# US 10,478,134 B2 · Systems and methods for improved diagnostics for nuclear medicine imaging > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,478,134 B2 - Document ID: US10478134B2 - Status: Granted - Kind: B2 - Application number: 15/715,666 - Filed: 2017-09-26 - Published: 2019-03-28 - Granted: 2019-11-19 - Earliest claimed: 2017-09-26 - Assignees: General Electric Company - Applicants: General Electric Company - Inventors: Raz Carmi; Jonathan Sachs - Web page: https://patentgrep.com/patent/US10478134B2 ## CPC - A61B 6/037: {Emission tomography} - A61B 6/06: Diaphragms - A61B 6/5217: {extracting a diagnostic or physiological parameter from medical diagnostic data} - G01T 1/161: Applications in the field of nuclear medicine, e.g. in vivo counting {(apparatus for radiation diagnosis A61B6/00)} - G06T 7/0012: {Biomedical image inspection} - G06T 7/11: Region-based segmentation - G16H 30/40: for processing medical images, e.g. editing - G16H 50/30: for calculating health indices; for individual health risk assessment - A61B 6/4266: {characterised by using a plurality of detector units (A61B6/4014 takes precedence)} - G06T 2207/10081: Computed x-ray tomography [CT] - G06T 2207/10104: Positron emission tomography [PET] - G06T 2207/10108: Single photon emission computed tomography [SPECT] - G06T 2207/30004: Biomedical image processing - G06V 10/26: Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion - G06V 2201/03: Recognition of patterns in medical or anatomical images - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G01T: MEASUREMENT OF NUCLEAR OR X-RADIATION (radiation analysis of materials, mass spectrometry G01N23/00; tubes for determining the presence, intensity, density or energy of radiation or particles H01J47/00) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - 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 ## Abstract Systems and methods described herein generally relate to improved medical diagnostics for nuclear medicine (NM) imaging. The systems and methods define an uncertainty model of a medical imaging system. The uncertainty model is based on natural-statistics distribution of the medical imaging system response. The systems and methods acquire image data of a patient from the medical imaging system, and calculate an uncertainty map of the patient based on the uncertainty model and the image data. The uncertainty map represents a collection of realizations that are generated based on the image data and the uncertainty model. The systems and methods apply a classification or ranking algorithm to the image data and the uncertainty map to calculate image data classification or ranking of the patient including confidence values. ## Claims ### Claim 1 A method comprising: defining an uncertainty model of a medical imaging system, wherein the uncertainty model is based on a natural-statistics distribution of the medical imaging system; acquiring image data of a patient from the medical imaging system; calculating an uncertainty map of the patient based on the uncertainty model and the image data, wherein the uncertainty map represents a collection of realizations that are generated based on the image data and the uncertainty model; and applying a classification or ranking algorithm to the image data and the uncertainty map to calculate image data classification or ranking of the patient including confidence values, wherein the realizations are based on simulations of selections from the uncertainty model, the simulations automatically randomize parameters of the medical imaging system to select different image voxel values. ### Claim 2 (depends on 1) The method of claim 1, wherein the classification or ranking represents a severity ranking of the image data. ### Claim 3 (depends on 1) The method of claim 1, further comprising determining a length of a scan of the patient based on a temporary image volume. ### Claim 4 (depends on 1) The method of claim 1, further comprising adjusting parameters of the medical imaging system based on the uncertainty map, wherein the parameters adjust the uncertainty model of the medical imaging system. ### Claim 5 (depends on 1) The method of claim 1, further comprising receiving a pathological state of the patient, and adjusting at least one of the confidence values based on the pathological state. ### Claim 6 (depends on 1) The method of claim 1, further comprising receiving a plurality of uncertainty maps for multiple patients, and adjusting the classification or ranking algorithm based on the plurality of uncertainty maps, wherein the classification or ranking algorithm is adjusted to identify features of the plurality of uncertainty maps representing a medical condition relating to one or more diagnoses. ### Claim 7 A method comprising: defining an uncertainty model of a medical imaging system, wherein the uncertainty model is based on a natural-statistics distribution of the medical imaging system; acquiring image data of a patient from the medical imaging system; calculating an uncertainty map of the patient based on the uncertainty model and the image data, wherein the uncertainty map represents a collection of realizations that are generated based on the image data and the uncertainty model; applying a classification or ranking algorithm to the image data and the uncertainty map to calculate image data classification or ranking of the patient including confidence values; and calculating an uncertainty metric based on the realizations, wherein a range of the uncertainty metric is used in the calculating operation of the confidence values. ### Claim 8 A method comprising: defining an uncertainty model of a medical imaging system, wherein the uncertainty model is based on a natural-statistics distribution of the medical imaging system; acquiring image data of a patient from the medical imaging system; calculating an uncertainty map of the patient based on the uncertainty model and the image data, wherein the uncertainty map represents a collection of realizations that are generated based on the image data and the uncertainty model; applying a classification or ranking algorithm to the image data and the uncertainty map to calculate image data classification or ranking of the patient including confidence values; and overlaying the confidence values on an image volume based on the image data, wherein the confidence values are based on at least one of the realizations. ### Claim 9 A medical imaging system, comprising: a plurality of detector units disposed about a gantry configured to acquire image data of a patient; a memory that includes a classification or ranking algorithm; and at least one processor operably coupled to the detector units, the at least one processor configured to: define an uncertainty model of a medical imaging system, wherein the uncertainty model is based on a natural-statistics distribution of the medical imaging system; acquire image data of a patient from the medical imaging system; calculate an uncertainty map of the patient based on the uncertainty model and the image data, wherein the uncertainty map represents a collection of realizations that are generated based on the image data and the uncertainty model; and apply the classification or ranking algorithm to the image data and the uncertainty map to calculate image data classification or ranking of the patient including confidence values, wherein the realizations are based on simulations of selections from the uncertainty model, the simulations automatically randomize parameters of the medical imaging system to select different image voxel values. ### Claim 10 (depends on 9) The medical imaging system of claim 9, wherein the classification or ranking represents a severity ranking of the image data. ### Claim 11 (depends on 9) The medical imaging system of claim 9, wherein the at least one processor is configured to determine a length of a scan of the patient based on a temporary image volume. ### Claim 12 (depends on 9) The medical imaging system of claim 9, wherein the at least one processor is configured to adjust parameters of the medical imaging system based on the uncertainty map, wherein the parameters adjust the uncertainty model of the medical imaging system. ### Claim 13 (depends on 9) The medical imaging system of claim 9, wherein the at least one processor is configured to receive a pathological state of the patient and adjust at least one of the confidence values based on the pathological state. ### Claim 14 (depends on 9) The medical imaging system of claim 9, wherein the at least one processor is configured to receive a plurality of uncertainty maps for multiple patients and adjust the classification or ranking algorithm based on the plurality of uncertainty maps, wherein the classification or ranking algorithm is adjusted to identify features of the plurality of uncertainty maps representing a medical condition relating to one or more diagnoses. ### Claim 15 A medical imaging system, comprising: a plurality of detector units disposed about a gantry configured to acquire image data of a patient; a memory that includes a classification or ranking algorithm; and at least one processor operably coupled to the detector units, the at least one processor configured to: define an uncertainty model of a medical imaging system, wherein the uncertainty model is based on a natural-statistics distribution of the medical imaging system; acquire image data of a patient from the medical imaging system; calculate an uncertainty map of the patient based on the uncertainty model and the image data, wherein the uncertainty map represents a collection of realizations that are generated based on the image data and the uncertainty model; calculate an uncertainty metric based on the realizations; and and apply the classification or ranking algorithm to the image data and the uncertainty map to calculate image data classification or ranking of the patient including confidence values, wherein a range of the uncertainty metric is used to calculate the confidence values. ### Claim 16 A medical imaging system, comprising: a plurality of detector units disposed about a gantry configured to acquire image data of a patient; a memory that includes a classification or ranking algorithm; and at least one processor operably coupled to the detector units, the at least one processor configured to: define an uncertainty model of a medical imaging system, wherein the uncertainty model is based on a natural-statistics distribution of the medical imaging system; acquire image data of a patient from the medical imaging system; calculate an uncertainty map of the patient based on the uncertainty model and the image data, wherein the uncertainty map represents a collection of realizations that are generated based on the image data and the uncertainty model; apply the classification or ranking algorithm to the image data and the uncertainty map to calculate image data classification or ranking of the patient including confidence values; and overlay the confidence values on an image volume based on the image data, wherein the confidence values are based on at least one of the realizations. ### Claim 17 A tangible and non-transitory computer readable medium comprising one or more programmed instructions configured to direct one or more processors to: define an uncertainty model of a medical imaging system, wherein the uncertainty model is based on a natural-statistics distribution of the medical imaging system; acquire image data of a patient from the medical imaging system; calculate an uncertainty map of the patient based on the uncertainty model and the image data, wherein the uncertainty map represents a collection of realizations that are generated based on the image data and the uncertainty model; and applying a classification or ranking algorithm to the image data and the uncertainty map to calculate image data classification or ranking of the patient including confidence values, wherein the realizations are based on simulations from the uncertainty model, the simulations automatically randomize parameters of the medical imaging system to select different image voxel values.