Patents by Inventor Leiguang Gong
Leiguang Gong has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 8761475Abstract: A system and method for recognizing and labeling anatomical structures in an image includes creating a list of objects such that one or more objects on the list appear before a target object and setting the image as a context for a first object on the list. The first object is detected and labeled by subtracting a background of the image. A local context is set for a next object on the list using the first object. The next object is detected and labeled by registration using the local context. Setting a local context and detecting and labeling the next object are repeated until the target object is detected and labeled. Labeling of the target object is refined using region growing.Type: GrantFiled: July 18, 2012Date of Patent: June 24, 2014Assignee: International Business Machines CorporationInventors: Leiguang Gong, Jonathan B. Rohrer, Giridharan R. Iyengar
-
Patent number: 8385688Abstract: A system and method for recognizing and labeling anatomical structures in an image includes creating a list of objects such that one or more objects on the list appear before a target object and setting the image as a context for a first object on the list. The first object is detected and labeled by subtracting a background of the image. A local context is set for a next object on the list using the first object. The next object is detected and labeled by registration using the local context. Setting a local context and detecting and labeling the next object are repeated until the target object is detected and labeled. Labeling of the target object is refined using region growing.Type: GrantFiled: August 27, 2008Date of Patent: February 26, 2013Assignee: International Business Machines CorporationInventors: Leiguang Gong, Jonathan B. Rohrer, Giridharan R. Iyengar
-
Publication number: 20120281904Abstract: A system and method for recognizing and labeling anatomical structures in an image includes creating a list of objects such that one or more objects on the list appear before a target object and setting the image as a context for a first object on the list. The first object is detected and labeled by subtracting a background of the image. A local context is set for a next object on the list using the first object. The next object is detected and labeled by registration using the local context. Setting a local context and detecting and labeling the next object are repeated until the target object is detected and labeled. Labeling of the target object is refined using region growing.Type: ApplicationFiled: July 18, 2012Publication date: November 8, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: LEIGUANG GONG, JONATHAN B. ROHRER, GIRIDHARAN R. IYENGAR
-
Patent number: 8244008Abstract: A method for optimizing images, the method comprising, receiving a designation of a first feature of interest, receiving a designation of a second feature of interest, receiving a target image, receiving an atlas image including labels of first and second features of interest of the target image and a first optimization parameter associated with the first feature of interest and a second optimization parameter associated with the second feature of interest, mapping the atlas image onto the target image resulting in a global mapped image, defining an area of the first feature of interest and an area of the second feature of interest, mapping the reference image onto the area of the first feature of interest on the global mapped image using the first optimization parameter, and mapping the reference image onto the area of the second feature of interest on the global mapped image using the second optimization parameter.Type: GrantFiled: July 21, 2008Date of Patent: August 14, 2012Assignee: International Business Machines CorporationInventors: Jonathan B. Rohrer, Giridharan R. Iyengar, Leiguang Gong
-
Patent number: 7844562Abstract: A system and method for reasoning about concepts, relations and rules having a semantic network comprising at least one node from a predetermined set of node types, at least one link from a predetermined set of link types, and zero or more rules from a predetermined set of rule types, a subset of the rule types being matching rule types, each node and each link being associated with a set of zero or more rules; a network reasoning data structure having a reasoning type database having at least one regular expression, each of the regular expressions being a class of sequences having at least three node types and two link types, wherein the network reasoning data structure further has a context being a set of rules; and a reasoning engine having an activator for activating one or more activated paths in the semantic network, the set of activated paths having a common starting node in the semantic network, wherein the reasoning engine further has a validator for selecting a subset of the activated paths being vaType: GrantFiled: October 30, 2008Date of Patent: November 30, 2010Assignee: International Business Machines CorporationInventors: Leiguang Gong, Leora Morgenstern, Erik T. Mueller, Doug Riecken, Moninder Singh
-
