# US 2019/0172576 A1 · Automated cloud image processing and routing > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0172576 A1 - Document ID: US20190172576A1 - Status: Published application - Kind: A1 - Application number: 16/266,745 - Filed: 2019-02-04 - Published: 2019-06-06 - Earliest claimed: 2015-09-30 - Assignees: General Electric Company - Applicants: General Electric Company - Inventors: Jerome Francois Knoplioch; Antoine Aliotti - Web page: https://patentgrep.com/patent/US20190172576A1 ## CPC - G16H 30/40: for processing medical images, e.g. editing - G06V 10/40: Extraction of image or video features - G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS - G16H 40/67: for remote operation - H04L 67/1097: for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS] - G06V 2201/03: Recognition of patterns in medical or anatomical images - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract Example systems, methods and computer program products for cloud-based, anatomy-specific identification, processing and routing of image data in a cloud infrastructure are disclosed. An example method includes evaluating, automatically by a particularly programmed processor in a cloud infrastructure, image data to identify an anatomy in the image data. The example method includes processing, automatically by the processor, the image data based on a processing algorithm determined by the processor based on the anatomy identified in the image data. The example method also includes routing, automatically by the processor, the image data to a data consumer based on a routing strategy determined by the processor based on the anatomy identified in the image data. The example method includes generating, automatically by the processor based on the processing and routing, at least one of a push of the image data and a notification of availability of the image data. ## Claims ### Claim 1 A method comprising: evaluating, automatically using at least a first processor, image data to identify one or more anatomy in the image data by building a feature vector from at least one of image features or tags identified in the image data to compute a probable anatomy identification in comparison to at least one of training examples or rules; building, using the at least the first processor, a set of routes to process the image data, each route including one or more nodes, wherein the set of routes includes at least one processing node and at least one storage node, the at least one processing node to include a selected anatomy processor from a plurality of anatomy processors, each of the plurality of anatomy processors configured to process the image data based on a different anatomy, the selected anatomy processor configured to process the image data based on a selected one of the one or more anatomy; routing, using the at least the first processor, the image data according to the set of routes to process the image data using at least the selected anatomy processor to generate processed image data; and generating, automatically by the first anatomy processor, at least one of a) a push of the processed image data to a data consumer or b) a notification of availability of the processed image data in at least one storage node. ### Claim 2 (depends on 1) The method of claim 1, wherein the at least the first processor is part of a cloud infrastructure. ### Claim 3 (depends on 1) The method of claim 1, wherein at least one storage node is associated with an exam record for the image data. ### Claim 4 (depends on 1) The method of claim 1, wherein the image data is evaluated for routing and processing as the image data is streamed to the at least one first processor. ### Claim 5 (depends on 1) The method of claim 1, wherein the routing is facilitated using at least one anatomy router corresponding to the one or more anatomy identified in the image data. ### Claim 6 (depends on 1) The method of claim 1, wherein the set of routes includes a plurality of routes defined by a plurality of processing nodes and a plurality of storage nodes. ### Claim 7 (depends on 1) The method of claim 1, further including processing, at each processing node, the image data according an anatomy-specific processing algorithm instantiated by the anatomy processor associated with the respective processing node. ### Claim 8 At least one computer-readable storage medium including instructions that, when executed, cause at least one first processor to at least: evaluate image data to identify one or more anatomy in the image data by building a feature vector from at least one of image features or tags identified in the image data to compute a probable anatomy identification in comparison to at least one of training examples or rules; build a set of routes to process the image data, each route including one or more nodes, wherein the set of routes includes at least one processing node and at least one storage node, the at least one processing node to include a selected anatomy processor from a plurality of anatomy processors, each of the plurality of anatomy processors configured to process the image data based on a different anatomy, the selected anatomy processor configured to process the image data based on a selected one of the one or more anatomy; route the image data according to the set of routes to process the image data using at least the selected anatomy processor to generate processed image data; and generate at least one of a) a push of the processed image data to a data consumer or b) a notification of availability of the processed image data in at least one storage node. ### Claim 9 (depends on 8) The at least one computer-readable storage medium of claim 8, wherein the at least one first processor is part of a cloud infrastructure. ### Claim 10 (depends on 8) The at least one computer-readable storage medium of claim 8, wherein at least one storage node is associated with an exam record for the image data. ### Claim 11 (depends on 8) The at least one computer-readable storage medium of claim 8, wherein the image data is evaluated for routing and processing as the image data is streamed to the at least one first processor. ### Claim 12 (depends on 8) The at least one computer-readable storage medium of claim 8, wherein the routing is facilitated using at least one anatomy router corresponding to the one or more anatomy identified in the image data. ### Claim 13 (depends on 8) The at least one computer-readable storage medium of claim 8, wherein the set of routes includes a plurality of routes defined by a plurality of processing nodes and a plurality of storage nodes. ### Claim 14 (depends on 8) The at least one computer-readable storage medium of claim 8, wherein, at each processing node, the image data is processed according an anatomy-specific processing algorithm instantiated by the anatomy processor associated with the respective processing node. ### Claim 15 An apparatus comprising: at least one computer-readable storage medium including instructions; and at least one first processor to at least: evaluate, by executing an instruction, image data to identify one or more anatomy in the image data by building a feature vector from at least one of image features or tags identified in the image data to compute a probable anatomy identification in comparison to at least one of training examples or rules; build, by executing an instruction, a set of routes to process the image data, each route including one or more nodes, wherein the set of routes includes at least one processing node and at least one storage node, the at least one processing node to include a selected anatomy processor from a plurality of anatomy processors, each of the plurality of anatomy processors configured to process the image data based on a different anatomy, the selected anatomy processor configured to process the image data based on a selected one of the one or more anatomy; route, by executing an instruction, the image data according to the set of routes to process the image data using at least the selected anatomy processor to generate processed image data; and generate, by executing an instruction, at least one of a) a push of the processed image data to a data consumer or b) a notification of availability of the processed image data in at least one storage node. ### Claim 16 (depends on 15) The apparatus of claim 15, wherein the at least one first processor is part of a cloud infrastructure. ### Claim 17 (depends on 15) The apparatus of claim 15, wherein at least one storage node is associated with an exam record for the image data. ### Claim 18 (depends on 15) The apparatus of claim 15, wherein the image data is evaluated for routing and processing as the image data is streamed to the at least one first processor. ### Claim 19 (depends on 15) The apparatus of claim 15, further including at least one anatomy router corresponding to the one or more anatomy identified in the image data to route the image data. ### Claim 20 (depends on 15) The apparatus of claim 15, wherein the set of routes includes a plurality of routes defined by a plurality of processing nodes and a plurality of storage nodes.