Ex Parte Grbic et al

Patent Trial and Appeal Board

Mar 23, 2017

13713603 (P.T.A.B. Mar. 23, 2017)

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.
13/713,603 12/13/2012 Sasa Grbic 2011P28451US01 1006
28524 7590 03/27/2017
SIEMENS CORPORATION
INTELLECTUAL PROPERTY DEPARTMENT
3501 Quadrangle Blvd Ste 230
EXAMINER
PATEL, JITESH
Orlando, EL 32817 ART UNIT PAPER NUMBER
2617
NOTIFICATION DATE DELIVERY MODE
03/27/2017 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 SASA GRBIC, RAZVANIOANIONASEC,
FERNANDO VEGA-HIGUERA, DOMINIK BERNHARDT,
and
DORIN COMANICIU
Appeal 2017-000637
Application 13/713,603
Technology Center 2600
Before BRADLEY W. BAUMEISTER, JOSEPH P. LENTIVECH, and
DAVID J. CUTITTAII, Administrative Patent Judges.
CUTITTA, Administrative Patent Judge.
DECISION ON APPEAL
Appellants appeal under 35 U.S.C. § 134(a) from the Examiner’s
rejections of claims 1—30, which constitute all of the claims pending in this
application. Appeal Br. I.1 We have jurisdiction under 35 U.S.C. § 6(b).
We reverse.
1 Rather than repeat the Examiner’s positions and Appellants’ arguments in
their entirety, we refer to the following documents for their respective
details: Appellants’ Specification filed December 13, 2012 (“Spec.”); the
Appeal 2017-000637
Application 13/713,603
STATEMENT OF THE CASE
Appellants describe the present invention as follows:
A method and system for automatic aortic valve
calcification evaluation is disclosed. A patient-specific aortic
valve model in a 3D medical image volume, such as a 3D
computed tomography (CT) volume. Calcifications in a region
of the 3D medical image volume [are] defined based on the aortic
valve model. A 2D calcification plot is generated that shows
locations of the segmented calcifications relative to aortic valve
leaflets of the patient-specific aortic valve model. The 2D
calcification plot can be used for assessing the suitability of a
patient for a Transcatheter Aortic Valve Replacement (TAVI)
procedure, as well as risk assessment, positioning of an aortic
valve implant, and selection of a type of aortic valve implant.
Abstract.
Independent claim 1, reproduced below, is illustrative of the appealed
claims:
1. A method for automatic aortic valve calcification
evaluation, comprising:
detecting a patient-specific aortic valve model in a
3D medical image volume;
segmenting calcifications in a region of the 3D
medical image volume defined based on the aortic valve
model; and
generating a 2D calcification plot showing locations
of the segmented calcifications relative to aortic valve
leaflets of the patient-specific aortic valve model.
Appeal Br. 17 (Claims App’x).
Final Action mailed August 20, 2015 (“Non-Final Act.”); the Appeal Brief
filed January 20, 2016 (“Appeal Br.”); the Examiner’s Answer mailed
August 3, 2016 (“Ans.”); and the Reply Brief filed October 3, 2016 (“Reply
Br.”).
2
Appeal 2017-000637
Application 13/713,603
REFERENCES
The Examiner relies upon the following prior art in rejecting the
claims on appeal:
Jurgen K. Willmann et al., Electrocardiographically Gated Multi-Detector
Row CTfor Assessment of Valvular Morphology and Calcification in Aortic
Stenosis, Institute of Diagnostic Radiology 120 (2002) (“Willmann”).
Giovanni Melina et al., Three-dimensional in vivo characterization of
calcification in native valves and in Freestyle versus homograft aortic
valves, The Journal of Thoracic and Cardiovascular Surgery Volume 130,
Number 1, 41 (2005) (“Melina”).
Razvan loan Ionasec et al., Patient-Specific Modeling and Quantification of
the Aortic and Mitral Valves from 4D Cardiac CT and TEE, IEEE
TRANSACTIONS ON MEDICAL IMAGING 1 (2009) (“Razvan”).
Victoria Delgado et al., Automated Assessment of the Aortic Root
Dimensions With Multidetector Row Computed Tomography, Ann. Thoracic
Surgeons 91:716-23 (2011) (“Delgado”).
Claims 1—4, 7, 8, 14, 15, 17, 18, 20—22, and 25 stand rejected under
35 U.S.C. § 103(a) as obvious over Razman and Willmann. Final Act. 7—14.
Claims 5, 6, 16, 23, and 24 stand rejected under 35 U.S.C. § 103(a) as
obvious over Razman, Willmann, and Rollins. Final Act. 14—17.
Claims 9, 19, and 26 stand rejected under 35 U.S.C. § 103(a) as
obvious over Razman, Willmann, and Melina. Final Act. 17—18.
Claims 10, 12, 13, 27, 29, and 30 stand rejected under 35 U.S.C.
§ 103(a) as obvious over Razman, Willmann, and Delgado. Final Act. 18—
Suri
Rollins et al. (“Rollins”)
US 2011/0257545 Al Oct. 20, 2011
US 2012/0075638 Al Mar. 29, 2012
REJECTIONS
21.
3
Appeal 2017-000637
Application 13/713,603
Claims 11 and 28 stand rejected under 35 U.S.C. § 103(a) as obvious
over Razman, Willmann, and Suri. Final Act. 21—22.
We review the appealed rejections for error based upon the issues
identified by Appellants, and in light of the arguments and evidence
produced thereon. Ex parte Frye, 94 USPQ2d 1072, 1075 (BPAI 2010)
(precedential).
FINDINGS AND CONTENTIONS
The Examiner finds that Razvan teaches the claimed steps of detecting
“a patient-specific aortic valve model in a 3D medical image volume” and
“segmenting calcifications in a region of the 3D medical image volume
defined based on the aortic valve model,” as recited in claim 1. Final
Act. 7—8 (citing Razman Figs. 10, 13(i)). In particular, the Examiner finds
