3D Brain MRI Classification for Alzheimer Diagnosis Using CNN with Data Augmentation
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913897661857792 |
|---|---|
| author | Vo, Thien Nhan Ho, Bac Nam |
| author_facet | Vo, Thien Nhan Ho, Bac Nam |
| contents | A three-dimensional convolutional neural network was developed to classify T1-weighted brain MRI scans as healthy or Alzheimer. The network comprises 3D convolution, pooling, batch normalization, dense ReLU layers, and a sigmoid output. Using stochastic noise injection and five-fold cross-validation, the model achieved test set accuracy of 0.912 and area under the ROC curve of 0.961, an improvement of approximately 0.027 over resizing alone. Sensitivity and specificity both exceeded 0.90. These results align with prior work reporting up to 0.10 gain via synthetic augmentation. The findings demonstrate the effectiveness of simple augmentation for 3D MRI classification and motivate future exploration of advanced augmentation methods and architectures such as 3D U-Net and vision transformers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04097 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | 3D Brain MRI Classification for Alzheimer Diagnosis Using CNN with Data Augmentation Vo, Thien Nhan Ho, Bac Nam Image and Video Processing Computer Vision and Pattern Recognition Machine Learning A three-dimensional convolutional neural network was developed to classify T1-weighted brain MRI scans as healthy or Alzheimer. The network comprises 3D convolution, pooling, batch normalization, dense ReLU layers, and a sigmoid output. Using stochastic noise injection and five-fold cross-validation, the model achieved test set accuracy of 0.912 and area under the ROC curve of 0.961, an improvement of approximately 0.027 over resizing alone. Sensitivity and specificity both exceeded 0.90. These results align with prior work reporting up to 0.10 gain via synthetic augmentation. The findings demonstrate the effectiveness of simple augmentation for 3D MRI classification and motivate future exploration of advanced augmentation methods and architectures such as 3D U-Net and vision transformers. |
| title | 3D Brain MRI Classification for Alzheimer Diagnosis Using CNN with Data Augmentation |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2505.04097 |