, E. Nomikou, I. Daskalopoulos, A. Jha, J. S. Pons, J. Rothwell, M. U. Luchini, T. Moussouri, M. Iannone, G. Roussos
PERVASIVE AND MOBILE COMPUTING
(2018)
Article
Computer Science, Artificial Intelligence
Alan Mosca, George D. Magoulas
NEURAL COMPUTING & APPLICATIONS
(2019)
Article
Computer Science, Information Systems
Tomasz D. Sikora, George D. Magoulas
ENTERPRISE INFORMATION SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Maitrei Kohli, George D. Magoulas, Michael S. C. Thomas
Article
Computer Science, Artificial Intelligence
Nitsa J. Herzog, George D. Magoulas
Summary: This paper introduces a computer-aided approach for early dementia diagnosis using deep learning models. The approach utilizes an MRI brain asymmetry biomarker and employs a convolutional neural network for image classification, achieving high accuracy.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2022)
Proceedings Paper
Biochemical Research Methods
Nitsa J. Herzog, George D. Magoulas
Summary: The combination of neuroimaging technologies and deep networks has attracted considerable attention and achieved excellent performance in various applications. Transfer learning methods allow retraining of deep networks, previously trained on large datasets, using smaller datasets from new application domains, thereby reducing training time and dependence on large-scale data. This paper investigates the application of deep networks trained on ImageNet data for the diagnosis of dementia, and empirical evaluation shows the potential of transfer learning methods in detecting early degenerative changes in the brain.
COMPUTATIONAL INTELLIGENCE METHODS FOR BIOINFORMATICS AND BIOSTATISTICS, CIBB 2021
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Dilek Celik, George D. Magoulas
TRANSFORMING LEARNING WITH MEANINGFUL TECHNOLOGIES, EC-TEL 2019
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Cosmin Stamate, George D. Magoulas, Michael S. C. Thomas
PROCEEDINGS OF SAI INTELLIGENT SYSTEMS CONFERENCE (INTELLISYS) 2016, VOL 2
(2018)
Article
Computer Science, Interdisciplinary Applications
Anwar ul Haq, George Magoulas, Arshad Jamal, Asim Majeed, Diane Sloan
JOURNAL OF ENTERPRISE INFORMATION MANAGEMENT
(2018)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Konstantinos Karoudis, George D. Magoulas
INNOVATIONS IN SMART LEARNING
(2017)
Proceedings Paper
Computer Science, Information Systems
Beate Grawemeyer, Konstantinos Karoudis, George Magoulas, Marta Pinto, Alexandra Poulovassilis
WWW'17 COMPANION: PROCEEDINGS OF THE 26TH INTERNATIONAL CONFERENCE ON WORLD WIDE WEB
(2017)