# US 2019/0244398 A1 · Systems and methods for follow-up functional imaging > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0244398 A1 - Document ID: US20190244398A1 - Status: Published application - Kind: A1 - Application number: 15/889,757 - Filed: 2018-02-06 - Published: 2019-08-08 - Earliest claimed: 2018-02-06 - Assignees: General Electric Company - Applicants: General Electric Company - Inventors: Raz Carmi - Web page: https://patentgrep.com/patent/US20190244398A1 ## CPC - G06T 7/0016: {involving temporal comparison} - G06T 7/0012: {Biomedical image inspection} - G06T 12/30: Image post-processing, e.g. metal artefact correction - G16H 10/60: for patient-specific data, e.g. for electronic patient records - G16H 20/00: ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance - G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS - 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: 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 ## Abstract A method is provided for follow-up functional imaging after obtaining a first functional image data set of a patient. The method includes obtaining a second functional image data set of the patient at a follow-up time subsequent to the obtaining of the first functional image data set. The method also includes generating a local change map using the first functional image data set and the second functional image data set. Further, the method includes generating a mutual structural similarity map using the first functional image data set and the second functional image data set. Also, the method includes generating a significant-response map using the local change map and the mutual structural similarity map. The method also includes displaying the significant-response map. ## Claims ### Claim 1 A method for follow-up functional imaging after obtaining a first functional image data set of a patient, the method comprising: obtaining a second functional image data set of the patient at a follow-up time subsequent to the obtaining of the first functional image data set; generating a local change map using the first functional image data set and the second functional image data set; generating a mutual structural similarity map using the first functional image data set and the second functional image data set; generating a significant-response map using the local change map and the mutual structural similarity map; and displaying the significant-response map. ### Claim 2 (depends on 1) The method of claim 1, wherein generating the local change map comprises: determining, for each voxel of the first functional image set, a first set of change metric values between a value of the voxel in the first functional image data set and values of neighboring voxels in the second functional image data set; and determining, for each voxel of the second functional image set, a second set of change metric values between a value of the voxel in the second functional image data set and values of neighboring voxels in the first functional image data set. ### Claim 3 (depends on 2) The method of claim 2, further comprising: applying an operator on the first and second sets of change metric values: and determining a signal change for each selected voxel coordinate based on the first and second sets of change metric values to which the operator has been applied. ### Claim 4 (depends on 1) The method of claim 1, further comprising determining mutual structural similarity analysis values across different spatial scales for the first functional image data set and the second functional image data set, and combining the mutual structural similarity analysis values of the different spatial scales to generate the mutual structural similarity map. ### Claim 5 (depends on 1) The method of claim 1, wherein generating the mutual structural similarity map comprises: determining a set of different spatial scales to be analyzed across an image volume; for each spatial coordinate and spatial scale combination, selecting sub-set data from the first functional imaging data set and the second functional imaging data set; performing a mutual structural similarity analysis to determine mutual structural similarity values for each particular spatial coordinate and spatial scale combination, based on the sub-set data; and weighting and combining, for each particular spatial coordinate, the mutual structural similarity analysis values for the corresponding spatial scales to generate the mutual structural similarity map. ### Claim 6 (depends on 1) The method of claim 1, wherein generating the significant-response map comprises: for each voxel, combining corresponding values from the local change map and the mutual structural similarity map; and generating the significant-response map from the combined values. ### Claim 7 (depends on 6) The method of claim 6, wherein combining the corresponding values comprises: increasing a significant-response value when a corresponding local signal change absolute value increases and a corresponding mutual structural similarity value decreases; and decreasing a significant-response value when the corresponding local signal change absolute value decreases and a corresponding mutual structural similarity value increases. ### Claim 8 (depends on 1) The method of claim 1, wherein the first functional imaging data and the second functional imaging data comprise one of single photon emission computed tomography (SPECT) imaging data or positron emission tomography (PET) imaging data. ### Claim 9 (depends on 1) The method of claim 1, further comprising: reconstructing a first image with the first functional imaging data; reconstructing a second image with the second function imaging data; and displaying the first image and the second image with