Application of Deep Learning for Prediction of Alzheimer’s Disease in PET/MR Imaging

Zhao, Yan; Guo, Qianrui; Zhang, Yukun; Zheng, Jia; Yang, Yang; Du, Xuemei; Feng, Hongbo; Zhang, Shuo

doi:10.3390/bioengineering10101120

Cited by 13 publications

(3 citation statements)

References 97 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More in-depth discussions surrounding artificial intelligence (AI) and machine learning (ML) were present across all article types within this review [ 78 , 79 , 80 ]. Zhou et al and Minoshima et al summarized the common ML techniques used in radiology such as feed-forward neural networks (FFNN) and convolutional neural networks (CNN) [ 78 , 79 ]. This work showed that most AI studies in hybrid imaging employ a CNN or generative adversarial network (GAN) as a part of the classification model.…”

Section: Discussionmentioning

confidence: 99%

“…More in-depth discussions surrounding artificial intelligence (AI) and machine learning (ML) were present across all article types within this review [78][79][80]. Zhou et al and Minoshima et al summarized the common ML techniques used in radiology such as feed-forward neural networks (FFNN) and convolutional neural networks (CNN) [78,79].…”

Section: Artificial Intelligencementioning

confidence: 99%

See 1 more Smart Citation

Current Trends and Applications of PET/MRI Hybrid Imaging in Neurodegenerative Diseases and Normal Aging

Lee,

Renslo,

Wong

et al. 2024

Diagnostics

View full text Add to dashboard Cite

Dementia is a significant global health issue that is exacerbated by an aging population. Imaging plays an established role in the evaluation of patients with neurocognitive disorders such as dementia. In current clinical practice, magnetic resonance imaging (MRI) and positron emission tomography (PET) are primary imaging modalities used separately but in concert to help diagnose and classify dementia. The clinical applications of PET/MRI hybrid imaging in dementia are an active area of research, particularly given the continued emergence of functional MRI (fMRI) and amyloid PET tracers. This narrative review provides a comprehensive overview of the rationale and current evidence for PET/MRI hybrid dementia imaging from 2018 to 2023. Hybrid imaging offers advantages in the accuracy of characterizing neurodegenerative disorders, and future research will need to address the cost of integrated PET/MRI systems compared to stand-alone scanners, the development of new biomarkers, and image correction techniques.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Artificial Intelligencementioning

confidence: 99%

Current Trends and Applications of PET/MRI Hybrid Imaging in Neurodegenerative Diseases and Normal Aging

Lee,

Renslo,

Wong

et al. 2024

Diagnostics

View full text Add to dashboard Cite

show abstract

“…It could be used for all phases of Alzheimer's disease as well as to differentiate between healthy people and the ill. Additionally, MRI could be utilized for the detection of mild cognitive impairment (MCI) and Alzheimer's disease (AD), as well as the conversion from MCI to AD. It can also be used to distinguish between distinct forms of dementia, such as frontotemporal dementia and AD, which may exhibit similar clinical symptoms [6,7].…”

Section: Introductionmentioning

confidence: 99%

Severity Grading and Early Detection of Alzheimer’s Disease through Transfer Learning

Alqahtani,

Zohdy

et al. 2023

Information

View full text Add to dashboard Cite

Alzheimer’s disease (AD) is an illness affecting the neurological system in people commonly aged 65 years and older. It is one of the leading causes of dementia and, subsequently, the cause of death as it gradually affects and destroys brain cells. In recent years, the detection of AD has been examined in ways to mitigate its impacts while considering early detection through computer-aided diagnosis (CAD) tools. In this study, we developed deep learning models that focus on early detection and classifying each case, non-demented, moderate-demented, mild-demented, and very-mild-demented, accordingly through transfer learning (TL); an AlexNet, ResNet-50, GoogleNet (InceptionV3), and SqueezeNet by utilizing magnetic resonance images (MRI) and the use of image augmentation. The acquired images, a total of 12,800 images and four classifications, had to go through a pre-processing phase to be balanced and fit the criteria of each model. Each of these proposed models split the data into 80% training and 20% testing. AlexNet performed an average accuracy of 98.05%, GoogleNet (InceptionV3) performed an average accuracy of 97.80%, and ResNet-50 had an average performing accuracy of 91.11%. The transfer learning approach assists when there is not adequate data to train a network from the start, which aids in tackling one of the major challenges faced when working with deep learning.

show abstract

Counseling and disclosure practices in predictive Alzheimer's disease diagnostics: A scoping review

Perry,

Radenbach,

Geschke

et al. 2024

Alzheimer's & Dementia

View full text Add to dashboard Cite

New possibilities of biomarker‐based predictive technologies for Alzheimer's disease (AD) have become more reliable as well as more accessible. Standardized clinical recommendations and guidance for counseling and disclosure in this context are not yet well developed. Our scoping review identified publications from database searches in PubMed, PsycINFO, LIVIVO, and Web of Science. Inclusion criteria were: (1) information or counseling, (2) biomarkers and a type of cognitive impairment or AD, and (3) published between 2005 and 2024. We identified 63 articles and synthesized them along the categories of staged information provision: pre‐test counseling, disclosure, and post‐disclosure follow‐up. Most publications referred to the context of disclosure (48), followed by pre‐test counseling (33), and post‐disclosure follow‐up (31). Some publications referred to all stages of counseling (17). Our findings highlight the need to further develop and specify comprehensive and standardized guidelines for counseling, disclosure, and post‐disclosure follow‐up in the context of AD biomarker testing.Highlights New possibilities of biomarker‐based predictive technologies for Alzheimer's disease (AD) have become more reliable and also more accessible. However, clinical recommendations and guidance for counseling and disclosure in the context of AD biomarker testing are currently not well developed. We carried out a scoping review with the aim to generate an overview of the scientific literature and guidance available regarding counseling, biomarker test result and dementia risk disclosure, and clinical management prior to and in the course of a biomarker‐based diagnosis in early stages of AD. We identified 63 relevant articles. Most publications referred to the context of disclosure (48), followed by pre‐test counseling (33), and post‐disclosure follow‐up (31). Some publications referred to all stages of counseling (17). Our findings highlight the urgent need for national and international consensus guidelines for comprehensive and staged counseling and disclosure practices. While most publications identify relevant ethical challenges posed for counseling practices in the context of AD biomarker testing, they rarely present any practical recommendations for clinicians, on how and what to counsel on a concrete level.

show abstract

Application of Deep Learning for Prediction of Alzheimer’s Disease in PET/MR Imaging

Cited by 13 publications

References 97 publications

Current Trends and Applications of PET/MRI Hybrid Imaging in Neurodegenerative Diseases and Normal Aging

Current Trends and Applications of PET/MRI Hybrid Imaging in Neurodegenerative Diseases and Normal Aging

Severity Grading and Early Detection of Alzheimer’s Disease through Transfer Learning

Counseling and disclosure practices in predictive Alzheimer's disease diagnostics: A scoping review

Contact Info

Product

Resources

About