Detailed Action
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 05/19/2026 has been considered by the examiner.
Response to Amendment
The amendment filed 07/28/2026 has been entered. Claims 2, 5, 7-9 are cancelled, and claims 1, 3, 6, 10-16, 18, and 20-22 remain pending in the application. Applicant’s amendments to the Claims have overcome each and every 112(b) rejections previously set forth in the Non-Final Office Action mailed 04/29/2026.
Response to Arguments
Applicant’s arguments filed 07/28/2026 with respect to claim(s) 1 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Given the amendments to claim 1, reference to Vasireddi is being relied upon to teach dependent claim 10-11 more-consistently with the instant claim language, as shown below.
Given the amendments to claim 1, reference to Radulescu is being relied upon to teach dependent claim 12-16 more-consistently with the instant claim language, as shown below.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 3, 6, 10-11, 18, and 20-22 are rejected under 35 U.S.C. 103 as being unpatentable over Chen (CN 111012377 published November 3, 2020) in view of Deo et al. (US 20210000449 A1, published January 7, 2021), Golden et al. (US 20200380675 A1, published December 3, 2020), and Vasireddi et al. (WO 2019071128 A1, published April 11, 2019), hereinafter referred to as Chen, Deo, Golden, and Vasireddi, respectively.
Regarding claim 1, and similarly for claims 18 and 20, Chen teaches a method for detecting medical indices from medical images, the method performed by a processor of a computing device that is operably coupled to a memory storing executable instructions, the method comprising:
receiving, from an image source, a series of medical images depicting a heart over time and including frames at time t-1, time t, and time t+1, each frame constituting a medical image (pg. 6, para. 2 "As shown in FIG. 2 using the convolutional neural network model Unet to divide the left ventricular center cavity of the heart-tip four-cavity tangent plane, using the original ultrasonic image (Echo Cine Raw Frames) [time series of images including timet-1, time t, and timet+1] and light stream (Echo Cine Optical Flow) as input...");
applying an artificial neural network of the processor to the series of medical images to obtain a segmentation prediction for the frame at time t (see pg. 6, para. 2 "As shown in FIG. 2 using the convolutional neural network model Unet to divide the left ventricular center cavity of the heart-tip four cavity tangent plane, using the original ultrasonic image (Echo Cine Raw Frames) and light stream (Echo Cine Optical Flow) as input...to obtain the final image segmentation result (current) of the image segmentation result."),
the artificial neural network configured to model temporal dependencies and having been trained using motion-propagated image pairs by estimating motion vector fields between adjacent frames among the frames at time t-1, time t, and time t+1 and by propagating images and image labels across the adjacent frames (see pg. 6, para. 2 "As shown in FIG. 2 using the convolutional neural network model Unet to divide the left ventricular center cavity of the heart-tip four-cavity tangent plane, using the original ultrasonic image (Echo Cine Raw Frames) [time series of images including time t-1, time t, and time t+1] and light stream (Echo Cine Optical Flow) as input processing the obtained feature map by bidirectional CONVLSTM layer (LSTM) [modelling temporal dependencies]. to obtain the final image segmentation result (current) of the image segmentation result." Training a model is inherent and known in the art);
generating, by the processor, a segmentation mask according to a plurality of regions of the heart depicted at time t (Fig. 2, Outputs include mask of heart region; see pg. 6, para. 2 "to obtain the final image segmentation result (current) of the image segmentation result.").
Chen teaches generating a segmentation mask of a heart region, but does not explicitly teach generating a segmentation mask according to a plurality of regions of the heart.
Whereas, Deo, in an analogous field of endeavor, teaches generating a segmentation mask according to a plurality of regions of the heart, wherein the plurality of regions comprise a first region corresponding to left ventricle (LV), a second region corresponding to interventricular septum (IVS), a third region corresponding to LV posterior wall (LVPW), a fourth region corresponding to right ventricle (RV), a fifth region corresponding to aorta, and a sixth region corresponding to left atrium (LA) (Fig. 3, PLAX view with segmented regions of LV, LA, RV, aorta, IVS, and LV posterior wall; see para. 0056 – “FIG. 3 shows convolutional neural networks successfully segment cardiac chambers. We used the U-net algorithm to derive segmentation models for...PLAX (bottom left)...”).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified generating a segmentation mask of a heart region, as disclosed in Chen, by generating a segmentation mask according to a plurality of regions of the heart, as disclosed in Deo. One of ordinary skill in the art would have been motivated to make this modification in order to precisely measure a plurality of cardiac dimensions in one image.
