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 .
Response to Amendment
Claim 6 is cancelled, claim 21 is added, and claims 1-5 and 7-21 remain pending in the application in response to the applicant’s amendments to the rejections previously set forth in the Non-Final Office Action mailed 04/08/2026.
Response to Arguments
Applicant’s arguments filed 07/27/2026 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 Ezhov is being relied upon to teach dependent claim 2, 17, and 21 more-consistently with the instant claim language, as shown below.
Given the amendments to claim 1, reference to Masood is being relied upon to teach dependent claim 7 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 1-5 and 8-21 are rejected under 35 U.S.C. 103 as being unpatentable over Li et al. (US 20220114388 A1, published April 14, 2022), from IDS, in view of Ezhov et al. (US 20230013902 A1, published January 19, 2023 with a priority date of October 30, 2018), hereinafter referred to as Li and Ezhov, respectively.
Regarding claim 1, and similarly for claims 10 and 16, Li teaches an image diagnostic system comprising:
a catheter insertable into a blood vessel (see para. 0083 "A catheter-based data collection probe 30 is introduced into the subject 4 and is disposed in the lumen of the particular blood vessel, such as for example, a coronary artery.");
a memory that stores a program (see para. 0091 "For example, the software modules 67 can be running on a processor at workstation 85 and the database 90 can be located in the memory of server 50."); and
a processor configured to execute the program (see para. 0096 "Various software modules that can include without limitation software, a component thereof, or one or more steps of a software-based or processor executed method can be used in a given embodiment of the disclosure.'") to:
control the catheter to acquire a tomographic image of a blood vessel (see para. 0080 "Angiography system 20 is configured to noninvasively image the subject 4 such that frames of angiography data, typically in the form of frames of image data, are generated while a pullback procedure is performed using a probe 30 such that a blood vessel in region 25 of subject 4 is imaged using angiography in one or more imaging technologies such as OCT or IVUS, for example."),
input the acquired image into a computer model to generate information that indicates a plurality of predetermined regions of the blood vessel in the image (Fig. 1F; see para. 0121 "Once the MLS [machine learning system, computer model] is trained, inputting image data to the neural network is performed to generate a set of image data with predictions, detections, classifications, etc. of the various features/regions of interest. Step 105."),
using the generated information, determine the predetermined regions of the blood vessel in the acquired image, and output information indicating the determined regions (see para. 0156 "An exemplary output Cartesian image of a patient artery that has been classified by an MLS [machine learning system] and one or more related methods is shown in FIGS. 3D and 3E in images B and D.").
Li teaches inputting an image to a trained computer model to output information indication a plurality of regions of the blood vessel in the image, but does not explicitly teach also outputting information indicating whether the regions overlap.
Whereas, Ezhov, in an analogous field of endeavor, teaches the information further indicating for each of the predetermined regions whether it overlaps another region, the computer model having been trained with a plurality of tomographic images and a plurality of information each specifying the predetermined regions that can overlap in a corresponding one of the tomographic images, and wherein the generated information indicates, for each of pixels of the input image, respective probabilities that the pixel corresponds to the predetermined regions, and each of the probabilities is determined such that a single pixel can correspond to two or more of the predetermined regions that overlap (see para. 0111 – “In one embodiment, a model of a probability distribution over anatomical structures via semantic segmentation may be performed: using a standard fully-convolutional network [computer model], such as VNet or 3D UNet, to transform IxHxWxD tensor of input image with I color channels per voxel [3D pixel], to HxWxDxC tensor defining class probabilities per voxel [3D pixel], where C is the number of possible classes (anatomical structures) [predetermined regions]… In case of a class overlap, a sigmoid activation function may be applied to each class in C independently [a single pixel can correspond to two or more of the predetermined regions that overlap].” where it is inherent and known in the art for train a convolutional neural network using labeled images).
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 outputting information of an image from the trained model, as disclosed in Li, by having the information include indicating whether the regions overlap, as disclosed in Ezhov. One of ordinary skill in the art would have been motivated to make this modification in order to define a plurality of class probabilities per voxel, as taught in Ezhov (see para. 0111).
