Ex Parte Zhang et alDownload PDFPatent Trial and Appeal BoardOct 23, 201411856109 (P.T.A.B. Oct. 23, 2014) Copy Citation UNITED STATES PATENT AND TRADEMARK OFFICE ____________ BEFORE THE PATENT TRIAL AND APPEAL BOARD ____________ Ex parte WEI ZHANG, ADRIAN BARBU, YEFENG ZHENG, and DORIN COMANICIU ____________ Appeal 2012-004501 Application 11/856,109 Technology Center 2100 ____________ Before JEFFREY S. SMITH, JOHNNY A. KUMAR, and CATHERINE SHIANG, Administrative Patent Judges. KUMAR, Administrative Patent Judge. DECISION ON APPEAL Appeal 2012-004501 Application 11/856,109 2 STATEMENT OF THE CASE This is an appeal under 35 U.S.C. § 134(a) from the Examiner’s final rejection of claims 10–14 and 24–28. We have jurisdiction under 35 U.S.C. § 6(b). We affirm. Representative Claim 10. A method for detecting objects in CT volume data using a probabilistic boosting cascade tree (PBCT), comprising: receiving an input CT volume; processing said input CT volume using a PBCT having a plurality of nodes to detect one or more objects in said input CT volume, wherein said PBCT comprises at least one tree node and at least one cascade node, wherein each of said at least one tree node and said at least one cascade node classifies voxels of the input CT volume as positive or negative, wherein said at least one cascade node has a single child node for further classifying voxels classified as positive by said at least one cascade node, wherein voxels classified as negative by said at least one cascade node are discarded, and wherein said at least one tree node has a first child node for further classifying voxels classified as positive by said at least one tree node and a second child node for further classifying voxels classified as negative by said at least one tree node. Examiner’s Rejections The Examiner rejected claims 10–14 and 24–28 under 35 U.S.C. §§ 102(a) and 102(e) as being anticipated by Tu (US 2006/0079761 A1, Apr. 13, 2006). Ans. 5–8. Appeal 2012-004501 Application 11/856,109 3 ANALYSIS We adopt as our own the findings and reasons set forth in the Examiner’s Answer (see Ans. 5–18). We highlight and address specific findings and arguments for emphasis as follows. Appellants contend that Tu does not describe “wherein voxels classified as negative by said at least one cascade node are discarded,” as recited in claim 10, and similarly recited in independent claim 24. App. Br. 6–9; Reply Br. 1–9. In particular, Appellants contend in Tu “the first node of the fourth row does not discard voxels classified as negative by that node, but instead sends such voxels to the child node which further processes such voxels to calculate probabilities for such voxels.” Reply Br. 4. Appellants further contend, “In the PBTs of FIGS. 8 and 10 of Tu, the classification of a voxel as negative by one node does not mean that the voxel is classified as negative overall.” Id. at 5–6 (emphasis omitted). Appellants’ arguments are not commensurate in scope with the broad claim language, because claim 10 recites “at least one cascade node are discarded,” rather than reciting “all nodes” or “each node” to be discarded. The Examiner finds: Figure 8 shows a cascade node in the fourth row, with the first node ending processing with a negative (the negative leaf node with no children meaning that no further processing/actions are taken with this node) and the node on the right (positive, with further processing for the node (two children). This clearly denotes one node which has further processing (fifth row, second node) and another node with no further processing (first node, fifth row). Therefore, the first node in the fourth row is clearly a cascade node, as its negative child is “discarded” in the sense that no further decisions are made about it, and the positive child is passed on for further decisions, (i.e. further classifying). Therefore the tree clearly and distinctly has a Appeal 2012-004501 Application 11/856,109 4 cascade node. Figure 10 shows a very similar situation. In Figure 10, the cascade node is found in the third node on the right. This node has a negative child which receives no further processing (there are no further decisions made in the tree based upon that node). The branch to the right, which is positive, is passed to another node which does have further decisions and is further processed with a positive and negative child. Clearly, both trees denote a cascade node, which is a node that, as defined by the appellant, has a single child node for further classifying for positive, and those classified as negative are “discarded.” Ans. 11–12 (emphasis omitted). Thus, the Examiner provides a well-reasoned explanation, which demonstrates that Tu discloses the “wherein voxels classified as negative by said at least one cascade node are discarded” limitation (Id.). We concur with the Examiner’s fact finding as it is supported by Tu’s disclosure. Accordingly, we sustain the rejection of claims 10 and 24 under 35 U.S.C. § 102. Appellants do not present arguments for separate patentability of claims 12–14 and 26–28, which fall with claims 10 and 24, respectively. App. Br. 9–10. Regarding dependent claims 11 and 25, while Appellants raised additional arguments for patentability of the cited dependent claims (App. Br. 10–11), we find that the Examiner has rebutted in the Answer each and every one of those arguments supported by sufficient evidence. Ans. 7, 9– 17. Therefore, we adopt the Examiner’s findings and underlying reasoning, which are incorporated herein by reference. Appeal 2012-004501 Application 11/856,109 5 DECISION The Examiner did not err in rejecting claims 10–14 and 24–28 under 35 U.S.C. §§ 102(a) and 102(e) as being anticipated by Tu. No time period for taking any subsequent action in connection with this appeal may be extended under 37 C.F.R. § 1.136(a). See 37 C.F.R. § 41.50(f). AFFIRMED msc Copy with citationCopy as parenthetical citation