Abstract: A method of augmenting the number of labeled images for training a neural network comprising the steps of—Starting from a dataset of labeled images with corresponding segmentation masks and a dataset of unlabeled images, gathering for a given image i in a data set of labeled images a number of images with similar metadata in said dataset of unlabeled images so as to form data sub-set Sim i,—Training a multiclass segmentation neural network on said labeled images thereby generating segmentation masks for the images in subset Sim i,—On the basis of these segmentation masks judging similarity between images of Sim i and image i and finding the most similar image(s) in Sim i by computing and comparing histograms of segmentation masks of image i and images in Sim i—Transferring the histogram of the most similar images in Sim i to given image i.

Abstract: Method of segmenting anatomical structures such as organs in 3D scans in an architecture that combines U-net, time-distributed convolutions and bidirectional convolutional LSTM.

Abstract: A neural network, trained for the task of deriving the attribution of image regions that significantly influence classification in a tool for pathology classification, comprising (i) a contracting branch, (ii) an attenuation module, (iii) an interconnected upsampling branch, and (iv) a final mapping module.

Abstract: A method for finding image regions that significantly influence classification in a tool for pathology classification in a medical image wherein image regions that influence classification are inpainted, by replacing the pixels in these regions by representations of heathy tissue, resulting in an image with a healthy classification-score in the classification tool.

Abstract: A composition of microorganisms, comprising photoautotrophic microorganisms (16) which produce oxygen by photosynthetic water oxidation chemoheterotrophic microorganisms (17) which respire oxygen, wherein the photoautotrophic microorganisms (16) and the chemoheterotrophic microorganisms (17) are comprised in a biofilm (13), the biofilm further comprising components (15) which were secreted by the photoautotrophic microorganisms (16) and/or the chemoheterotrophic microorganisms (17), and a reactor (1), a method for forming a biofilm, and a method for biocatalytic conversion employing such composition.

Abstract: A method for training an artificial neural network on an additional untrained segmentation task prevents the loss of previously acquired segmentation skills on originally trained segmentation tasks.

Abstract: Method of segmenting anatomical structures such as organs in 3D scans in an architecture that combines U-net, time-distributed convolutions and bidirectional convolutional LSTM.

Abstract: A pipe-line method for multi-label segmentation of anatomic structures in a medical image using a convolutional neural network trained with a weighted loss function takes into account under—representation of at least one anatomical structure in a ground-truth mask relative to other anatomical structures. Different architectures for the convolutional neural network are described.

Abstract: A method for training an artificial neural network on an additional untrained segmentation task prevents the loss of previously acquired segmentation skills on originally trained segmentation tasks.

Abstract: A pipe-line method for multi-label segmentation of anatomic structures in a medical image using a convolutional neural network trained with a weighted loss function takes into account under—representation of at least one anatomical structure in a ground-truth mask relative to other anatomical structures. Different architectures for the convolutional neural network are described.

Abstract: A method and system for automatically detecting systemic arteries in arbitrary field-of-view computed tomography angiography (CTA) includes fully-automatically analyzing a medical image represented by a digital image representation.

Abstract: A method, and an according apparatus and system, for analyzing medical images of blood vessels includes the steps of a) classifying a surrounding of at least one vessel represented in at least one medical image by applying a first classifier to the medical image such that the surrounding of the vessel is assigned to one of at least two surrounding classes, and b) segmentation of the at least one vessel dependent on the surrounding class to which the surrounding of the vessel has been assigned. The invention allows for a reliable segmentation and/or shape detection, in particular bifurcation detection, of blood vessels represented in medical images.

Abstract: A method and system for automatically detecting systemic arteries in arbitrary field-of-view computed tomography angiography (CTA) includes fully-automatically analyzing a medical image represented by a digital image representation.

Abstract: A method, an apparatus, and a system for labeling one or more parts of a spine in at least one magnetic resonance image of a human or animal body, includes transforming the image having a first number of intensity levels into a target image having a second number of intensity levels, the second number of intensity levels being smaller than the first number of intensity levels, preferably by considering the entropy of texture variations in one or more training images; determining a position, in particular a center position, in each of the one or more parts of the spine in the target image; and labeling the determined position of the one or more parts of the spine in the image or the target image with anatomical labels.

Abstract: A method, and an according apparatus and system, for analyzing medical images of blood vessels includes the steps of a) classifying a surrounding of at least one vessel represented in at least one medical image by applying a first classifier to the medical image such that the surrounding of the vessel is assigned to one of at least two surrounding classes, and b) segmentation of the at least one vessel dependent on the surrounding class to which the surrounding of the vessel has been assigned. The invention allows for a reliable segmentation and/or shape detection, in particular bifurcation detection, of blood vessels represented in medical images.

Abstract: A method, and an according apparatus and system, for segmentation of anatomical structures in medical images includes segmenting an anatomical structure represented in a medical image by applying an algorithm based on a morphological active contour without edges (MACWE) to the medical image, wherein in the algorithm based on the morphological active contour without edges one or more features relating to a surrounding and/or context of the anatomical structure represented in the medical image are considered.

Abstract: A method, apparatus, and system for reliably identifying a specific part of a spine in an image of a human or animal body, includes the steps of determining one or more parts of the spine in the image, determining one or more discriminative parameters for each of the one or more parts of the spine in the image, the discriminative parameters relating to at least one anatomical property of each of the one or more parts of the spine, classifying the discriminative parameters of the one or more parts of the spine in the image, and identifying a specific part of the spine based on the classification of the discriminative parameters of the one or more parts of the spine in the image. An identified vertebra, in particular the T12 vertebra and/or its associated intervertebral discs, can be used advantageously as a starting point of powerful automatic spine labeling algorithms.

Abstract: A method and a corresponding apparatus and system localizes a spine in an image, in particular a computed tomography (CT) image, of a human or animal body, allowing for a reduced need for computational power and/or memory on the one hand and assuring a reliable localization of the spine on the other hand. The method includes a) acquiring a plurality of slice images of at least a part of a human or animal body, and b) automatically selecting slice images and/or parts of slice images from the acquired plurality of slice images by considering at least one parameter (?z, ?z, ?z, ?z) characterizing a distribution of bones in the acquired slice images, wherein the selected slice images and/or parts of the slice images includes image information about the spine.

Abstract: A method, apparatus, and system for reliably identifying a specific part of a spine in an image of a human or animal body, includes the steps of determining one or more parts of the spine in the image, determining one or more discriminative parameters for each of the one or more parts of the spine in the image, the discriminative parameters relating to at least one anatomical property of each of the one or more parts of the spine, classifying the discriminative parameters of the one or more parts of the spine in the image, and identifying a specific part of the spine based on the classification of the discriminative parameters of the one or more parts of the spine in the image. An identified vertebra, in particular the T12 vertebra and/or its associated intervertebral discs, can be used advantageously as a starting point of powerful automatic spine labeling algorithms.

Abstract: A method, an apparatus, and a system label one or more parts of a spine in an image, in particular a computed tomography (CT) image, of a human or animal body, and in order to achieve a reliable spine labeling and a high throughput of images, match a model of a spine segment with segments of the spine in the image by starting matching the model of a spine segment with an initial segment of the spine in the image, wherein the initial segment of the spine in the image is located at an initial position along the spine in the image, and continue to match the model of a spine segment with one or more further segments of the spine in the image, wherein the further segments of the spine in the image are located at positions farther along the spine in the image.