Unsupervised Anomaly Detection for Fetal Brain MRI using Two-Stage Denoising Autoencoder (ω-DAE)
Résumé
Fetal germinal matrix and intraventricular hemorrhage (GMH-IVH) is the most common type of fetal brain hemorrhage and holds significant clinical importance. MRI is pivotal for the early detection of subtle prenatal GMH-IVH lesions, which manifest as hypointense signals in T2-weighted MRI. Deep learning emerges as a powerful tool for detecting such lesions from MRI, but they require large datasets from diseased subjects with ground-truth labels for training. Unfortunately, such datasets are difficult to obtain due to the rarity of GMH-IVH (0.5‰–0.9‰) and the challenges in annotating fetal MRI. Moreover, the low signal-to-noise ratio (SNR) in fetal brain MRI causes existing unsupervised anomaly detection methods to struggle with precise lesion segmentation. To address these challenges, we propose the ω-DAE based on 3D convolutional neural networks (CNNs) for unsupervised diagnosis of GMH-IVH.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |