Abstract: Systems, methods, and apparatus for segmenting internal structures depicted in an image. In one aspect, a method includes receiving data representing image data that depicts internal structures of a subject, providing an input data structure to a machine learning model, wherein the input data structure comprises fields structuring data that represents the received data representing the image data that depicts internal structures of the subject, wherein the machine learning model is a multi-stage deep convolutional network that has been trained to segment internal structures depicted by one or more images, receiving output data generated by the machine learning model based on the machine learning model's processing of the input data structure, and processing the output data to generate rendering data that, when rendered, a computer, causes the computer to output, for display, data that visually distinguishes between different internal structures depicted by the image data.

Abstract: Methods, systems, apparatus, and computer programs, for processing images through multiple neural networks that are trained to detect a pancreatic ductal adenocarcinoma. In one aspect, a method includes actions of obtaining a first image that depicts a first volume of voxels, performing coarse segmentation of the first image using a first neural network trained (i) to process images having the first volume of voxels and (ii) to produce first output data, determining a region of interest of the first image based on the coarse segmentation, performing multi-stage fine segmentation on a plurality of other images that are each based on the region of interest of the first image to generate output data for each stage of the multi-stage fine segmentation, and determining based on the first output data and the output data of each stage of the multi-stage fine segmentation, whether the first image depicts a tumor.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, used for object detection in an input image that can include at least partial object occlusion. In some implementations, input data representing the image depicting an object can include object-based features and context-based features used for object detection. The feature is processed by a deep convolutional neural network (DCNN) model. First feature data generated by the DCNN is provided to an occlusion model and a generative compositional model. The occlusion model can detect locations where an object depicted in the image is occluded by an object of any other type. The generative compositional model detects the presence of different classes of objects that represent parts or partial components of object depicted in the image. The output of the compositional model and occlusion model is a likelihood map that shows if an object is depicted in the input image.

Abstract: Methods, systems, and apparatuses, including computer programs for detecting pancreatic neoplasms. A method includes providing an image as an input to a first model, obtaining first output data generated by the first model based on the first model's processing of the image, the first output data representing a portion of the image that depicts a pancreas, providing the first output data as an input to a second model, obtaining second output data generated by the second model based on the second model's processing of the second input data, the second output indicating whether the depicted pancreas is normal or abnormal, providing the first output data and the second output data as an input to a third model, and obtaining third output data generated by the third model, the third output data including data indicating that the pancreas is normal or data indicating a likely location of a pancreatic neoplasm.

Abstract: Methods, systems, apparatus, and computer programs, for processing images through multiple neural networks that are trained to detect a pancreatic ductal adenocarcinoma. In one aspect, a method includes actions of obtaining a first image that depicts a first volume of voxels, performing coarse segmentation of the first image using a first neural network trained (i) to process images having the first volume of voxels and (ii) to produce first output data, determining a region of interest of the first image based on the coarse segmentation, performing multi-stage fine segmentation on a plurality of other images that are each based on the region of interest of the first image to generate output data for each stage of the multi-stage fine segmentation, and determining based on the first output data and the output data of each stage of the multi-stage fine segmentation, whether the first image depicts a tumor.

Abstract: Systems, methods, and apparatus for segmenting internal structures depicted in an image. In one aspect, a method includes receiving data representing image data that depicts internal structures of a subject, providing an input data structure to a machine learning model, wherein the input data structure comprises fields structuring data that represents the received data representing the image data that depicts internal structures of the subject, wherein the machine learning model is a multi-stage deep convolutional network that has been trained to segment internal structures depicted by one or more images, receiving output data generated by the machine learning model based on the machine learning model's processing of the input data structure, and processing the output data to generate rendering data that, when rendered, a computer, causes the computer to output, for display, data that visually distinguishes between different internal structures depicted by the image data.

Abstract: Methods, systems, apparatus, and computer programs, for processing images through multiple neural networks that are trained to detect a pancreatic ductal adenocarcinoma. In one aspect, a method includes actions of obtaining a first image that depicts a first volume of voxels, performing coarse segmentation of the first image using a first neural network trained (i) to process images having the first volume of voxels and (ii) to produce first output data, determining a region of interest of the first image based on the coarse segmentation, performing multi-stage fine segmentation on a plurality of other images that are each based on the region of interest of the first image to generate output data for each stage of the multi-stage fine segmentation, and determining based on the first output data and the output data of each stage of the multi-stage fine segmentation, whether the first image depicts a tumor.

Abstract: Methods, systems, apparatus, and computer programs, for processing images through multiple neural networks that are trained to detect a pancreatic ductal adenocarcinoma. In one aspect, a method includes actions of obtaining a first image that depicts a first volume of voxels, performing coarse segmentation of the first image using a first neural network trained (i) to process images having the first volume of voxels and (ii) to produce first output data, determining a region of interest of the first image based on the coarse segmentation, performing multi-stage fine segmentation on a plurality of other images that are each based on the region of interest of the first image to generate output data for each stage of the multi-stage fine segmentation, and determining based on the first output data and the output data of each stage of the multi-stage fine segmentation, whether the first image depicts a tumor.

Abstract: A method and device of performing a person-to-person payment from a wireless personal communications device of an originator to a wireless communications device of a recipient is provided. The method include transferring a respective blind payment identifier, which is associated with a payment having a monetary value, from a wireless personal communications device of the originator to a wireless personal communications device of the recipient by using a direct device-to-device communications protocol. The personal communications device includes means arranged to communicate wirelessly with a remote payment system to set up a payment therewith including by obtaining and storing a blind payment identifier; and means arranged to communicate directly with a proximal, second personal communications device and impart the blind payment identifier thereto.

Abstract: A method and apparatus for performing a transaction based on a payment identifier which is embedded in or on a product. In response to an order for a product, a payment identifier is generated and associated with a monetary amount which is ring-fenced in an account. The payment identifier is embedded in or on the ordered product and the product is sent to a recipient. On receipt of the product, the recipient uses the payment identifier to obtain the monetary amount, via an Automated Teller Machine or an electronic bank transfer to their account. Ring-fenced monetary amounts in respect of the account are managed by a payment system and an associated method.

Abstract: A method and apparatus for detecting text in real-world images comprises calculating a cascade of classifiers, the cascade comprising a plurality of stages, each stage including one or more weak classifiers, the plurality of stages organized to start out with classifiers that are most useful for ruling out non-text regions, and removing regions classified as non-text regions from the cascade prior to completion of the cascade, to further speed up processing.

Abstract: A method and apparatus for detecting text in real-world images comprises calculating a cascade of classifiers, the cascade comprising a plurality of stages, each stage including one or more weak classifiers, the plurality of stages organized to start out with classifiers that are most useful for ruling out non-text regions, and removing regions classified as non-text regions from the cascade prior to completion of the cascade, to further speed up processing.

Abstract: A method and apparatus for detecting text in real-world images comprises calculating a cascade of classifiers, the cascade comprising a plurality of stages, each stage including one or more weak classifiers, the plurality of stages organized to start out with classifiers that are most useful for ruling out non-text regions, and removing regions classified as non-text regions from the cascade prior to completion of the cascade, to further speed up processing.