Automatic autism spectrum disorder detection using artificial intelligence methods with MRI neuroimaging: A review

Frontiers in Molecular Neuroscience, Год журнала: 2022, Номер 15

Опубликована: Окт. 4, 2022

Autism spectrum disorder (ASD) is a brain condition characterized by diverse signs and symptoms that appear in early childhood. ASD also associated with communication deficits repetitive behavior affected individuals. Various detection methods have been developed, including neuroimaging modalities psychological tests. Among these methods, magnetic resonance imaging (MRI) are of paramount importance to physicians. Clinicians rely on MRI diagnose accurately. The non-invasive include functional (fMRI) structural (sMRI) methods. However, diagnosing fMRI sMRI for specialists often laborious time-consuming; therefore, several computer-aided design systems (CADS) based artificial intelligence (AI) developed assist specialist Conventional machine learning (ML) deep (DL) the most popular schemes AI used ASD. This study aims review automated using AI. We CADS ML techniques diagnosis modalities. There has very limited work use DL develop diagnostic models A summary studies provided Supplementary Appendix. Then, challenges encountered during described detail. Additionally, graphical comparison automatically discussed. suggest future approaches detecting ASDs neuroimaging.

Язык: Английский

---

A survey of multimodal information fusion for smart healthcare: Mapping the journey from data to wisdom

Information Fusion, Год журнала: 2023, Номер 102, С. 102040 - 102040

Опубликована: Сен. 27, 2023

Multimodal medical data fusion has emerged as a transformative approach in smart healthcare, enabling comprehensive understanding of patient health and personalized treatment plans. In this paper, journey from to information knowledge wisdom (DIKW) is explored through multimodal for healthcare. We present review focused on the integration various modalities. The explores different approaches such feature selection, rule-based systems, machine ;earning, deep learning, natural language processing, fusing analyzing data. This paper also highlights challenges associated with By synthesizing reviewed frameworks theories, it proposes generic framework that aligns DIKW model. Moreover, discusses future directions related four pillars healthcare: Predictive, Preventive, Personalized, Participatory approaches. components survey presented form foundation more successful implementation Our findings can guide researchers practitioners leveraging power state-of-the-art revolutionize healthcare improve outcomes.

Язык: Английский

---

Multi-source information fusion: Progress and future

Chinese Journal of Aeronautics, Год журнала: 2023, Номер 37(7), С. 24 - 58

Опубликована: Дек. 12, 2023

Multi-Source Information Fusion (MSIF), as a comprehensive interdisciplinary field based on modern information technology, has gained significant research value and extensive application prospects in various domains, attracting high attention interest from scholars, engineering experts, practitioners worldwide. Despite achieving fruitful results both theoretical applied aspects over the past five decades, there remains lack of systematic review articles that provide an overview recent development MSIF. In light this, this paper aims to assist researchers individuals interested gaining quick understanding relevant techniques trends MSIF, which conducts statistical analysis academic reports related achievements MSIF two provides brief theories, methodologies, well key issues challenges currently faced. Finally, outlook future directions are presented.

Язык: Английский

---

Effective Techniques for Multimodal Data Fusion: A Comparative Analysis

Sensors, Год журнала: 2023, Номер 23(5), С. 2381 - 2381

Опубликована: Фев. 21, 2023

Data processing in robotics is currently challenged by the effective building of multimodal and common representations. Tremendous volumes raw data are available their smart management core concept learning a new paradigm for fusion. Although several techniques representations have been proven successful, they not yet analyzed compared given production setting. This paper explored three most techniques, (1) late fusion, (2) early (3) sketch, them classification tasks. Our different types (modalities) that could be gathered sensors serving wide range sensor applications. experiments were conducted on Amazon Reviews, MovieLens25M, Movie-Lens1M datasets. Their outcomes allowed us to confirm choice fusion technique representation crucial obtain highest possible model performance resulting from proper modality combination. Consequently, we designed criteria choosing this optimal technique.

