# US 8,787,634 B2 · Apparatus and method for indicating likely computer-detected false positives in medical imaging data > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 8,787,634 B2 - Document ID: US8787634B2 - Status: Granted - Kind: B2 - Application number: 12/519,799 - Filed: 2007-12-14 - Published: 2010-01-07 - Granted: 2014-07-22 - Earliest claimed: 2006-12-19 - Assignees: Koninklijke Philips N.V. - Applicants: Rafael Wiemker; Roland Opfer; Thomas Buelow - Inventors: Rafael Wiemker; Roland Opfer; Thomas Buelow - Web page: https://patentgrep.com/patent/US8787634B2 ## CPC - G06T 7/0012: {Biomedical image inspection} - G06T 2207/30061: Lung - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A data structure for use by a computer system for processing medical image data and representing at least one first region of a patient includes at least one computer-detected feature of interest. The data structure includes a first computer code that is executable to detect first data representing at least one second region included within a respective first region. At least one said feature of interest in said second region has a significant likelihood of representing a computer-detected false positive. The second computer code is executable to provide second data for enabling at least one said first region to be displayed on a display device, such that at least one said second region is displayed on the display apparatus differently from part of said first region not containing features of interest having a significant likelihood of representing computer-detected false positives. ## Claims ### Claim 1 A system for processing medical image data representing at least one first region of a patient including at least one feature of interest automatically detected by a computer, the system comprising: at least one processor configured to: detect first data representing at least one second region, included within a respective said first region, wherein at least one said feature of interest in said second region has a significant likelihood of representing a false positive automatically detected by a computer, said false positives being caused by at least one of motion, streak artifacts, and photon-starvation, wherein detecting the false positive automatically by the computer includes: transforming the medical image data utilizing a slice-wise 2D transformation to generate a distance value for each voxel; determining an influence region of each voxel which has a displacement-discontinuity value which exceeds a predetermined threshold; and automatically identifying the influence region as said false positives; provide second data for enabling at least one said first region to be displayed on a display device; and causing the at least one said second region to be displayed on the display apparatus differently from the rest of said first region. ### Claim 2 (depends on 1) The system according to claim 1, wherein detecting the first data includes: detecting data representing the at least one second region on the basis of motion of said second region. ### Claim 3 (depends on 1) The system according to claim 1, wherein detecting the first data includes: detecting data representing the at least one second region on the basis of streak artifacts of said second region. ### Claim 4 (depends on 1) The system according to claim 1, wherein detecting the first data includes: detecting data representing the at least one second region on the basis of photon-starvation of said second region. ### Claim 5 (depends on 1) The system according to claim 1, wherein providing the second data causes said second regions to be depicted by a first set of graphical markers. ### Claim 6 (depends on 5) The system according to claim 5, wherein said first set of graphical markers includes different colored boundary lines of said second regions. ### Claim 7 (depends on 5) The system according to claim 5, wherein providing the second data causes at least some of said features of interest in the at least one second region to be depicted by a second set of graphical markers. ### Claim 8 (depends on 7) The system according to claim 7, wherein said second set of graphical markers includes different colored boundary lines encircling said features of interest. ### Claim 9 (depends on 1) The system according to claim 1, wherein providing the second data causes display of the at least one feature of interest in the at least one second region to be suppressed. ### Claim 10 (depends on 1) The system according to claim 1 further including: at least one imaging device configured for forming the medical image data representing the at least one first region of the patient including at least one feature of interest automatically detected by the computer; and at least one display device configured for displaying the at least one first region and the at least one second region. ### Claim 11 (depends on 1) The system according to claim 1, wherein the at least one processor is configured to detect at least one secondary region based on motion. ### Claim 12 A method of processing medical image data representing at least one first region of a patient including at least one feature of interest automatically detected by a computer, the method comprising: with a computer determining at least one second region, included within a respective said first region, in which the at least one second region computer-detected features of interest have a significant likelihood of representing a false positive automatically detected by a computer, said false positives being caused by at least one of motion, streak artifacts, and photon-starvation wherein detecting the false positive automatically by the computer includes: transforming the medical image data utilizing a slice-wise 2D transformation to generate a distance value for each voxel; determining an influence region of each voxel which has a displacement-discontinuity value which exceeds a predetermined threshold; and automatically identifying the influence region as said false positives; and displaying the at least one first region on a display device and displaying the at least one second region on the display device differently from one or more parts of said first region not containing features of interest having a significant likelihood of representing false positives automatically detected by the computer. ### Claim 13 (depends on 12) The method according to claim 12, wherein the at least one second region are determined with a streak artifact detection image-processing algorithm. ### Claim 14 (depends on 12) A computer readable non-transitory storage medium carrying software configured to control one or more processors to perform the method according to claim 12. ### Claim 15 A medical imaging system comprising: one or more processors configured to: in a region of a medical image, automatically detect features of interest by the processor; determine at least one sub-region of the region in which sub-region features of interest automatically detected by the processor have a significant likelihood of representing a false positive automatically detected by the processor, wherein detecting the false positive automatically by the computer includes: transforming the medical image data utilizing a slice-wise 2D transformation to generate a distance value for each voxel; determining an influence region of each voxel which has a displacement-discontinuity value which exceeds a predetermined threshold; and automatically identifying the influence region as said false positives; and generate graphical markers which indicate the sub-region; and a display device which displays the medical image, the graphical markers, and the features of interest automatically detected by the processor; wherein determining the sub-region includes determining with the one or more processors sub-regions which are subject to at least one of: motion; streak artifacts; and photon-starvation. ### Claim 16 (depends on 15) The medical imaging system according to claim 15, wherein the sub-region includes a lung and the feature of interest includes nodules. ### Claim 17 (depends on 15) The medical imaging system according to claim 15, wherein motion includes at least one of cardiac motion and respiratory motion. ### Claim 18 (depends on 15) The medical imaging system according to claim 15, wherein there are a plurality of sub-regions with features of interest and wherein the one or more processors is further configured to: mark the sub-regions with the significant likelihood of representing a false positive with first markers; and mark the sub-regions with no significant likelihood of representing a false positive with second markers, the second markers being different from the first markers. ### Claim 19 (depends on 15) The system according to claim 15, wherein determining the at least one sub regions includes: detecting a photon-starvation sub-region.