Chen in view of Deo teaches generating a segmentation mask, but does not explicitly teach computing a reference line corresponding a region based on the segmentation mask.
Whereas, Golden, in an analogous field of endeavor, teaches computing, by the processor, at least one reference line based on the segmentation mask, each of the at least one reference line being a straight line corresponding to one region of the plurality of regions (Fig. 45; see para. 0349 "FIG. 45 is a screenshot4500 of the MPR that displays the regions covered by the individual segmentations [segmentation mask of regions]. In at least some implementations, the MPR displays the major diameter and the orthogonal diameter as lines 4504 and 4506 [reference lines], respectively, on a selected segmentation 4508.").
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified generating a segmentation mask, as disclosed in Chen in view of Deo, by also computing a reference line corresponding to a region based on the segmentation mask, as disclosed in Golden. One of ordinary skill in the art would have been motivated to make this modification in order to display values associated with the physical extent of the segmentation, such as volume of the segmentation, the longest diameter of the segmentation, etc., as taught in Golden (see para. 0349).
Chen in view of Deo and Golden teaches computing a reference line based on a segmentation mask, and it is inherent and known in the art to generate a line within a heart region to calculate a cardiac parameter such as diameter, area, or volume of a heart region, but does not explicitly teach computing reference lines corresponding to different heart regions.
Whereas, Vasireddi, in an analogous field of endeavor, teaches
computing, by the processor, at least one reference line, each of the at least one reference line being a straight line corresponding to one region of the plurality of regions (see para. 0039 – “The algorithms later disclosed herein are performed by the processor 112 according to the instructions contained in the memory 114...In one embodiment, module 116 can detect a left ventricle in a region of interest ("ROI") of the image, and further process the ROI to estimate the left ventricular wall thicknesses (i.e., interventricular septal thickness and posterior wall thickness) and cavity dimensions (i.e., LV length and LV end-diastolic dimension) ("the LV dataset").”); and
determining, by the processor, at least one medical index based on the at least one reference line, each of the at least one medical index comprising a value determined based on a length of the at least one reference line (Fig. 3; see para. 0039 – “The algorithms later disclosed herein are performed by the processor 112 according to the instructions contained in the memory 114...In one embodiment, module 116 can detect a left ventricle in a region of interest ("ROI") of the image, and further process the ROI to estimate the left ventricular wall thicknesses (i.e., interventricular septal thickness and posterior wall thickness) and cavity dimensions (i.e., LV length and LV end-diastolic dimension) ("the LV dataset").”), and
wherein the at least one reference line is computed by:
identifying a transversal line that passes through (1) a reference point of at the first region and (2) a center of a left boundary line of the first region and that crosses the first region (Fig. 3, left ventricular length LVL as transversal line in LV (first region));
identifying a first orthogonal line that intersects the transversal line at the reference point and is orthogonal to the transversal line (Fig. 3, left ventricular end-diastolic dimension LVID as first orthogonal line, intersects and orthogonal to LVL (transversal line));
generating a first reference line including at least a part of the first orthogonal line (Fig. 3, first reference line is the first orthogonal line, where the first orthogonal line is LVID);
identifying a second orthogonal line that passes through a point of contact between the first reference line and a segmentation contour of the second region and is orthogonal to a long axis of the second region (Fig. 3, IVS thickness as second orthogonal line, which is between the first reference line (LVID) and the outer boundary (which would be a segmentation contour) of the IVS, and orthogonal to a long axis);
generating a second reference line including at least a part of the second orthogonal line (the identifying a second orthogonal line (Fig. 3, second reference line is the second orthogonal line, where the second orthogonal line is IVS thickness);
identifying a third orthogonal line that passes through a point of contact between the first reference line and a segmentation contour of the third region and is orthogonal to a long axis of the third region (Fig. 3, PW (posterior wall of LV) thickness as third orthogonal line, which is between the first reference line (LVID) and the outer boundary (which would be a segmentation contour) of the PW, and orthogonal to a long axis); and
generating a third reference line including at least a part of the third orthogonal line (Fig. 3, third reference line is the third orthogonal line, where the third orthogonal line is PW thickness).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified computing a one reference line based on the segmentation mask, as disclosed in Chen in view of Deo and Golden, by computing reference lines corresponding to different heart regions, as disclosed in Vasireddi. One of ordinary skill in the art would have been motivated to make this modification in order to improve accuracy and precision of the estimated LV mass, as taught in Vasireddi (see para. 0009 and 0070).