Furthermore, regarding claims 2 and 17, Ezhov further teaches wherein the processor executes the program further to: determine a closed area in the acquired image in which two or more predetermined regions overlap, assign two or more labels corresponding to said two or more predetermined regions to the closed area, and store, in the memory, information that associates the closed area with the assigned labels (see para. 0111 – “see para. 0111 – “In one embodiment, a model of a probability distribution over anatomical structures via semantic segmentation may be performed: using a standard fully-convolutional network, such as VNet or 3D UNet, to transform IxHxWxD tensor of input image with I color channels per voxel, to HxWxDxC tensor defining class probabilities per voxel, where C is the number of possible classes (anatomical structures)…” where it is inherent and known in the art for train a convolutional neural network using labeled images).
Furthermore, regarding claims 3 and 18, Li further teaches wherein the predetermined regions include at least two of a region inside a stent, a region of a lumen, and a region inside an external elastic membrane(see para. 0104 "Each region/feature corresponding to lumen L, intima I, plaque Q, adventitia ADV, imaging probe P, media M, and others may be generated by the MLS using a trained NN such as a CNN.").
Furthermore, regarding claims 4 and 19, Li further teaches wherein the predetermined regions further include at least one of a plaque region, a thrombus region, a hematoma region, and a medical device region (see para. 0104 "Each region/feature corresponding to lumen L, intima I, plaque Q, adventitia ADV, imaging probe P, media M, and others may be generated by the MLS using a trained NN such as a CNN.").
Furthermore, regarding claims 5 and 20, Li further teaches a display, wherein the processor executes the program further to control the display to display the information indicating the determined regions (see para. 0122 "In one embodiment, the method includes displaying final predictive output images from neural network/machine learning system with class/type indicia. Step 108.").
Furthermore, regarding claim 8, Li further teaches wherein the catheter includes:
a first sensor configured to transmit ultrasonic waves and receive the waves reflected by the blood vessel while the catheter is inserted in the blood vessel, and a second sensor configured to emit light and receive the light reflected by the blood vessel while the catheter is inserted in the blood vessel (see para. 0085 "For example a combination OCT [second sensor] and IVUS [first sensor] data collection probe requires an OCT and IVUS PIU [patient interface unit 35]."), and
the processor executes the program to:
generate an ultrasonic tomographic image of the blood vessel based on the reflected waves received by the first sensor and an optical coherence tomographic image of the blood vessel based on the reflected light received by the second sensor (see para. 0085 "For example a combination OCT and IVUS data collection probe requires an OCT and IVUS PIU...In this way, a blood vessel of the subject4 can be imaged longitudinally or via cross-sections."), and
input the generated images into the computer model to generate the information (Fig. 1F; see para. 0121 "Once the MLS [machine learning system, computer model] is trained, inputting image data to the neural network is performed to generate a set of image data with predictions, detections, classifications, etc. of the various features/regions of interest. Step 105.").
Furthermore, regarding claim 9, Li further teaches an angiography apparatus configured to generate an angiographic image of the blood vessel, wherein the catheter includes a marker that can be imaged by the angiography apparatus (see para. 0080 "Angiography system 20 is configured to noninvasively image the subject 4 such that frames of angiography data, typically in the form of frames of image data, are generated while a pullback procedure is performed using a probe 30 such that a blood vessel in region 25 of subject 4 is imaged using angiography in one or more imaging technologies such as OCT or IVUS, for example."; see para. 0083 "The probe 30 typically includes a probe tip, one or more radiopaque markers, an optical fiber, and a torque wire.").
Furthermore, regarding claim 11, Li further teaches wherein the processor executes the program to assign one or more labels each indicating one of the predetermined regions to a closed area in the tomographic image (see para. 0143 "The user selected region for annotation in FIG. 3B corresponds to Media as shown by the class identifier selected in FIG. 3A. In this way, any feature/class can be selected for labelling and is stored in memory with the annotations.").
Furthermore, regarding claim 12, Li further teaches an input device, wherein the processor executes the program to specify the closed area upon input of a designation thereof on the displayed image through the input device (see para. 0143 "FIGS. 3A and 3B show user interfaces [input device] for a system suitable for navigating through frames of image data and annotating image data to generate ground truths… In one embodiment, various drawing and editing tools can be used to annotate raw image data. These annotated image can be used to generate ground truth masks with the class or feature of the annotating region being defined and stored in memory using interface 305 of FIG. 3A.").
