Article
Medicine, General & Internal
Kiruthigha Manikantan, Suresh Jaganathan
Summary: This article proposes a model using graphical neural networks to diagnose autism patients. In the model, radiomic features from sMRI are used as edges, and spatial-temporal data from rs-fMRI are used as nodes. The graph's edges are constructed using the similarity of first-order and texture features derived from the sMRI data. The features of each node of the graph are represented by assembling and learning the features from brain summaries using 3DCNN. The model improves classification results by utilizing the structural similarities of the brain.
Article
Neurosciences
Kai Chen, Wenwen Zhuang, Yanfang Zhang, Shunjie Yin, Yinghua Liu, Yuan Chen, Xiaodong Kang, Hailin Ma, Tao Zhang
Summary: This study identified changes in large-scale white matter functional networks in autism spectrum disorder, including decreased white matter and white-matter functional network connectivity, as well as reduced spontaneous activity. These changes are associated with behavioral deficits in autism spectrum disorder.
Article
Behavioral Sciences
Heng Chen, Jinjin Long, Shanshan Yang, Bifang He
Summary: This study investigated the atypical functional covariance between gray matter (GM) and white matter (WM) in children with Autism Spectrum Disorder (ASD). Results indicated altered functional co-development pattern between specific GM and WM regions in ASD individuals, which was related to stereotyped behaviors of ASD. These findings suggest potential insights into the GM/WM functional development in ASD.
Article
Neurosciences
Yasuhito Nagai, Eiji Kirino, Shoji Tanaka, Chie Usui, Rie Inami, Reiichi Inoue, Aki Hattori, Wataru Uchida, Koji Kamagata, Shigeki Aoki
Summary: This study evaluated functional connectivity in adult autism spectrum disorder (ASD) patients using rs-fMRI and DKI. The results showed abnormal FC between different brain regions in ASD patients compared to healthy controls. Additionally, DKI data revealed microstructural alterations in the white matter tracts of ASD patients.
Article
Neurosciences
Clara F. Weber, Evelyn M. R. Lake, Stefan P. Haider, Ali Mozayan, Pratheek S. Bobba, Pratik Mukherjee, Dustin Scheinost, Robert T. Constable, Laura Ment, Seyedmehdi Payabvash
Summary: The study utilized functionally guided tractography to identify ASD-related microstructural connectome changes, showing that early ASD-related WM disruptions can be detected using functional nodes, and supporting the benefit of functionally informed nodes in diffusion imaging-based tractography.
FRONTIERS IN NEUROSCIENCE
(2023)
Article
Medicine, General & Internal
Xiangfei Zhang, Shayel Parvez Shams, Hang Yu, Zhengxia Wang, Qingchen Zhang
Summary: Autism spectrum disorder (ASD) is a lifelong neurological disease that greatly affects patients' quality of life. Early diagnosis is important for improving the lives of ASD children. This paper proposes a similarity measure-based approach for ASD diagnosis, using few-shot learning to measure potential similarities in RS-fMRI data distributions and training a similarity function for samples from multiple sites to enhance generalization. Experimental results demonstrate the superiority of the proposed method over comparison methods in terms of accuracy, precision, and F1 score.
Article
Computer Science, Artificial Intelligence
Fatima Zahra Benabdallah, Ahmed Drissi El Maliani, Dounia Lotfi, Rachid Jennane, Mohammed El Hassouni
Summary: This paper proposes a framework that takes into account the properties of local connectivity and long range under-connectivity in the autistic brain. The originality of the proposed approach is to adopt elimination techniques to well reveal the autistic brain connectivity alterations, and successfully prove the existence of deficits in the long-range connectivity in ASD subjects' brains.
Review
Biochemical Research Methods
Ming Xu, Vince Calhoun, Rongtao Jiang, Weizheng Yan, Jing Sui
Summary: This article reviews recent advances in using machine learning techniques to classify individuals with autism spectrum disorder, covering neuroimaging, methods, and sample sizes. It points out challenges in ASD diagnosis and provides recommendations for future directions.
JOURNAL OF NEUROSCIENCE METHODS
(2021)
Article
Behavioral Sciences
Pengchen Ren, Qingshang Bi, Wenbin Pang, Meijuan Wang, Qionglin Zhou, Xiaoshan Ye, Ling Li, Le Xiao
Summary: This study used a large sample of rs-fMRI data from ASD patients and TD controls to classify patients into subtypes using a machine learning model. The results showed differences in brain functional connectivity between these subtypes, which helps to reduce the heterogeneity of the disease.