Furthermore, regarding claims 3, 21, and 22, Golden further teaches generating, by the processor, the at least one reference point based on the segmentation mask, the at least one reference point being generated based on at least one center point of the plurality of regions, wherein the at least one center point is computed from central moments in a corresponding region of the plurality of regions (see para. 0159 – “The centroid of each connected prediction is defined to be the center of mass of predicted probabilities, the center of the binarized mask, the center of the circumscribing bounding box, or the random location within the segmentation, among other options.”).
Furthermore, regarding claim 6, Deo further teaches wherein: the plurality of regions are based on an echocardiographic image acquired in the parasternal long-axis (PLAX) view, the first region is located between the second region and the third region, the second region is located between the fourth region and the first region, the fourth region is located at a top of the echocardiographic image, the fifth region is adjacent to a right side of the first region, and the sixth region is adjacent to the right side of the first region and is located below the fifth region (Fig. 3, PLAX view with segmented regions of LV, LA, RV, aorta, IVS, and LV posterior wall; see para. 0056 – “FIG. 3 shows convolutional neural networks successfully segment cardiac chambers. We used the U-net algorithm to derive segmentation models for...PLAX (bottom left)...”).
Furthermore, regarding claim 10, Vasireddi further teaches wherein the computing the at least one reference line further comprises:
identifying a center line of a short axis of the second region (Fig. 3, IVS thickness as center line of second region (IVS));
identifying a first vertical line perpendicular to a boundary line of the second region at a point where the center line and the boundary line of the second region meet (Fig. 3, LVID as first vertical line, a boundary line at the point where center line (IVS thickness) and boundary of second region (IVS) meet would be perpendicular to first vertical line (LVID)); and
generating a first reference line including at least a part of the first vertical line (Fig. 3, LVID as first reference line, which is first vertical line), and
wherein the first reference line is used to measure a diameter of the first region (Fig. 3, left ventricular end-diastolic dimension LVID (diameter) as first reference line).
Furthermore, regarding claim 11, Vasireddi further teaches wherein the computing the at least one reference line further comprises:
identifying a second vertical line perpendicular to a boundary line of the third region at a point where the first reference line and the boundary line of the third region meet (Fig. 3, PW thickness as second vertical line, a boundary line at the point where first reference line (LVID) and boundary of third region (PW) meet would be perpendicular to second vertical line (PW)); and
generating a second reference line including at least a part of the second vertical line (Fig. 3, PW thickness as second reference line, which is second vertical line), and
wherein the second reference line is used to measure a thickness of the third region (Fig. 3, PW thickness as second line reference).
The motivation for claims 3, 6, 10-11, and 21-22 was shown previously in claim 1.
Claims 12-16 are rejected under 35 U.S.C. 103 as being unpatentable over Chen in view of Deo, Golden, and Vasireddi, as applied to claim 1 above, and in further view of Radulescu et al. (US 20150011886 A1, published January 8, 2015), hereinafter referred to as Radulescu.
Regarding claim 12, Chen in view of Deo, Golden, and Vasireddi teaches all of the elements disclosed in claim 1 above.
Chen in view of Deo, Golden, and Vasireddi teaches measuring different regions of a heart ultrasound image, but does not explicitly teach measuring the diameter of the aorta.
Whereas, Radulescu, in an analogous field of endeavor, teaches wherein the computing the at least one reference line further comprises: identifying a point closest to the fourth region (RV) among points on a boundary line of the fifth region (aorta); identifying a parallel line including the closest point and parallel to a junction of the first region (LV) and the fifth region (aorta); and generating a third reference line including at least a part of the parallel line (identifying the diameter of the aorta; Fig. 4; see para. 0052 – “A caliper measurement of the diameter 424 of the ascending aorta, at its widest, is shown.”).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified measuring different regions of a heart ultrasound image, as disclosed in Chen in view of Deo, Golden, and Vasireddi, by also measuring the diameter of the aorta, as disclosed in Radulescu. One of ordinary skill in the art would have been motivated to make this modification in order to accurately measure for a potential aneurysm, as taught in Radulescu (see para. 0052).
