Abstract: Anomalies in images are detected. A generative network and/or an autoencoder (“G/A-Network”), a Siamese network, a first training-dataset of normal images and a second training-dataset of abnormal images are provided. The G/A-network is trained to produce latent data from input images and output images from the latent data, wherein the training is performed with images of the first training-dataset, wherein a loss function is used for training at least at the beginning of training, and the loss function enhances the similarity of the input images and respective output images. The Siamese network is trained to generate similarity measures between input images and respective output images, wherein the training is performed with images of the first training-dataset and the second training-dataset in that images of both training-datasets are used as input images for the G/A-network and output images of the G/A-network are compared with their respective input images by the Siamese network.

Abstract: A first sequence of cardiac image frames are received by a first neural network of the neural network system. The first neural network outputs a first set of feature values. The first set of feature values includes a plurality of data subsets, each corresponding to a respective image frame and relating to spatial features of the respective image frame. The first set of feature values are received at a second neural network of the neural network system. The second neural network outputs a second set of feature values relating to temporal features of the spatial features. Based on the second set of feature values, a cardiac phase value relating to a cardiac phase associated with a first image frame is determined.

Abstract: A method, apparatus and non-transitory computer readable medium are for segmenting different types of structures, including cancerous lesions and regular structures like vessels and skin, in a digital breast tomosynthesis (DBT) volume. In an embodiment, the method includes: pre-classification of the DBT volume in dense and fatty tissue and based on the result; localizing a set of structures in the DBT volume by using a multi-stream deep convolutional neural network; and segmenting the localized structures by calculating a probability for belonging to a specific type of structure for each voxel in the DBT volume by using a deep convolutional neural network for providing a three-dimensional probabilistic map.

Abstract: A first sequence of cardiac image frames are received by a first neural network of the neural network system. The first neural network outputs a first set of feature values. The first set of feature values includes a plurality of data subsets, each corresponding to a respective image frame and relating to spatial features of the respective image frame. The first set of feature values are received at a second neural network of the neural network system. The second neural network outputs a second set of feature values relating to temporal features of the spatial features. Based on the second set of feature values, a cardiac phase value relating to a cardiac phase associated with a first image frame is determined.

Abstract: A method, apparatus and non-transitory computer readable medium are for segmenting different types of structures, including cancerous lesions and regular structures like vessels and skin, in a digital breast tomosynthesis (DBT) volume. In an embodiment, the method includes: pre-classification of the DBT volume in dense and fatty tissue and based on the result; localizing a set of structures in the DBT volume by using a multi-stream deep convolutional neural network; and segmenting the localized structures by calculating a probability for belonging to a specific type of structure for each voxel in the DBT volume by using a deep convolutional neural network for providing a three-dimensional probabilistic map.