10323986 (B.P.A.I. May. 19, 2010)

Ex Parte Sabol et al

Board of Patent Appeals and InterferencesMay 19, 2010

10323986 (B.P.A.I. May. 19, 2010)

UNITED STATES PATENT AND TRADEMARK OFFICE _____________ BEFORE THE BOARD OF PATENT APPEALS AND INTERFERENCES _____________ Ex parte JOHN M. SABOL, GOPAL B. AVINASH, and MATTHEW J. WALKER _____________ Appeal 2009-004773 Application 10/323,986 Technology Center 2600 ______________ Decided: May 19, 2010 _______________ Before, ROBERT E. NAPPI, THOMAS S. HAHN, and ELENI MANTIS MERCADER, Administrative Patent Judges. NAPPI, Administrative Patent Judge. DECISION ON APPEAL Appeal 2009-004773 Application 10/323,986 This is a decision on appeal under 35 U.S.C. § 134(a) of the final rejection of claims 1-58. We have jurisdiction under 35 U.S.C. § 6(b). We affirm the Examiner’s rejection of these claims. INVENTION The invention is directed to a system and method for processing images wherein both a human and a computer detect and classify features within the image. The human and computer findings are reconciled with one another in order to create a final image data set. See Spec: 1-7. Claim 1 is representative of the invention and reproduced below: 1. A method for processing an image for use by an end user, comprising: providing an image data set to one or more human analysts, wherein the human analyst detects one or more features within the image data set to produce a feature detected data set; providing the feature detected data set to one or more human classifiers, wherein the human classifier classifies each of the one or more features with a first classification to produce a human classified data set; subjecting the feature detected data set to one or more computer implemented classification routines which classify each of the one or more features with a second classification to produce a computer classified data set; combining the human classified data sets and the computer classified data sets to form an integrated image data set; and reconciling one or more discrepancies between the human classified data sets and the computer classified data sets which are present in the integrated image data set to form a final image data set. 2 Appeal 2009-004773 Application 10/323,986 REFERENCES Courtney US 5,519,786 May 21, 1996 Kaufman US 2003/0016850 A1 Jan. 23, 2003 (filed Jul. 17, 2001) Rogers US 6,556,699 B2 Apr. 29, 2003 (filed Aug. 24, 2001) REJECTION AT ISSUE Claims 1, 2, 5-11, 45, 46, and 48-51 are rejected under 35 U.S.C. § 103(a) as being unpatentable over Rogers. Ans. 3-5. Claims 3, 4, 23-31, 41-44, and 47 are rejected under 35 U.S.C. § 103(a) as being unpatentable over Rogers in view of Kaufman. Ans. 5-8. Claims 12, 13, and 16-22 are rejected under 35 U.S.C. § 103(a) as being unpatentable over Rogers in view of Courtney. Ans. 8-10. Claims 14, 15, 32-40, and 52-581 are rejected under 35 U.S.C. § 103(a) as being unpatentable over Rogers in view of Courtney and Kaufman. Ans. 10-13. ISSUE 35 U.S.C. § 103(a) rejections Appellants argue on pages 10-13 of the Appeal Brief and pages 3-5 of the Reply Brief that the Examiner’s rejection of claims 1, 2, 5-11, 45, 46, 1 While claim 60 was included in the Examiner’s rejection, claim 60 was cancelled in response to an Election/Restriction Requirement, mailed April 5, 2006. Therefore, claim 60 will not be addressed. 3 Appeal 2009-004773 Application 10/323,986 and 48-51 is in error. Appellants argue that Rogers does not disclose “'subjecting [a] feature detected data set to one or more computer implemented classification routines’ where a ‘human analyst [has detected] one or more features within [an] image data set to produce [the] feature detected data set.’” App. Br. 10. Additionally, Appellants argue on pages 13-17 of the Appeal Brief that the Examiner’s rejection of claims 3-4, 12-44, 47, and 52-58 is in error for the same reasons as independent claims 1 and 45. Thus, Appellants’ contentions with respect to claims 1-58 present us with the issue: Did the Examiner err in finding that Rogers discloses subjecting the feature detected data set to one or more computer implemented classification routines where the human analyst detects one or more features within the image data set to produce a feature detected data set? FINDINGS OF FACT (FF) Rogers 1. Rogers discloses a method and system of automatically detecting microcalcifications in a radiographic image. Col. 1, ll. 24-26. 