Razvan teaches segmenting calcifications because “[F]ig. 13 (i), although
not labeled with a ‘calcium deposit’ marking, does depict equivalent calcium
deposit regions as white spots in conjunction with the depicted aortic
stenosis that is caused by said calcium deposits.” Final Act. 23. The
Examiner, again referring to Figure 13(i) of Razman, expands upon this
finding in the Answer:
The calcifications in said regions of the 3D medical image
volume appear segmented based on the patient-specific aortic
model. The image suggests a segmenting of the underlying
calcifications based on the superimposed patient-specific aortic
model because the model specifically corresponds to the
underlying 3D medical image of aortic stenosis with severe
calcifications and the underlying calcifications appear
segmented by the superimposed patient-specific aortic model.
Ans. 3.
4
Appeal 2017-000637
Application 13/713,603
The Examiner finds that Razvan does not teach “generating a
2D calcification plot showing locations of the segmented calcifications
relative to aortic valve leaflets of the patient-specific aortic valve model.”
Final Act. 7—8. The Examiner finds that Willmann teaches this limitation.
Final Act. 7—8; Ans. 2—A. The Examiner finds that motivation exists “to
include Willmann’s method of reconstructing calcification related data to
create aortic valve calcification diagrams in Razvan’s aortic modeling.”
Final Act. 8—9.
Appellants assert, among other arguments, that while Razvan’s
Figure 13(i) shows aortic calcification, the imaged calcification is not
segmented. Appeal Br. 6. Appellants further assert that
although Fig. 13(i) of Razvan shows the results for estimating a
patient-specific model of the aortic valve for a patient with aortic
stenosis with severe calcification, the calcifications themselves
are not segmented in Fig 13(i). That is, FIG. 13(i) of Razvan
merely shows that the aortic valve modeling algorithm of Razvan
can be successfully performed in the presence of aortic stenosis
with severe calcification, but does not disclose segmentation of
the calcifications. There is no [] description in Razvan of
segmenting calcifications in a regions defined by the patient-
specific model of the aortic valve.
Id.
ANAFYSIS
Claim 1 recites “segmenting calcifications in a region of the
3D medical image volume defined based on the aortic valve model.” The
Specification explains that image segmentation of the calcifications may by
accomplished using the graph cuts segmentation algorithm. Spec. 122. The
Specification further indicates “[i]t is also possible that other segmentations
5
Appeal 2017-000637
Application 13/713,603
techniques, such as a random walker segmentation algorithm, intensity-
based thresholding, or machine-learning based classification can be used to
implement the calcification segmentation.” Spec. 123.
As such, Appellants’ Specification reasonably indicates that “image
segmenting,” as used in the present context, is an affirmative process of
partitioning clusters of a digital image’s pixels into salient image regions
that correspond to individual surfaces, objects, or natural parts of objects.
See e.g., http://www.cs.toronto.edu/~iepson/csc2503/segmentation.pdf.
Image segmentation is not suggested by an image appearing segmented and
is not merely a result of the image naturally having light and dark regions.
Razvan relates to patient specific modeling of the aortic valve using
cardiac computed tomography (CT) and transesophageal echocardiogram
(TEE) data. Razvan 1. Figure 13 of Razvan shows estimation results on
various pathologies for both valves and imaging modalities, including aortic
stenosis with severe calcification at Figure 13(i). Razvan 13.
The Examiner does not provide sufficient evidence that Razvan
teaches segmenting calcifications as claimed. That is, we find insufficient
the Examiner’s rationale that Razvan teaches segmenting calcifications
because the calcifications in Razvan’s Figure 13 (i) “appear segmented”
(Ans. 3) and are depicted as “white spots.” Final Act. 23. Instead, we agree
with Appellants that the figure cited by the Examiner “merely shows . . .
aortic stenosis with severe calcification, but does not disclose segmentation
of the calcifications.” Appeal Br. 6. Furthermore, the Examiner fails to cite
to any text in Razvan that specifically describes segmenting the
calcifications of Figure 13 (i).
6
Appeal 2017-000637
Application 13/713,603
CONCLUSIONS
For at least the foregoing reasons, Appellants have persuaded us of
error in the Examiner’s obviousness rejection of independent claims 1,14,
and 20, each of which recite “segmenting calcifications.” Accordingly, we
do not sustain the Examiner’s rejection of these claims, or of claims 2—4, 7,
8, 15, 17, 18, 21, 22, and 25, which depend from these claims.
With respect to the remaining rejections of dependent claims 5, 6, 9,
10-13, 16, 19, 23, 24, and 26—30, the additional reliance on Rollins, Melina,
Delgado, and Suri, taken alone or in combination, does not cure the
deficiency of the obviousness rejection discussed above. See Final Act. 14—
22 (indicating that the respective references are relied upon only for the
additional limitations of the cited dependent claims).
DECISION
The Examiner’s decision rejecting claims 1—30 is reversed.
REVERSED
7