Furthermore, regarding claim 13, Li further teaches wherein the GUI components include a plurality of buttons corresponding to the labels (Fig. 3A, "Add Calcium Label", "Add Media Label", "Add Lumen Label", "Add "Feature/Class" Label" buttons on user interface 305).
Furthermore, regarding claim 14, Li further teaches wherein the labels indicate at least two of a stent, a lumen, and an external elastic membrane (see para. 0104 "Each region/feature corresponding to lumen L, intima I, plaque Q, adventitia ADV, imaging probe P, media M, and others may be generated by the MLS using a trained NN such as a CNN.").
Furthermore, regarding claim 15, Li further teaches wherein the labels further indicate at least one of a plaque, a thrombus, a hematoma, and a medical device (see para. 0104 "Each region/feature corresponding to lumen L, intima I, plaque Q, adventitia ADV, imaging probe P, media M, and others may be generated by the MLS using a trained NN such as a CNN.").
Furthermore, regarding claim 21, Ezhov further teaches wherein the computer model includes an output layer that calculates each of the respective probabilities using a sigmoid function as an activation function (see para. 0111 – “In one embodiment, a model of a probability distribution over anatomical structures via semantic segmentation may be performed: using a standard fully-convolutional network, such as VNet or 3D UNet, to transform IxHxWxD tensor of input image with I color channels per voxel, to HxWxDxC tensor defining class probabilities per voxel, where C is the number of possible classes (anatomical structures)…In case of a class overlap, a sigmoid activation function may be applied to each class in C independently.”).
The motivation for claims 2, 17, and 21 was shown previously in claims 1 and 16.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Li in view of Ezhov, as applied to claim 1 above, and in further view of Masood et al. (US 20140003701 A1, published January 2, 2014), hereinafter referred to as Masood.
Regarding claim 7, Li in view of Ezhov teaches all of the elements disclosed in claim 1 above.
Li in view of Ezhov teaches a single pixel can correspond to two or more of the predetermined regions that overlap, but does not explicitly teach comparing the respective probabilities with thresholds to determine the predetermined regions.
Whereas, Masood, in an analogous field of endeavor, teaches wherein the processor executes the program to compare the respective probabilities with thresholds to determine the predetermined regions (see para. 0109 – “According to the assignment of probabilities according to the present embodiment, a probability for each tissue type or class is assigned to each voxel, giving multiple probability values per voxel. Near the peak of each distribution, the probability for one class is much greater than for the other class [comparing respective probabilities with thresholds]. In the regions of overlap, the probability for each class will be similar.”).
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 a single pixel can correspond to two or more of the predetermined regions that overlap, as disclosed in Li in view of Ezhov, by also comparing the respective probabilities with thresholds to determine the predetermined regions, as disclosed in Masood. One of ordinary skill in the art would have been motivated to make this modification in order to provide a smoothing effect between the regions, as taught in Masood (see para. 0113).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Heindl et al. (US 20200167928 A1, published May 28, 2020) discloses an incorrect calculation for one pixel in an overlapping area may be at least partially mitigated by a correct calculation once the overlapping area is analyzed again.
Klingensmith et al. (US 20220370033 A1, published November 24, 2022) discloses a 1×1×1 convolution with a sigmoid activation function was used to reduce the final output of the U-net to a feature map with the same number of output channels as labels. The final shape of the output predictions from this U-Net architecture is 64×64×64×5, such that each 64×64×64 layer contains a probability map for each class for every voxel in the input volume. These models were trained with the same GPU-based system used to train the 2D multiclass U-net model.
Nikolov et al. (US 20200082534 A1, published March 12, 2020) discloses the segmentation neural network can generate a segmentation output which characterizes a single voxel as being highly likely to belong to both a “spinal cord” and a “spinal canal”.
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
/PASCAL M BUI PHO/Supervisory Patent Examiner, Art Unit 3798
Prosecution Insights