2. A digital mammogram is manually cropped to create an analysis region that includes areas of the image that contain breast tissue. Col. 5, ll. 1-9. 3. The cropped mammogram is operated on by a computer-assisted diagnostic (CAD) system to create a set of suspicious regions. Col. 1, ll. 53-55 and col. 17, ll. 59-61. 4 Appeal 2009-004773 Application 10/323,986 PRINCIPLES OF LAW Office personnel must rely on Appellants’ disclosure to properly determine the meaning of the terms used in the claims. Markman v. Westview Instruments, Inc., 52 F.3d 967, 980 (Fed. Cir. 1995) (en banc). “[I]nterpreting what is meant by a word in a claim is not to be confused with adding an extraneous limitation appearing in the specification, which is improper.” In re Cruciferous Sprout Litigation, 301 F.3d 1343, 1348 (Fed. Cir. 2002) (internal quotation marks and citations omitted; emphasis in original). ANALYSIS 35 U.S.C. § 103(a) rejections Appellants’ arguments have not persuaded us of error in the Examiner’s rejection of claims 1-58. Independent claim 1 recites a “human analyst detects one or more features within the image data set to produce a feature detected data set…[and]…subjecting the feature detected data set to one or more computer implemented classification routines.” Independent claim 45 recites similar limitations. Appellants initially argue that Rogers does not disclose an image wherein a human analyst has identified any features because manually cropping an image is not the same as detecting one or more features in an image data set. App. Br. 10. In addition, Appellants argue that the Examiner’s interpretation is inconsistent with the claim language and that a more reasonable interpretation would require the human analyst to detect distinct data. App. Br. 12; Reply Br. 3. While the interpretation cited by Appellants may be what Appellants intended, the Examiner is only required to “give claims their broadest reasonable construction consistent with the specification.” In re ICON Health and 5 Appeal 2009-004773 Application 10/323,986 Fitness, Inc., 496 F. 3d 1374, 1379 (Fed. Cir. 2007). The term “features” is found in Appellants’ Specification. However, the Specification does not provide a specific definition for the term. As such, we adopt, and find reasonable, the Examiner’s interpretation that detecting features includes cropping an image to only include portions of an image that are of interest. Ans. 13. Based upon the Examiner’s reasonable interpretation of the term “features,” as described above, we find that Rogers does disclose the claim limitations of claim 1, recited above. Rogers discloses an image data set that is manually cropped, to separate an analysis region (consisting of breast tissue), from the entire image to create the feature detected data set. FF 1, 2. This feature detected data set, i.e., the breast tissue of interest, is submitted for computer-aided diagnosis (CAD) and suspicious regions are reported as an additional data set. FF 3. Thus, Rogers discloses a human analyst detecting one or more features in an image data set to produce a detected data set and the detected data set is subjected to a computer implemented classification routine. As such, Appellants’ arguments are not found to be persuasive. Accordingly, Appellants’ arguments have not persuaded us that the Examiner erred in finding that Rogers discloses subjecting the feature detected data set to one or more computer implemented classification routines where the human analyst detects one or more features within the image data set to produce a feature detected data set. Accordingly, we sustain the Examiner’s rejection of independent claims 1 and 45 and claims 2-44 and 46-58. 6 Appeal 2009-004773 Application 10/323,986 SUMMARY The Examiner’s decision to reject claims 1-58 is affirmed. No time period for taking any subsequent action in connection with this appeal may be extended under 37 C.F.R. § 1.136 (a)(1)(iv). AFFIRMED ELD PATRICK S. YODER FLETCHER, YODER & VAN SOMEREN P.O. BOX 692289 HOUSTON, TX 77269-2289 7