2021
DOI: 10.1016/j.expneurol.2021.113608
|View full text |Cite
|
Sign up to set email alerts
|

Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
22
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
4
3
2
1

Relationship

1
9

Authors

Journals

citations
Cited by 39 publications
(22 citation statements)
references
References 255 publications
0
22
0
Order By: Relevance
“…Model selection is the process of selecting the hyperparameters of the best-performing model. The hyperparameters must be set manually after finding the optimal hyperparameter configuration as per the model selection process [110].…”
Section: Plos Onementioning
confidence: 99%
“…Model selection is the process of selecting the hyperparameters of the best-performing model. The hyperparameters must be set manually after finding the optimal hyperparameter configuration as per the model selection process [110].…”
Section: Plos Onementioning
confidence: 99%
“…The dependence of AI on su cient labeled data to yield models with proper generalization and reliable results has been discussed frequently [14], [17], [94]. Due to data privacy concerns, this is a pain-point for all medical AI development.…”
Section: Potential Validity Threatsmentioning
confidence: 99%
“…Machine learning-based techniques such as support vector machine (SVM) classification and regression provide promising approaches to differentiate normal from pathological neurocognitive aging. They have been employed to predict chronological age from structural magnetic resonance imaging (MRI; Cole et al, 2017, 2018), to estimate brain age (Bashyam et al, 2020; Habes et al, 2021) or to distinguish health from disease (Dyrba et al, 2021; Eitel et al, 2021).…”
Section: Introductionmentioning
confidence: 99%