BEHAVIOURAL BRAIN RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
S. Qasim Abbas, Lianhua Chi, Yi-Ping Phoebe Chen
Summary: The growing prevalence of neurological disorders demands robust computer-aided diagnosis. A benchmark neuroimaging diagnostics is absent for Autism Spectrum Disorder. Existing CADs using multisite data face variabilities and heterogeneities. To resolve this problem, a Deep Multimodal Neuroimaging Framework (DeepMNF) is proposed that integrates cross-modality spatiotemporal information. It achieves superior validation performance and demonstrates the effectiveness of multimodal framework development.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2023)
Article
Behavioral Sciences
Carla E. M. Golden, Victoria X. Wang, Hala Harony-Nicolas, Patrick R. Hof, Joseph D. Buxbaum
Summary: Mutations and deletions in the SHANK3 gene cause Phelan-McDermid syndrome, characterized by intellectual disability and autism spectrum disorder. Studies on both patients and rat models with Shank3 deficiency show reductions in brain volume and white matter alterations.
Review
Biology
Asrar G. Alharthi, Salha M. Alzahrani
Summary: This review paper explores the use of artificial intelligence and machine learning in the diagnosis of Autism Spectrum Disorder (ASD). It discusses the use of MRI and deep learning models for ASD diagnosis, as well as the application of visual transformers and brain transformers in the field. The paper provides an overview of existing models and their effectiveness in ASD detection.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Neurosciences
Marissa DiPiero, Hassan Cordash, Molly B. Prigge, Carolyn K. King, Jubel Morgan, Jose Guerrero-Gonzalez, Nagesh Adluru, Jace B. King, Nicholas Lange, Erin D. Bigler, Brandon A. Zielinski, Andrew L. Alexander, Janet E. Lainhart, Douglas C. Dean
Summary: All diffusion MRI measures showed significant associations with age across white matter and gray matter. Significant group differences were observed in both white matter and gray matter. There were no significant age-by-group interactions detected. Within the ASD group, positive relationships were found between white matter microstructure and ADOS-2 Calibrated Severity Scores. The findings provide new insights into group differences of white matter and gray matter microstructure in autistic males from adolescence into adulthood, contributing to a better understanding of brain-behavior relationships of ASD.
FRONTIERS IN NEUROSCIENCE
(2023)
Article
Neurosciences
Xiaonan Guo, Xujun Duan, John Suckling, Jia Wang, Xiaodong Kang, Heng Chen, Bharat B. Biswal, Jing Cao, Changchun He, Jinming Xiao, Xinyue Huang, Runshi Wang, Shaoqiang Han, Yun-Shuang Fan, Jing Guo, Jingping Zhao, Lijie Wu, Huafu Chen
Summary: This study aimed to investigate the structural alterations in the autistic brain during early childhood, and found spatially distributed increases in gray matter volume in the autism group compared to typically developing children. Additionally, atypical neurodevelopment of the fusiform face area was observed in the autistic brain, with altered developmental effects on the social brain network regions.
Article
Psychiatry
Yun Cai, Jinghui Zhao, Lian Wang, Yuanjun Xie, Xiaotang Fan
Summary: Research has found that there are abnormalities in the topological organization of the white matter structural network in adults with autism spectrum disorder (ASD), which may play a crucial role in the underlying pathological mechanism of ASD.
ASIAN JOURNAL OF PSYCHIATRY
(2022)
Article
Computer Science, Artificial Intelligence
Majid Ghasemi, Manoochehr Kelarestaghi, Farshad Eshghi, Arash Sharifi
Summary: The study introduces an adaptive fuzzy dictionary learning method for image classification, which optimizes basis vectors to accurately represent data and addresses the inherent uncertainty in input data. Experimental results demonstrate the superior performance of the method in medical image classification, with high accuracy, sensitivity, and specificity.
PATTERN ANALYSIS AND APPLICATIONS
(2021)
Article
Computer Science, Theory & Methods
Elham Azhir, Nima Jafari Navimipour, Mehdi Hosseinzadeh, Arash Sharifi, Aso Darwesh
Summary: The study presents an improved incremental DBSCAN algorithm that adjusts parameters to optimize clustering results and introduces fitness functions for both labeled and unlabeled datasets. Efficiency of the algorithm is enhanced with parallelization of the optimization process.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)
Article
Computer Science, Theory & Methods
H. Pezeshki, M. Rastgarpour, A. Sharifi, S. Yazdani
Summary: The study proposes a new method for extracting spiculated parts and tumor core in mammography, segmenting the tumor based on similarity and dissimilarity, and extracting statistical features and fractal dimensions to enhance complexity of tumor shape. Simulation results show the proposed method is more suitable than other methods, with increased accuracy of classification using fractal dimension.
MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Shirin Khezri, Jafar Tanha, Ali Ahmadi, Arash Sharifi
Summary: This article discusses semi-supervised data stream classification problems and proposes a novel Semi-Supervised Ensemble algorithm named SSE-PBS. Based on a performance-based selection metric using pseudo-accuracy and energy regularization factor, SSE-PBS improves classification performance and handles different types of concept drifts, outperforming other methods in experiments.
Article
Mathematical & Computational Biology
Morteza Amini, MirMohsen Pedram, AliReza Moradi, Mahshad Ouchani
Summary: This paper focuses on the automatic diagnosis of Alzheimer's disease using machine learning methods and convolutional neural networks (CNN). By correlating functional magnetic resonance imaging (fMRI) images and MMSE scores of Alzheimer's patients, features are extracted and classified, with results showing that the CNN method has higher accuracy in diagnosing Alzheimer's disease.
COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE
(2021)
Article
Mathematical & Computational Biology
Morteza Amini, MirMohsen Pedram, AliReza Moradi, Mahshad Ouchani
Summary: The study focuses on diagnosing EEG signal function using time-dependent power spectrum descriptors and analyzing early detection of Alzheimer's disease through various classification methods, with convolutional neural network achieving an accuracy of 82.3%. Results show that the convolutional neural network outperforms other methods in diagnostic accuracy, with higher detection rate in mild cognitive impairment cases but needs improvement in detecting Alzheimer's disease and healthy population.
COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE
(2021)
Article
Computer Science, Hardware & Architecture
Payam Porkar Rezaeiye, Arash Sharifi, Amir Masoud Rahmani, Mehdi Dehghan
Summary: Efficiency is crucial in IoT networks with the increasing use of IoT, and a new algorithm based on access point selection is proposed to enhance load balancing and efficiency. The algorithm greatly improves network efficiency and better distributes network load.
JOURNAL OF SUPERCOMPUTING
(2021)
Article
Computer Science, Interdisciplinary Applications
Saeed Pirmoradi, Mohammad Teshnehlab, Nosratollah Zarghami, Arash Sharifi
Summary: This study presents a new machine learning approach for identifying significant miRNAs and classifying kidney cancer subtypes to design an automatic diagnostic tool. The proposed self-organizing deep neuro-fuzzy system successfully classified kidney cancer subtypes with high accuracy, overcoming key obstacles in neuro-fuzzy system applications.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Review
Mathematical & Computational Biology
Morteza Amini, Mir Mohsen Pedram, Alireza Moradi, Mahdieh Jamshidi, Mahshad Ouchani
Summary: Alzheimer's disease is characterized by the gradual decrease in neuron connections in the brain, with machine learning algorithms playing a significant role in classification and early detection. Combining neuroimaging techniques can increase the accuracy of AD detection, with MRI and fMRI showing promising results in sensitivity metrics from different machine learning methods.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2021)
Article
Computer Science, Artificial Intelligence
Fariba Salehi, Mohammad Reza Keyvanpour, Arash Sharifi
Summary: This study introduces a semi-supervised collaborative fuzzy clustering method that emphasizes aggregating diverse knowledge sources to reveal data structures and the importance of knowledge sharing. By combining fuzzy logic, semi-supervised, and collaborative learning simultaneously, the proposed method outperforms rival techniques in terms of accuracy, precision, recall, specificity, NMI, ARI, and convergence speed.
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Elham Azhir, Nima Jafari Navimipour, Mehdi Hosseinzadeh, Arash Sharifi, Aso Darwesh
Summary: Query optimization aims to identify the best Query Execution Plan by comparing different execution plans based on their costs. Access plan recommendation is a technique that reuses previously-generated plans to execute new queries. Clustering algorithms can help identify similar query patterns efficiently.
PEERJ COMPUTER SCIENCE
(2021)
Article
Mathematical & Computational Biology
Mahsa Pourhosein Kalashami, Mir Mohsen Pedram, Hossein Sadr
Summary: This study proposes a method for addressing the challenging problem of emotion recognition in Brain-Computer Interaction (BCI) using data augmentation and feature extraction techniques. By using deep generative models and a Conditional Wasserstein GAN to regenerate additional EEG features, the performance of EEG-based emotion recognition models is improved. Experimental results show a 6.5% increase in accuracy for valence and a 3.0% increase for arousal after data augmentation.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2022)
Article
Mathematical & Computational Biology
Morteza Amini, Mir Mohsen Pedram, AliReza Moradi, Mahdieh Jamshidi, Mahshad Ouchani
Summary: The study demonstrates a causal relationship between SNPs and quantitative PET imaging traits in Alzheimer's disease. CNN achieved the highest accuracy of 91.1% in AD classification based on brain tissue variations in PET images. KNN and CNN methods are beneficial in diagnosing AD, while LDA and SVM showed lower accuracy levels.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2022)
Article
Engineering, Biomedical
Seyyed Amirhossein Ghaznavi Bidgoli, Arash Sharifi, Mohammad Manthouri
Summary: This study aimed to establish a standard dataset of panoramic radiographs of jaws and teeth, utilizing a deep neural network algorithm to classify teeth. The results showed that the proposed network was highly stable and achieved better dental diagnosis.
COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING-IMAGING AND VISUALIZATION
(2021)
Article
Computer Science, Artificial Intelligence
Sepideh Adabi, Fatemeh Alayin, Arash Sharifi
Summary: Determining the true value of bids in negotiation-based cloud resource allocation is a key challenge, and a flexible pricing mechanism is necessary. Research shows that the proposed negotiators outperform other negotiators in terms of performance.