A 3D convolutional neural network to ...
Type de document :
Article dans une revue scientifique: Article original
PMID :
URL permanente :
Titre :
A 3D convolutional neural network to classify subjects as Alzheimer's disease, frontotemporal dementia or healthy controls using brain 18F-FDG PET.
Auteur(s) :
Rogeau, Antoine [Auteur]
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Hives, Florent [Auteur]
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Bordier, Cecile [Auteur]
Lille in vivo imaging and Functional Exploration - PLBS [LiiFE]
Lahousse, Hélène [Auteur]
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Roca, Vincent [Auteur]
Lille in vivo imaging and Functional Exploration - PLBS [LiiFE]
Lebouvier, Thibaud [Auteur]
Lille Neurosciences & Cognition (LilNCog) - U 1172
Pasquier, Florence [Auteur]
Lille Neurosciences & Cognition (LilNCog) - U 1172
Huglo, Damien [Auteur]
Thérapies Lasers Assistées par l'Image pour l'Oncologie (ONCO-THAI) - U1189
Semah, Franck [Auteur]
Lille Neurosciences & Cognition (LilNCog) - U 1172
Lopes, Renaud [Auteur]
Lille Neurosciences & Cognition (LilNCog) - U 1172
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Hives, Florent [Auteur]
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Bordier, Cecile [Auteur]
Lille in vivo imaging and Functional Exploration - PLBS [LiiFE]
Lahousse, Hélène [Auteur]
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Roca, Vincent [Auteur]
Lille in vivo imaging and Functional Exploration - PLBS [LiiFE]
Lebouvier, Thibaud [Auteur]
![refId](/themes/Mirage2//images/idref.png)
Lille Neurosciences & Cognition (LilNCog) - U 1172
Pasquier, Florence [Auteur]
![refId](/themes/Mirage2//images/idref.png)
Lille Neurosciences & Cognition (LilNCog) - U 1172
Huglo, Damien [Auteur]
![refId](/themes/Mirage2//images/idref.png)
Thérapies Lasers Assistées par l'Image pour l'Oncologie (ONCO-THAI) - U1189
Semah, Franck [Auteur]
![refId](/themes/Mirage2//images/idref.png)
Lille Neurosciences & Cognition (LilNCog) - U 1172
Lopes, Renaud [Auteur]
![refId](/themes/Mirage2//images/idref.png)
Lille Neurosciences & Cognition (LilNCog) - U 1172
Titre de la revue :
NeuroImage
Nom court de la revue :
Neuroimage
Pagination :
120530
Date de publication :
2024-02-05
ISSN :
1095-9572
Mot(s)-clé(s) en anglais :
FDG PET
Deep learning
Alzheimer's disease
Frontotemporal dementia
Convolutional neural network
Deep learning
Alzheimer's disease
Frontotemporal dementia
Convolutional neural network
Discipline(s) HAL :
Sciences cognitives
Résumé en anglais : [en]
With the arrival of disease-modifying drugs, neurodegenerative diseases will require an accurate diagnosis for optimal treatment. Convolutional neural networks are powerful deep learning techniques that can provide great ...
Lire la suite >With the arrival of disease-modifying drugs, neurodegenerative diseases will require an accurate diagnosis for optimal treatment. Convolutional neural networks are powerful deep learning techniques that can provide great help to physicians in image analysis. The purpose of this study is to introduce and validate a 3D neural network for classification of Alzheimer's disease (AD), frontotemporal dementia (FTD) or cognitively normal (CN) subjects based on brain glucose metabolism. Retrospective [18F]-FDG-PET scans of 199 CE, 192 FTD and 200 CN subjects were collected from our local database, Alzheimer's disease and frontotemporal lobar degeneration neuroimaging initiatives. Training and test sets were created using randomization on a 90 %-10 % basis, and training of a 3D VGG16-like neural network was performed using data augmentation and cross-validation. Performance was compared to clinical interpretation by three specialists in the independent test set. Regions determining classification were identified in an occlusion experiment and Gradient-weighted Class Activation Mapping. Test set subjects were age- and sex-matched across categories. The model achieved an overall 89.8 % accuracy in predicting the class of test scans. Areas under the ROC curves were 93.3 % for AD, 95.3 % for FTD, and 99.9 % for CN. The physicians' consensus showed a 69.5 % accuracy, and there was substantial agreement between them (kappa = 0.61, 95 % CI: 0.49–0.73). To our knowledge, this is the first study to introduce a deep learning model able to discriminate AD and FTD based on [18F]-FDG PET scans, and to isolate CN subjects with excellent accuracy. These initial results are promising and hint at the potential for generalization to data from other centers.Lire moins >
Lire la suite >With the arrival of disease-modifying drugs, neurodegenerative diseases will require an accurate diagnosis for optimal treatment. Convolutional neural networks are powerful deep learning techniques that can provide great help to physicians in image analysis. The purpose of this study is to introduce and validate a 3D neural network for classification of Alzheimer's disease (AD), frontotemporal dementia (FTD) or cognitively normal (CN) subjects based on brain glucose metabolism. Retrospective [18F]-FDG-PET scans of 199 CE, 192 FTD and 200 CN subjects were collected from our local database, Alzheimer's disease and frontotemporal lobar degeneration neuroimaging initiatives. Training and test sets were created using randomization on a 90 %-10 % basis, and training of a 3D VGG16-like neural network was performed using data augmentation and cross-validation. Performance was compared to clinical interpretation by three specialists in the independent test set. Regions determining classification were identified in an occlusion experiment and Gradient-weighted Class Activation Mapping. Test set subjects were age- and sex-matched across categories. The model achieved an overall 89.8 % accuracy in predicting the class of test scans. Areas under the ROC curves were 93.3 % for AD, 95.3 % for FTD, and 99.9 % for CN. The physicians' consensus showed a 69.5 % accuracy, and there was substantial agreement between them (kappa = 0.61, 95 % CI: 0.49–0.73). To our knowledge, this is the first study to introduce a deep learning model able to discriminate AD and FTD based on [18F]-FDG PET scans, and to isolate CN subjects with excellent accuracy. These initial results are promising and hint at the potential for generalization to data from other centers.Lire moins >
Langue :
Anglais
Audience :
Internationale
Vulgarisation :
Non
Établissement(s) :
Université de Lille
Inserm
CHU Lille
Inserm
CHU Lille
Collections :
Date de dépôt :
2024-03-15T22:01:45Z
2024-05-17T12:54:33Z
2024-05-17T12:54:33Z
Fichiers
- 1-s2.0-S1053811924000259-main.pdf
- Non spécifié
- Accès libre
- Accéder au document