Publication number: 20100054525Abstract: A system and method for recognizing and labeling anatomical structures in an image includes creating a list of objects such that one or more objects on the list appear before a target object and setting the image as a context for a first object on the list. The first object is detected and labeled by subtracting a background of the image. A local context is set for a next object on the list using the first object. The next object is detected and labeled by registration using the local context. Setting a local context and detecting and labeling the next object are repeated until the target object is detected and labeled. Labeling of the target object is refined using region growing.Type: ApplicationFiled: August 27, 2008Publication date: March 4, 2010Inventors: Leiguang Gong, Jonathan B. Rohrer, Giridharan R. Iyengar
-
Publication number: 20100014722Abstract: A method for optimizing images, the method comprising, receiving a designation of a first feature of interest, receiving a designation of a second feature of interest, receiving a target image, receiving an atlas image including labels of first and second features of interest of the target image and a first optimization parameter associated with the first feature of interest and a second optimization parameter associated with the second feature of interest, mapping the atlas image onto the target image resulting in a global mapped image, defining an area of the first feature of interest and an area of the second feature of interest, mapping the reference image onto the area of the first feature of interest on the global mapped image using the first optimization parameter, and mapping the reference image onto the area of the second feature of interest on the global mapped image using the second optimization parameter.Type: ApplicationFiled: July 21, 2008Publication date: January 21, 2010Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Jonathan B. Rohrer, Giridharan R. Iyengar, Leiguang Gong
-
Publication number: 20090055342Abstract: A system and method for reasoning about concepts, relations and rules having a semantic network comprising at least one node from a predetermined set of node types, at least one link from a predetermined set of link types, and zero or more rules from a predetermined set of rule types, a subset of the rule types being matching rule types, each node and each link being associated with a set of zero or more rules; a network reasoning data structure having a reasoning type database having at least one regular expression, each of the regular expressions being a class of sequences having at least three node types and two link types, wherein the network reasoning data structure further has a context being a set of rules; and a reasoning engine having an activator for activating one or more activated paths in the semantic network, the set of activated paths having a common starting node in the semantic network, wherein the reasoning engine further has a validator for selecting a subset of the activated paths being vaType: ApplicationFiled: October 30, 2008Publication date: February 26, 2009Inventors: Leiguang GONG, Leora MORGENSTERN, Erik T. MUELLER, Doug RIECKEN, Moninder SINGH
-
Patent number: 7447667Abstract: A system and method for reasoning about concepts, relations and rules having a semantic network comprising at least one node from a predetermined set of node types, at least one link from a predetermined set of link types, and zero or more rules from a predetermined set of rule types, a subset of the rule types being matching rule types, each node and each link being associated with a set of zero or more rules; a network reasoning data structure having a reasoning type database having at least one regular expression, each of the regular expressions being a class of sequences having at least three node types and two link types, wherein the network reasoning data structure further has a context being a set of rules; and a reasoning engine having an activator for activating one or more activated paths in the semantic network, the set of activated paths having a common starting node in the semantic network, wherein the reasoning engine further has a validator for selecting a subset of the activated paths being vaType: GrantFiled: December 11, 2002Date of Patent: November 4, 2008Assignee: International Business Machines CorporationInventors: Leiguang Gong, Leora Morgenstern, Erik T. Mueller, Doug Riecken, Moninder Singh
-
Publication number: 20040117395Abstract: A system and method for reasoning about concepts, relations and rules having a semantic network comprising at least one node from a predetermined set of node types, at least one link from a predetermined set of link types, and zero or more rules from a predetermined set of rule types, a subset of the rule types being matching rule types, each node and each link being associated with a set of zero or more rules; a network reasoning data structure having a reasoning type database having at least one regular expression, each of the regular expressions being a class of sequences having at least three node types and two link types, wherein the network reasoning data structure further has a context being a set of rules; and a reasoning engine having an activator for activating one or more activated paths in the semantic network, the set of activated paths having a common starting node in the semantic network, wherein the reasoning engine further has a validator for selecting a subset of the activated paths being vaType: ApplicationFiled: December 11, 2002Publication date: June 17, 2004Applicant: International Business Machines CorporationInventors: Leiguang Gong, Leora Morgenstern, Erik T. Mueller, Doug Riecken, Moninder Singh