Furthermore, regarding claim 13, Radulescu further teaches wherein the computing the at least one reference line further comprises: identifying a sinus point on a boundary line of the fifth region (aorta), the sinus point occurring at a high point or a low point of a convex part at an end of the boundary line of the fifth region (aorta); identifying a first vertical line including a point closest to the sinus point on a boundary line of the sixth region, the first vertical line being parallel to a vertical axis of the medical image and penetrating the sixth region (LA); and generating a fourth reference line including at least a part of the first vertical line (identifying the diameter of the aorta; Fig. 4; see para. 0052 – “A caliper measurement of the diameter 424 of the ascending aorta, at its widest, is shown.”).
Furthermore, regarding claim 14, Radulescu further teaches wherein the computing the at least one reference line further comprises: identifying a sinus point on a boundary line of the fifth region (aorta), the sinus point occurring at a high point or a low point of a convex part at an end of the boundary line of the fifth region; identifying a second vertical line including a point closest to the sinus point on a boundary line of the sixth region, the second vertical line being perpendicular to a long axis of the sixth region and penetrating the sixth region; and generating a fourth reference line including at least a part of the second vertical line (identifying the diameter of the aorta; Fig. 4; see para. 0052 – “A caliper measurement of the diameter 424 of the ascending aorta, at its widest, is shown.”).
Furthermore, regarding claim 15, Radulescu further teaches wherein the computing the at least one reference line further comprises: identifying a third vertical line including one point on a junction of the fifth region (aorta) and the first region (LV) and being perpendicular to a center line of a long axis of the fourth region (RV); and generating a fifth reference line including at least a part of the third vertical line (identifying length of aortic valve; see para. 0046 – “Then, a pair of imaging planes 108, 160 is selected to optimally cut the ring such that the resulting 2D images allow for proper aortic valve annulus diameter measurements...”).
Furthermore, regarding claim 16, Radulescu further teaches wherein the computing the at least one reference line further comprises: identifying a fourth vertical line including one point on a junction of the fifth region and the first region and being perpendicular to a vertical axis of the medical image at time t; and generating a fifth reference line including at least a part of the fourth vertical line (identifying length of aortic valve; see para. 0046 – “Then, a pair of imaging planes 108, 160 is selected to optimally cut the ring such that the resulting 2D images allow for proper aortic valve annulus diameter measurements...”).
The motivation for claims 13-16 was shown previously in claim 12.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Hare et al. (US 20200226757 A1, published July 16, 2020) discloses linear measurements of chamber size and inter-chamber distances are conducted on the systolic and diastolic frames of the video using image processing techniques to mimic the trained clinician, including measuring aortic valve area and aorta diameter.
Hare et al. (US 20230351593 A1, published November 2, 2023 with a priority date of December 11, 2018) discloses the segmented 2D images, including PLAX segmented images, are used to calculate measurements of cardiac features of the heart.
Gupta et al. (US 20130190600 A1, published July 25, 2013) discloses segmenting the features of interest in PLAX images.
Samset et al. (US 20190392944 A1, published December 26, 2019) discloses using the echocardiogram as an example, the diagnostic workflow protocol may define which distance, volume, mass, etc., measurements are to be taken on various anatomical features, such as the left ventricle, right ventricle, aorta, etc.
Nair (US 10971272 B1, published April 6, 2021) discloses findings input screens for the primary reporting structures (i.e., aorta, LV, aortic valve, RV) of the Parasternal long axis view.
Snider (US 5553620 A, published September 10, 1996) discloses cardiac calculations of 2D chamber dimensions in parasternal long axis view.
Rothberg (US 20190059851 A1, published February 28, 2019) discloses the aggregated landmark coordinate estimates are computed in a new center of mass layer from input at each predicting location.
Rothberg et al. (US 20170360412 A1, published December 21, 2017) discloses aggregation of the regressed locations at the last convolution layer is ensured by a new center-of-mass layer which computes mean position of the predictions.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Nyrobi Celestine whose telephone number is 571-272-0129. The examiner can normally be reached on Monday - Thursday, 7:00AM - 5:00PM EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Pascal Bui-Pho can be reached on 571-272-2714. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/N.C./Examiner, Art Unit 3798
Prosecution Insights