人工智能
模式识别(心理学)
计算机科学
异常检测
离群值
卷积神经网络
体素
癫痫
流体衰减反转恢复
磁共振成像
特征向量
无监督学习
医学
放射科
心理学
神经科学
作者
Zaruhi Alaverdyan,Julien Jung,Romain Bouet,Carole Lartizien
标识
DOI:10.1016/j.media.2019.101618
摘要
In this study, we propose a novel anomaly detection model targeting subtle brain lesions in multiparametric MRI. To compensate for the lack of annotated data adequately sampling the heterogeneity of such pathologies, we cast this problem as an outlier detection problem and introduce a novel configuration of unsupervised deep siamese networks to learn normal brain representations using a series of non-pathological brain scans. The proposed siamese network, composed of stacked convolutional autoencoders as subnetworks is designed to map patches extracted from healthy control scans only and centered at the same spatial localization to ‘close’ representations with respect to the chosen metric in a latent space. It is based on a novel loss function combining a similarity term and a regularization term compensating for the lack of dissimilar pairs. These latent representations are then fed into oc-SVM models at voxel-level to produce anomaly score maps. We evaluate the performance of our brain anomaly detection model to detect subtle epilepsy lesions in multiparametric (T1-weighted, FLAIR) MRI exams considered as normal (MRI-negative). Our detection model trained on 75 healthy subjects and validated on 21 epilepsy patients (with 18 MRI-negatives) achieves a maximum sensitivity of 61% on the MRI-negative lesions, identified among the 5 most suspicious detections on average. It is shown to outperform detection models based on the same architecture but with stacked convolutional or Wasserstein autoencoders as unsupervised feature extraction mechanisms.
科研通智能强力驱动
Strongly Powered by AbleSci AI