the significant-response map. ### Claim 10 An imaging system comprising: an imaging detector system configured to acquire a first functional image data set of a patient, and to acquire a second functional image data set of the patient at a follow-up time subsequent to the obtaining of the first functional image data set; at least one processor configured to: generate a local change map using the first functional image data set and the second functional image data set; generate a mutual structural similarity map using the first functional image data set and the second functional image data set; generate a significant-response map using the local change map and the mutual structural similarity map; and a display unit configured to display the significant-response map. ### Claim 11 (depends on 10) The system of claim 10, wherein the at least one processor is further configured to determine mutual structural similarity analysis values across different spatial scales for the first functional image data set and the second functional image data set, and to combine the mutual structural similarity analysis values of the different spatial scales to generate the mutual structural similarity map. ### Claim 12 (depends on 10) The system of claim 10, wherein the at least one processor is configured to generate the significant-response map by: for each voxel, combining corresponding values from the local change map and the mutual structural similarity map; and generating the significant-response map from the combined values. ### Claim 13 (depends on 12) The system of claim 12, wherein combining the corresponding values comprises: increasing a significant-response value when a corresponding local signal change absolute value increases and a corresponding mutual structural similarity value decreases; and decreasing a significant-response value when the corresponding local signal change absolute value decreases and a corresponding mutual structural similarity value increases. ### Claim 14 (depends on 10) The system of claim 10, wherein the imaging detector system is configured to acquire at least one of single photon emission computed tomography (SPECT) imaging data or positron emission tomography (PET) imaging data. ### Claim 15 A non-transitory computer readable storage medium having stored thereon a computer program comprising instructions, which, when executed by a computer, cause the computer to: obtain a first functional image data set of a patient from a first time; obtain a second functional image data set of the patient at a follow-up time subsequent to the obtaining of the first functional image data set; generate a local change map using the first functional image data set and the second functional image data set; generate a mutual structural similarity map using the first functional image data set and the second functional image data set; generate a significant-response map using the local change map and the mutual structural similarity map; and display the significant-response map. ### Claim 16 (depends on 15) The non-transitory computer readable storage medium of claim 15, wherein the instructions cause the computer to generate the local change map by: determining, for each voxel of the first functional image set, a first set of change metric values between a value of the voxel in the first functional image data set and values of neighboring voxels in the second functional image data set; and determining, for each voxel of the second functional image set, a second set of change metric values between a value of the voxel in the second functional image data set and values of neighboring voxels in the first functional image data set. ### Claim 17 (depends on 15) The non-transitory computer readable storage medium of claim 15, wherein the instructions cause the computer to: apply an operator on the first and second sets of change metric values: and determine a signal change for each selected voxel coordinate based on the first and second sets of change metric values to which the operator has been applied. ### Claim 18 (depends on 15) The non-transitory computer readable storage medium of claim 15, wherein the instructions cause the computer to generate the mutual structural similarity map by: determining a set of different spatial scales to be analyzed across an image volume; for each spatial coordinate and spatial scale combination, selecting sub-set data from the first functional imaging data set and the second functional imaging data set; performing a mutual structural similarity analysis to determine mutual structural similarity values for each particular spatial coordinate and spatial scale combination, based on the sub-set data; and weighting and combining, for each particular spatial coordinate, the mutual structural similarity analysis values for the corresponding spatial scales to generate the mutual structural similarity map. ### Claim 19 (depends on 15) The non-transitory computer readable storage medium of claim 15, wherein the instructions cause the computer to generate the significant-response map by: for each voxel, combining corresponding values from the local change map and the mutual structural similarity map; and generating the significant-response map from the combined values. ### Claim 20 (depends on 19) The non-transitory computer readable storage medium of claim 19, wherein combining the corresponding values comprises: increasing a significant-response value when a corresponding local signal change absolute value increases and a corresponding mutual structural similarity value decreases; and decreasing a significant-response value when the corresponding local signal change absolute value decreases and a corresponding mutual structural similarity value increases.