Ex Parte Zheng et alDownload PDFPatent Trial and Appeal BoardMar 20, 201712725679 (P.T.A.B. Mar. 20, 2017) Copy Citation United States Patent and Trademark Office UNITED STATES DEPARTMENT OF COMMERCE United States Patent and Trademark Office Address: COMMISSIONER FOR PATENTS P.O.Box 1450 Alexandria, Virginia 22313-1450 www.uspto.gov APPLICATION NO. FILING DATE FIRST NAMED INVENTOR ATTORNEY DOCKET NO. CONFIRMATION NO. 12/725,679 03/17/2010 Yefeng Zheng 2009P04861US01 9712 28524 7590 03/22/2017 SIEMENS CORPORATION INTELLECTUAL PROPERTY DEPARTMENT 3501 Quadrangle Blvd Ste 230 EXAMINER PAULSON, SHEETAL R. Orlando, EL 32817 ART UNIT PAPER NUMBER 3626 NOTIFICATION DATE DELIVERY MODE 03/22/2017 ELECTRONIC Please find below and/or attached an Office communication concerning this application or proceeding. The time period for reply, if any, is set in the attached communication. Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the following e-mail address(es): ipdadmin.us@siemens.com PTOL-90A (Rev. 04/07) UNITED STATES PATENT AND TRADEMARK OFFICE BEFORE THE PATENT TRIAL AND APPEAL BOARD Ex parte YEFENG ZHENG, BOGDAN GEORGESCU, MATTHIAS JOHN, JAN BOESE, and DORIN COMANICIU Appeal 2014-002827 Application 12/725,6791 Technology Center 3600 Before JOSEPH A. FISCHETTI, BART A. GERSTENBLITH, and BRADLEY B. BAYAT, Administrative Patent Judges. FISCHETTI, Administrative Patent Judge. DECISION ON APPEAL STATEMENT OF THE CASE Appellants seek our review under 35 U.S.C. § 134 of the Examiner’s final rejection of claims 1—29. We have jurisdiction under 35 U.S.C. § 6(b). SUMMARY OF DECISION We REVERSE. 1 Appellants identify Siemens Aktiengesellschaft as the real party in interest. (Appeal Br. 1). Appeal 2014-002827 Application 12/725,679 THE INVENTION Appellants claim a method and system for automatic aorta segmentation. (Spec. 1.). Claim 1, which is one of four independent claims before us on appeal, namely, 1, 15, 16 and 23, is reproduced below, and is illustrative of the subject matter on appeal. 1. A method for aorta segmentation in a 3D volume, comprising: detecting an aortic root in the 3D volume using marginal space learning (MSL); and tracking an ascending aorta from the detected aortic root in the 3D volume; and generating a segmented aorta including the detected aortic root and the ascending aorta. THE REJECTIONS The Examiner relies upon the following as evidence of unpatentability: Peterson US 2007/0116345 A1 May 24,2007 Schaefer US 2008/0205722 A1 Aug. 28,2008 The following rejections are before us for review. Claims 1—4, 6, 7, 10, 11, 13—16, 22, 23, and 29 are rejected under 35 U.S.C. § 102(e) as anticipated by Schaefer. Claims 5, 8, 9, 12, 17—21, and 24—28 are rejected under 35 U.S.C. § 103(a) as unpatentable over Schaefer and Peterson. 2 Appeal 2014-002827 Application 12/725,679 ANALYSIS 35 U.S.C. § 102(e) REJECTION There are four independent claims before us, namely claims 1, 15, 16, and 23. All independent claims require in one form or another, detecting an aortic root in the volume using marginal space learning (MSL) as follows: detecting an aortic root in the volume using marginal space learning (MSL); and tracking an ascending aorta from the detected aortic root in the 3D volume; and generating a segmented aorta including the detected aortic root and the ascending aorta. The Examiner found, concerning the limitation, “detecting an aortic root in the 3D volume using marginal space learning (MSL),” that this is disclosed at “Schaefer: para. 51-52; para. 75-77.” (Final Act. 2 (emphasis omitted)). The Examiner further finds, Schaefer discloses using front propagation from the seed point (i.e. root arc) to determine the end point (i.e. outer edge of the vessel) and using backtracing (directed towards voxels (i.e. space) with the largest time value decrease with respect to the current one) to create a path (i.e. to the end of aortic root), therefore detecting an aortic root using marginal space learning; this method also helps track the ascending aorta from the root. (Answer 10). Appellants argue that even if the “root arc” of Schaefer were considered to be the aortic root, which it is not, the “root arc” of Schaefer is estimated by finding the most cranial point of the longest three single vessel segments. There is no description in Schaefer that 3 Appeal 2014-002827 Application 12/725,679 the “root