Voxelwise 3D Convolutional and Recurrent Neural Networks for Epilepsy and Depression Diagnostics from Structural and Functional MRI Data

Pominova, Marina; Artemov, Alexey; Sharaev, Maxim; Kondrateva, Ekaterina; Bernstein, Alexander; Burnaev, Evgeny

doi:10.1109/icdmw.2018.00050

Cited by 27 publications

(18 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to the conventional automated brain segmentation methods, visualizations based on these more abstract representations may provide additional information with regard to the relationship between brain architecture and body weight. Similarly, several recent studies applied the Grad-CAM method to highlight brain regions that made an important contribution to predicting depression and epilepsy (Pominova et al, 2018), brain age (Bermudez et al, 2019), and Alzheimer's disease (Feng et al, 2018) based on structural MRI data.…”

Section: Discussionmentioning

confidence: 99%

Predicting Body Mass Index From Structural MRI Brain Images Using a Deep Convolutional Neural Network

Vakli

Deák-Meszlényi

Auer

et al. 2020

Front. Neuroinform.

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Predicting Body Mass Index From Structural MRI Brain Images Using a Deep Convolutional Neural Network

Vakli

Deák-Meszlényi

Auer

et al. 2020

Front. Neuroinform.

View full text Add to dashboard Cite

“…Miholca & Onicas obtained an accuracy of 92% using an MLP on task fMRI, but they selected features on the whole dataset, including test data. Pominova et al (2018) 55 is one of the rare studies that did not perform feature engineering, but applied a 3DConvLSTM model on full 4D fMRI data. They obtained an accuracy of 73% on a relatively small dataset of 50 subjects.…”

Section: Resultsmentioning

confidence: 99%

“…These four studies have relatively small sample sizes, ranging from 49 to 163. One study (2018) 55 is one of the rare studies that did not perform feature engineering, but applied a 3DConvLSTM model on full 4D fMRI data. They obtained an accuracy of 73% on a relatively small dataset of 50 subjects.…”

Section: Other Disordersmentioning

confidence: 99%

Deep learning applications for the classification of psychiatric disorders using neuroimaging data: systematic review and meta-analysis

Quaak

Mortel

Thomas

et al. 2020

Preprint

View full text Add to dashboard Cite

Deep learning (DL) methods have been increasingly applied to neuroimaging data to identify patients with psychiatric and neurological disorders. This review provides an overview of the different DL applications within psychiatry and compares DL model accuracy to conventional machine learning (ML). Fifty-three articles were included for qualitative analysis, primarily investigating autism spectrum disorder (ASD; n=22), schizophrenia (SZ; n=22) and attention-deficit/hyperactivity disorder (ADHD; n=9). Thirty-two of the thirty-five studies that directly compared DL to ML reported a higher accuracy for DL. Only sixteen studies could be included in a meta-regression to quantitatively compare DL and ML performance. This showed a higher odds ratio for DL models, though the comparison attained significance only for ASD. These results suggest that deep learning of neuroimaging data is a promising tool for the classification of individual psychiatric patients. The current evaluation is limited by minimal reporting of performance measures to enable quantitative comparisons, and the restriction to ADHD, SZ and ASD as current research focusses on large publicly available datasets.

show abstract

“…It is used as a diagnostic tool for various types of cancer, diseases of the central nervous system, such as multiple sclerosis or epilepsy (Hammers et al, 2007; Sharaev et al, 2018a,b), depression (Sheline, 2000; Ivanov et al, 2018) and in plenty other cases (Ronneberger et al, 2015; Çiçek et al, 2016). Recent advances in computer vision revealed a high potential for application of neural networks in the medical problems: classification of MRI or CT for disease diagnosis, automatic detection and segmentation of different pathologies (Gong et al, 2007; Davatzikos et al, 2008; Pominova et al, 2018). Even though it is unlikely that these models will be used as a diagnostic tool without any human intervention in the nearest future, they could be beneficial serving as decision support systems.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Generative Models for Knowledge Transfer in MRI Semantic Segmentation Problems

2019

Self Cite

View full text Add to dashboard Cite

Automatic segmentation methods based on deep learning have recently demonstrated state-of-the-art performance, outperforming the ordinary methods. Nevertheless, these methods are inapplicable for small datasets, which are very common in medical problems. To this end, we propose a knowledge transfer method between diseases via the Generative Bayesian Prior network. Our approach is compared to a pre-train approach and random initialization and obtains the best results in terms of Dice Similarity Coefficient metric for the small subsets of the Brain Tumor Segmentation 2018 database (BRATS2018).

show abstract

Voxelwise 3D Convolutional and Recurrent Neural Networks for Epilepsy and Depression Diagnostics from Structural and Functional MRI Data

Cited by 27 publications

References 36 publications

Predicting Body Mass Index From Structural MRI Brain Images Using a Deep Convolutional Neural Network

Predicting Body Mass Index From Structural MRI Brain Images Using a Deep Convolutional Neural Network

Deep learning applications for the classification of psychiatric disorders using neuroimaging data: systematic review and meta-analysis

Bayesian Generative Models for Knowledge Transfer in MRI Semantic Segmentation Problems

Contact Info

Product

Resources

About