Ex Parte Zhu et al

Patent Trial and Appeal Board

Aug 29, 2016

12774146 (P.T.A.B. Aug. 29, 2016)

UNITED STA TES p A TENT AND TRADEMARK OFFICE
APPLICATION NO. FILING DATE
121774,146 05/05/2010
28524 7590 08/31/2016
SIEMENS CORPORATION
INTELLECTUAL PROPERTY DEPARTMENT
3501 Quadrangle Blvd Ste 230
Orlando, FL 32817
FIRST NAMED INVENTOR
Ying Zhu
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
ATTORNEY DOCKET NO. CONFIRMATION NO.
2009P07877US01 7371
EXAMINER
PAULSON, SHEETAL R.
ART UNIT PAPER NUMBER
3686
NOTIFICATION DATE DELIVERY MODE
08/31/2016 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 YING ZHU, SIMONE PRUMMER, PENG WANG,
TERRENCE CHEN, MARTIN OSTERMEIER, and DORIN COMANICIU
Appeal2014-003442 1
Application 12/774,1462
Technology Center 3600
Before HUBERT C. LORIN, BART A. GERSTENBLITH, and
TARA L. HUTCHINGS, Administrative Patent Judges.
HUTCHINGS, Administrative Patent Judge.
DECISION ON APPEAL
STATEMENT OF THE CASE
Appellants appeal under 35 U.S.C. § 134(a) from the Examiner's final
rejection of claims 1-26. We have jurisdiction under 35 U.S.C. § 6(b).
We REVERSE.
1 Our decision references Appellants' Appeal Brief ("App. Br.," filed
Sept. 9, 2013) and Reply Brief ("Reply Br.," filed Jan. 17, 2014), and the
Examiner's Answer ("Ans.," mailed Nov. 21, 2013), Advisory Action
("Adv. Act.," mailed July 2, 2013), and Final Office Action ("Final Act.,"
mailed Apr. 12, 2013).
2 Appellants identify Siemens Aktiengesellschaft as the real party in
interest. App. Br. 1.
Appeal2014-003442
Application 12/774,146
CLAIMED fNVENTION
Appellants' claimed invention "relates to fluoroscopic image
sequences, and more particularly to detecting coronary vessel layers from
fluoroscopic image sequences." Spec. i12.
Claims 1, 11, and 20 are the independent claims on appeal. Claim 1,
reproduced below, is illustrative of the subject matter on appeal:
1. A method for extracting coronary vessels from a
contrast image, comprising:
calculating a motion field between each of a plurality of
mask images and a background region of the contrast image and
calculating covariances of motion vectors of each motion field;
generating a plurality of background layer predictions by
generating a background layer prediction from each of the
plurality of mask images based on the motion field and the
covariances of the motion field from each of the plurality of mask
images;
combining the plurality of background layer predictions
using statistical fusion to generate a final estimated background
layer; and
extracting a coronary vessel layer from the contrast image
by subtracting the final estimated background layer from the
contrast image.
REJECTION
Claims 1-26 are rejected under 35 U.S.C. § 102(e) as anticipated by
Zhu (US 2009/0010512 Al, pub. Jan. 8, 2009).
ANALYSIS
Independent Claim 1 and Dependent Claims 2-10
We are persuaded by Appellants' argument that the Examiner erred in
rejecting claim 1under35 U.S.C. § 102(e) because Zhu does not disclose or
suggest "combining the plurality of background layer predictions using
2
Appeal2014-003442
Application 12/774,146
statistical fusion to generate a final background layer," as recited in claim 1.
App. Br. 4--8; see also Reply Br. 2-3. The Examiner relies on paragraphs 27
and 28 of Zhu as disclosing the argued limitation. Final Act. 3. But we find
nothing in the cited paragraphs that discloses the argued limitation.
Zhu relates to detecting coronary vessel layers from fluoroscopic
image sequences. Zhu i-f 2. A method for extracting coronary vessels from a
fluoroscopic image sequence first involves receiving a sequence of mask
images and receiving a sequence of contrast images. Id. i-fi-122-23, Fig. 1
(steps 102 and 104). The mask images are fluoroscopic images of a
coronary region of a patient without any contrast agent injected into the
coronary vessels; whereas, the contrast images are fluoroscopic images in
which a contrast agent is so injected. Id. A sequence includes images of the
coronary region taken over a full cardiac cycle at regular intervals.
Id. i-fi-121, 23. After receiving the sequence of mask images and the sequence
of contrast images, the method processes the sequence of contrast images
frame-by-frame to independently extract the coronary vessels for each
contrast image in the sequence. Id. i-f 23. Thus, the method performs the
steps described below independently for each contrast image in the
sequence. Id.
Vessel regions in the contrast image are detected using learning-based
vessel segment detection. Id. i-fi-124--25, Fig. 1 (step 106). Background
motion is estimated between each of the mask image and the background
region of the contrast image. Id. i-f 26, Fig. 1 (step 108). The background
region of the contrast image is obtained by excluding the detected vessel
regions from the original contrast image. Id. The mask images are warped
based on the estimated background motion, and the warped mask image that
3
Appeal2014-003442
Application 12/774,146
best matches the background region of the contrast image is selected. Id.
Since the set of mask images represent a full cardiac cycle, the selected
mask image is the mask image obtained at the most similar point in the
cardiac cycle as the contrast image. Id. The selected mask image is warped
to compensate for motion between the mask and the background region of
the contrast image to generate an estimated background layer. Id. i-f 28,
Fig. 1 (step 110). And the coronary vessel layer is extracted from the
contrast image by subtracting the warped mask image from the contrast
image. Id. i-f 29, Fig. 1 (step 112).
In determining that Zhu teaches the argued combining limitation, the
Examiner finds:
Zhu teaches a motion field estimated using robust motion
estimation, which estimates the motion between the background
contrast image and a mask image; once that is calculated the
covariance-based fusion is applied to obtain the final estimate
of a dense motion field. Furthermore, Zhu [sic] that the mask
image is a background layer consisting of various background
structures, therefore multiple background layers; the mask
images are warped together to create an estimated background
layer.
Ans. 7.
However, Zhu does not disclose that the mask images are warped
together to create an estimated background layer. Rather, Zhu discloses that
one selected mask image that best-matches the contrast image is warped to
create an estimated background layer. See Zhu i-f 28. Additionally, while
Zhu describes using "covariance-based fusion," this is performed to estimate
a dense motion field. See id. i-f 27. Further, the background structures
mentioned in paragraph 27 of Zhu refer to structures within the image that
4
Appeal2014-003442
Application 12/774,146
"undergo non-rigid motion and are seen again in a contrast image" (id.), and
would not be construed as "multiple background layers."
In view of the foregoing, we do not sustain the Examiner's rejection
under 35 U.S.C. § 102(e) of independent claim 1 and claims 2, 5, 6, and 8-
12, which depend therefrom.
Independent Claims 11and20, and Dependent Claims 12-19 and 21-26
Independent claims 11 and 20 include language substantially similar
to the language of claim 1, and stand rejected based on the same erroneous
findings applied with respect to claim 1. Final Act. 5. Therefore, we do not
sustain the Examiner's rejection under 35 U.S.C. § 102(e) of independent
claims 11 and 20 and claims 12-19 and 16-21, which depend therefrom, for
the same reasons set forth with respect to claim 1.
DECISION
The Examiner's rejection of claims 1-26 under 35 U.S.C. § 102(e) is
reversed.
REVERSED
5