arc” is detected using marginal space learning. Paragraphs [0075]-[0077] describe how correspondence is estimated between extracted vessel models at different phases, and there is no description in this portion of Schaefer of detecting an aortic root using marginal space learning. In the Response to Arguments section of the Office Action, the Examiner asserts that “Schaefer teaches parameterizing vessel's arc and finding the spacing a reference phase vessel and current target vessel to detect the origin of the vessels; therefore it teaches the claimed subject matter.” (Office Action, page 9). However, parameterizing the 3D coordinates of a vessel by the vessels arc length and maintaining a predefined spacing between a reference phase vessel and a target phase vessel, as described in paragraphs [0076]-[0077] of Schaefer, are in no way related to “detecting an aortic root in a 3D volume using marginal space learning . . . .” (Appeal Br. 7). We agree with Appellants. The Examiner relies on the Specification of the present application to define MSL, finding, “MSL is a technique in which parameter estimation to localize an object is performed in a series of marginal spaces with increasing dimensionality.” (Answer 9). But, the Specification references U.S. Patent Application Publication No. 2008/0101676 A1 (“the ’676 publication”), which provides a more detailed definition of MSL than that construed by the Examiner.2 The present 2 Paragraph 21 of the Specification states: Recently, marginal space learning (MSL) has been developed to apply learning based techniques for 3D object detection. For example, a method for MSL-based heart chamber segmentation is described in detail in U.S. Patent Application Publication No. 2008/0101676, entitled “System and Method for Segmenting Chambers of a Heart in a Three Dimensional Image”, which is incorporated herein by reference. 4 Appeal 2014-002827 Application 12/725,679 Specification also incorporates the ’676 publication by reference, and hence the definition as well. The ’676 publication defines MSL in very specific terms at paragraph 26, namely, MSL incrementally learns classifiers on projected sample distributions. As the dimensionality increases, the valid or positive space region becomes more restricted by previous marginal space classifiers. The estimation is split into three problems: translation estimation, translation-orientation estimation, and full similarity estimation. It is not apparent how the Examiner’s finding in Schaefer of “propagation from the seed point (i.e. root arc) to determine the end point (i.e. outer edge of the vessel)” (Answer 10), meets the claimed MSL as defined in paragraph 26 of the ’676 publication. Particularly, the Examiner’s definition, “MSL is a technique in which parameter estimation to localize an object is performed in a series of marginal spaces with increasing dimensionality” {Id. at 9), does not specify marginal space classifiers that are required by the definition in the ’676 publication set forth above, and, thus, are not part of the Examiner’s findings. “A claim is anticipated only if each and every element as set forth in the claim is found, either expressly or inherently described, in a single prior art reference.” Verdegaal Bros. v. Union Oil Co. of California, 814 F.2d 628, 631 (Fed. Cir. 1987). Accordingly, we will not sustain the anticipation rejection of independent claims 1, 15, 16, and 23. Since claims 2-4, 6, 7, 10, 11, 13, 14, 22, and 29 depend from one of claims 1, 15, 16, and 23, and since we do not sustain the rejection of claims 1, 15, 16, and 23, the rejection of claims 2—4, 6, 7, 10, 11, 13, 14, 22, and 29 likewise is not sustained. 5 Appeal 2014-002827 Application 12/725,679 35 U.S.C. § 103(a) REJECTION We also reverse the rejection of dependent claims 5, 8, 9, 12, 17—21, and 24—28 under 35 U.S.C. § 103(a) because the rejection made under this section does not remedy the shortfalls discussed above in the anticipation rejection. CONCLUSIONS OF LAW We conclude the Examiner erred in rejecting claims 1—4, 6, 7, 10, 11, 13-16, 22, 23, and 29 under 35 U.S.C. § 102(e). We conclude the Examiner erred in rejecting claims 5, 8, 9, 12, 17— 21, and 2A-28 under 35 U.S.C. § 103(a). DECISION The decision of the Examiner to reject claims 1—29 is reversed. REVERSED 6 Copy with citationCopy as parenthetical citation