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: Methods are provided for the removal of sulfur and other ARD/AMD-generating materials through the smoldering combustion of an organic material. The methods comprise admixing an ARD/AMD-generating porous matrix material with an organic material to produce a mixture, exposing the mixture to an oxidant, and initiating a self-sustaining smoldering combustion of the mixture. Additional embodiments aggregate the organic material or ARD/AMD-generating porous matrix material or mixture thereof in an impoundment such as a reaction vessel, depression or matrix pile. Further embodiments utilize at least one heater to initiate combustion and at least one air supply port to supply oxidant to initiate and maintain combustion.

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 method for remediating contaminated soil and groundwater includes selecting a treatment material and creating a smolderable mixture of a contaminant, the treatment material, and soil.

Abstract: A method for remediating a contaminated porous matrix including selecting the type and quantity of organic fuel to create a smolderable mixture of the organic fuel and contaminated porous matrix, and controlling the rate of oxidant addition to manipulate the relative proportions of oxidative breakdown products, non-oxidative breakdown products, and non-destructive remediation processes. The method further involves collecting the volatilized contaminant, and any gaseous breakdown products of the contaminant.

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 remediating contaminated soil and groundwater includes selecting a treatment material and creating a smolderable mixture of a contaminant, the treatment material, and soil.

Abstract: A method for remediating contaminated soil and groundwater includes selecting a treatment material and creating a smolderable mixture of a contaminant, the treatment material, and soil.

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 method for remediating a contaminated porous matrix including selecting the type and quantity of organic fuel to create a smolderable mixture of the organic fuel and contaminated porous matrix, and controlling the rate of oxidant addition to manipulate the relative proportions of oxidative breakdown products, non-oxidative breakdown products, and non-destructive remediation processes. The method further involves collecting the volatilized contaminant, and any gaseous breakdown products of the contaminant.

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: Methods are provided for the removal of sulfur and other ARD/AMD-generating materials through the smoldering combustion of an organic material. The methods comprise admixing an ARD/AMD-generating porous matrix material with an organic material to produce a mixture, exposing the mixture to an oxidant, and initiating a self-sustaining smoldering combustion of the mixture. Additional embodiments aggregate the organic material or ARD/AMD-generating porous matrix material or mixture thereof in an impoundment such as a reaction vessel, depression or matrix pile. Further embodiments utilize at least one heater to initiate combustion and at least one air supply port to supply oxidant to initiate and maintain combustion.

Abstract: Methods are provided for generating or recovering gaseous materials such as hydrogen and solids such as metals through the smoldering combustion of an organic material. The methods include admixing a porous matrix material with an organic material, and, in some embodiments a catalyst, to produce a porous mixture. The mixture is exposed to an oxidant, initiating a self-sustaining smoldering combustion of the mixture, and collecting the vapors and combustion products or processing the porous matrix following combustion to physically separate the porous matrix material from ash containing inorganic materials of value. Additional embodiments aggregate the organic material or catalyst or porous matrix material or mixture thereof in an impoundment such as a reaction vessel, lagoon or matrix pile. Further embodiments utilize at least one heater to initiate combustion and at least one air supply port to supply oxidant to initiate and maintain combustion.

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: Operations include storing and/or accessing data in tape volume containers. A system receives a request to access a tape block in a data storage tape. The system maps the requested tape block in the data storage tape to an object in a container. The system then retrieves data from the object in the container. The system generates, from the retrieved data, a data stream in tape archive format. The system transmits the data stream, in tape archive format, in response to the request to access the tape block in the data storage tape.

Abstract: Methods are provided for generating or recovering gaseous materials such as hydrogen and solids such as metals through the smoldering combustion of an organic material. The methods include admixing a porous matrix material with an organic material, and, in some embodiments a catalyst, to produce a porous mixture. The mixture is exposed to an oxidant, initiating a self-sustaining smoldering combustion of the mixture, and collecting the vapors and combustion products or processing the porous matrix following combustion to physically separate the porous matrix material from ash containing inorganic materials of value. Additional embodiments aggregate the organic material or catalyst or porous matrix material or mixture thereof in an impoundment such as a reaction vessel, lagoon or matrix pile. Further embodiments utilize at least one heater to initiate combustion and at least one air supply port to supply oxidant to initiate and maintain combustion.