Язык: Английский

---

Explainable Deep-Learning-Based Diagnosis of Alzheimer’s Disease Using Multimodal Input Fusion of PET and MRI Images

Journal of Medical and Biological Engineering, Год журнала: 2023, Номер 43(3), С. 291 - 302

Опубликована: Июнь 1, 2023

Abstract Purpose Alzheimer’s disease (AD) is a progressive, incurable human brain illness that impairs reasoning and retention as well recall. Detecting AD in its preliminary stages before clinical manifestations crucial for timely treatment. Magnetic Resonance Imaging (MRI) provides valuable insights into abnormalities by measuring the decrease volume expressly mesial temporal cortex other regions of brain, while Positron Emission Tomography (PET) measures glucose concentration temporoparietal association cortex. When these data are combined, performance diagnostic methods could be improved. However, heterogeneous there need an effective model will harness information from both accurate prediction AD. Methods To this end, we present novel heuristic early feature fusion framework performs concatenation PET MRI images, modified Resnet18 deep learning architecture trained simultaneously on two datasets. The innovative 3-in-channel approach used to learn most descriptive features fused images binary classification Results experimental results show proposed achieved accuracy 73.90% ADNI database. Then, provide Explainable Artificial Intelligence (XAI) model, allowing us explain results. Conclusion Our latent representations multimodal even presence heterogeneity data; hence, partially solved issue with data.

Язык: Английский

---

Deep learning based multimodal biomedical data fusion: An overview and comparative review

Information Fusion, Год журнала: 2024, Номер 112, С. 102536 - 102536

Опубликована: Дек. 1, 2024

Язык: Английский

---

Mobile Traffic Prediction in Consumer Applications: A Multimodal Deep Learning Approach

IEEE Transactions on Consumer Electronics, Год журнала: 2024, Номер 70(1), С. 3425 - 3435

Опубликована: Фев. 1, 2024

Mobile traffic prediction is an important yet challenging problem in consumer applications because of the dynamic nature user behavior, varying application quality service (QoS) requirements, network congestion, and proliferation diverse mobile devices. The with multiple services, e.g., SMS, call, Internet, defined as mapping from historical data to future prediction. Both grid graph-based formulations have been extensively considered literature. However, effective multimodal deep learning approach both graph modals has not fully considered. This study proposes a convolutional neural (CNN)-graph (GNN) hybrid framework for single-step prediction, which information extracted call Internet services are fused make precise consumption consumers next hour. CNN module built using ConvLSTM, GNN adaptive (AGCN), fusion layer designed combine outputs modules. Numerical experiments based on real-world dataset demonstrate effectiveness proposed framework, achieves error lower than ten baselines.

Язык: Английский

---

Tumor microenvironment responsive nanozymes for multimodal imaging of tumors

Nano TransMed, Год журнала: 2024, Номер 3, С. 100032 - 100032

Опубликована: Янв. 29, 2024

Nanozymes exhibit immense potential and promising prospects in the realm of diagnostic imaging tumor therapy, owing to their inherent physicochemical properties enzymatic activities. With further development application nanotechnology, nanozymes are expected become an important tool field medicine, providing new solutions for disease diagnosis treatment. This review provides overview recent studies over past five years on capable responding microenvironment (TME) multimodal imaging, with a focus hypoxia, acid pH, excess GSH ROS. In addition, we present current status several common related contrast agents, such as MRI/CT, MRI/PET, MRI/SPECT, PET/CT. Moreover, some thoughts challenges, future development, clinical translation microenvironment-responsive shared. aims provide up-to-date theranostic nanomedicine reference those who fields, promote progress this interdisciplinary subject, accelerate translation.

Язык: Английский

---

Heart disease detection using deep learning methods from imbalanced ECG samples

Biomedical Signal Processing and Control, Год журнала: 2021, Номер 68, С. 102820 - 102820

Опубликована: Май 31, 2021

Язык: Английский

---

Factors associated with brain ageing - a systematic review

BMC Neurology, Год журнала: 2021, Номер 21(1)

Опубликована: Авг. 12, 2021

Abstract Background Brain age is a biomarker that predicts chronological using neuroimaging features. Deviations of this predicted from considered sign age-related brain changes, or commonly referred to as ageing. The aim systematic review identify and synthesize the evidence for an association between lifestyle, health factors diseases in adult populations, with Methods This was undertaken accordance PRISMA guidelines. A search Embase Medline conducted relevant articles terms relating prediction data tables two recent papers on ageing were also examined additional articles. Studies limited humans (aged 18 years above), clinical general populations. Exposures study design all types eligible. Results identified 52 studies, which community dwelling adults (mean 21 78 years, ~ 37% female). Most research came studies individuals diagnosed schizophrenia Alzheimer’s disease, healthy populations assessed cognitively. From these psychiatric neurologic most associated accelerated ageing, though not drew same conclusions. Evidence other exposures nascent, relatively inconsistent. Heterogenous methodologies, methods outcome ascertainment, partly accountable. Conclusion summarised current genetic, health, Overall there good suggest disease are mixed limited. mostly due lack independent replication, inconsistency across primarily cross sectional nature. Future efforts should focus replicating findings, prospective datasets. Trial registration copy protocol can be accessed through PROSPERO, number CRD42020142817 .

Язык: Английский

---