# US 10,769,498 B2 · Image data pre-processing > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,769,498 B2 - Document ID: US10769498B2 - Status: Granted - Kind: B2 - Application number: 16/070,537 - Filed: 2017-01-25 - Published: 2019-02-28 - Granted: 2020-09-08 - Earliest claimed: 2016-01-25 - Assignees: Koninklijke Philips N.V. - Applicants: Koninklijke Philips N.V. - Inventors: Eran Rubens; Bella Fadida-Specktor; Eliahu Zino; Menachem Melamed; Eran Meir; Netanel Weinberg; Maria Kaplinsky Nus - Web page: https://patentgrep.com/patent/US10769498B2 ## CPC - G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS - G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques} - G06T 5/60: using machine learning, e.g. neural networks - G06T 11/26: Drawing of charts or graphs - G06T 2207/20081: Training; Learning - G06T 2207/30004: Biomedical image processing - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A computer-implemented method (40) reduces processing time of an application for visualizing image data, which application is one of a plurality of applications selectable by a user. Each of the plurality of applications includes a pre-processing algorithm for pre-processing the image data. The method predicts which one of the pre-processing algorithms is to be performed in response to a selection of an application by the user by: —extracting a feature vector from the image data, metadata, and/or additional data associated with the image data, —supplying the feature vector as input to a machine learned model, and —receiving an algorithm identifier as output from the machine learned model. The algorithm identifier identifies the pre-processing algorithm. Additionally, the algorithm identifier is used to select (42) the pre-processing algorithm. The image data is pre-processed (43) using the selected pre-processing algorithm. ## Claims ### Claim 1 A computer-implemented method of reducing processing time of an application for visualizing image data, wherein the application is one of a plurality of applications selectable by a user, wherein each of the plurality of applications comprises a pre-processing algorithm of a plurality of pre-processing algorithms for pre-processing the image data before image processing the selected application has started, wherein the method comprises predicting which one of the plurality of pre-processing algorithms is to be performed in response to a selection of one of the applications by the user by: extracting a feature vector from the image data, metadata, and/or additional data associated with the image data, supplying the feature vector as input to a machine learned model, receiving an algorithm identifier as output from the machine learned model, the algorithm identifier identifying the pre-processing algorithm, using the algorithm identifier to select the pre-processing algorithm, thereby obtaining a selected pre-processing algorithm, and pre-processing the image data using the selected pre-processing algorithm. ### Claim 2 (depends on 1) The method according to claim 1, wherein the image data is Digital Imaging and Communications in Medicine (DICOM) image data, wherein the metadata is a DICOM header of the DICOM image data, and wherein the extracting the feature vector comprises extracting DICOM text tags from the DICOM header. ### Claim 3 (depends on 2) The method according to claim 2, wherein the DICOM text tags are free-text DICOM tags, and wherein the extracting the feature vector comprises processing the free-text DICOM tags to obtain a set of processed DICOM text tags. ### Claim 4 (depends on 3) The method according to claim 3, wherein the extracting the feature vector comprises using a random forest machine learning technique to generate the feature vector from the set of processed DICOM text tags. ### Claim 5 (depends on 1) The method according to claim 1, wherein the machine learned model is produced by a machine learning system. ### Claim 6 (depends on 5) The method according to claim 5, wherein the machine learning system comprises a machine learning engine configured for building a machine learned model by using a feature vector as input vector and receiving at least one algorithm identifier as output vector, wherein the feature vector is extracted from the image data, metadata, and/or additional data associated with the image data. ### Claim 7 (depends on 6) The method according to claim 6, wherein the feature vector is extracted from the image data, metadata and/or additional data associated with the image data from a single picture archiving and communication system. ### Claim 8 (depends on 1) The method according to claim 1, wherein a processing algorithm is configured for leaving the image data unaltered. ### Claim 9 (depends on 1) A computer readable medium comprising transitory or non-transitory data representing instructions arranged to cause a processor to carry out the method according to claim 1. ### Claim 10 (depends on 1) The method according to claim 1 wherein the selected pre-processing algorithm generates at least one of measurements and 3D views of body parts from the image data. ### Claim 11 (depends on 1) The method according to claim 1 wherein the image data includes medical image data generated by a medical scanner selected from the group consisting of a computer tomography (CT) scanner, a magnetic resonance (MR) scanner, and an x-ray scanner. ### Claim 12 (depends on 1) A device configured for reducing processing time of an application for visualizing image data, wherein the application is one of a plurality of applications selectable by a user, wherein each of the plurality of applications comprises at least one of a plurality of pre-processing algorithms for pre-processing the image data before the actual image processing is started, the device comprising one or more processors configured to perform the method according to claim 1. ### Claim 13 A device configured for reducing processing time of an application for visualizing image data, wherein the application is one of a plurality of applications selectable by a user, wherein each of the plurality of applications comprises at least one of a plurality of pre-processing algorithms for pre-processing the image data before actual processing of the image data is started, the device comprising: an input interface configured to access the image data, metadata, and/or additional data associated with the image data; a memory comprising application data representing the plurality of applications and instruction data representing a set of instructions; and a processor configured to communicate with the input interface and the memory and to execute the set of instructions, wherein the set of instructions, when executed by the processor, causes the processor to predict, in response to a selection of an application by the user, which one of the plurality of pre-processing algorithms is to be performed by: extracting a feature vector from the image data, metadata, and/or additional data associated with the image data, supplying the feature vector as input to a machine learned model, wherein the machine learned model is stored as model data in the memory, receiving an algorithm identifier as an output from the machine learned model, the algorithm identifier identifying at least one of the pre-processing algorithms, the set of instructions, when executed by the processor, further causing the processor to: use the algorithm identifier to select one or more of the pre-processing algorithms, thereby obtaining a selected one or more of the pre-processing algorithms, and pre-process the image data using the selected one or more of the pre-processing algorithms. ### Claim 14 (depends on 13) The device according to claim 13 being a workstation or imaging apparatus. ### Claim 15 (depends on 13) The device according to claim 13, wherein the selected one or more or more of the pre-processing algorithms generates at least one of measurements and 3D views of body parts from the image data. ### Claim 16 (depends on 13) The device according to claim 13, wherein the image data is generated by a CT scanner, an MR scanner, and an x-ray scanner. ### Claim 17 A device configured for reducing processing time of a processing application for visualizing medical diagnostic image data, wherein the application is one of a plurality of pre-processing applications selectable by a user, wherein each of the plurality of applications includes one or more pre-processing algorithms for pre-processing the medical diagnostic image data, the device including one or more processors configured to: receive from an input interface the medical diagnostic image data, metadata, and/or additional data associated with the medical image data and one or more user selected applications; predict which one or more of the pre-processing algorithms is to be performed in response to the one or more user-selected applications by: extracting a feature vector from the medical diagnostic image data, the metadata, and/or the additional data associated with the medical diagnostic image data, supplying the feature vector as an input to a machine learned model, and receiving one or more algorithm identifiers as an output from the machine learned model identifying one or more of the pre-processing algorithms; use the one or more algorithm identifiers to select the one or more pre-processing algorithms; and pre-process the medical diagnostic image data using the one or more selected pre-processing algorithms. ### Claim 18 (depends on 17) The apparatus according to claim 17 wherein the one or more applications generates at least one of measurements and 3D views of a body part from the medical diagnostic image data.