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 .
Acknowledgement of Amendment
The following office action is in response to the applicant’s amendment filed on 07/13/2026. Claims 1-14 are pending. Claim 11 is amended. Claims 1-14 are rejected under 35 U.S.C. 102/103 for the reasons stated in the Response to Arguments and 35 U.S.C. 102/103 sections below.
Response to Arguments
Applicant’s arguments, see Remarks page 10, filed 07/13/2026, with respect to the objections to the specification have been fully considered and are persuasive. The objections to the specification in the non-final rejection of 04/13/2026 have been withdrawn.
Applicant’s arguments, see Remarks page 10, filed 07/13/2026, with respect to the rejection of claims 11 and 12 under 35 U.S.C. 112(b) have been fully considered and are persuasive.
The examiner acknowledges that claim 11 has been amended to recite: “obtaining a training image sequence of successive training images that map or simulate a vascular structure, as well as the at least one medical device that is moving in the vascular structure, wherein the at least one medical device is introduced into the body of a patient at an orifice”. The examiner agrees that this amendment corrects the antecedent basis issue identified in the non-final rejection.
The rejection of claims 11 and 12 under 35 U.S.C. 112(b) in the non-final rejection of 04/13/2026 have been withdrawn.
Applicant’s arguments, see Remarks page 10-14, filed 07/13/2026, with respect to the rejection of the claims under 35 U.S.C. 101 have been fully considered and are persuasive.
Applicants first point to the 2025 memorandum published by the USPTO regarding software-related arts, including Artificial Intelligence (AI) and Machine Learning (ML), which states:
The courts consider a mental process (thinking) that “can be performed in the human mind, or by a human using a pen and paper, to be an abstract idea. The USPTO subject matter eligibility analysis follows this precedent and instructs examiners to determine that a claim recites a mental process when it contains limitation(s) that can practically be performed in the
human mind, including, for example, observations, evaluations, judgments,
and opinions. On the other hand, a claim does not recite a mental process when
it contains limitation(s) that cannot practically be performed in the human
mind, for instance when the human mind is not equipped to perform the claim
limitation(s).
The mental process grouping is not without limits. Examiners are reminded not to expand this grouping in a manner that encompasses claim limitations that cannot practically be performed in the human mind. The MPEP and the AI-SME Update provide examples of claim limitations that cannot be practically performed in the human mind. Claim limitations that encompass AI in a way that cannot be practically performed in the human mind do
not fall within this grouping. […]
Distinguishing claims that recite a judicial exception from claims that merely
involve a judicial exception: Examiners should be careful to distinguish
claims that recite an exception (which require further eligibility analysis)
from claims that merely involve an exception (which are eligible and do
not require further eligibility analysis).
Consider for example, the published USPTO examples 39, which illustrates claim limitations that merely involve an abstract idea, and 47, which shows limitations that recite an abstract idea. The claim limitation "training the neural network in a first stage using the first training set" of example 39 does not recite a judicial exception. Even though "training the neural network" involves a broad array of techniques and/or activities that may
involve or rely upon mathematical concepts, the limitation does not set forth or describe any
mathematical relationships, calculations, formulas, or equations using words or mathematical
symbols. Contrast this with the limitation "training, by the computer, the ANN based on the input data and a selected training algorithm to generate a trained ANN, wherein the selected
training algorithm includes a backpropagation algorithm and a gradient descent algorithm" of claim 2 of example 47. This limitation requires specific mathematical calculations by referring to the mathematical calculations by name, i.e., a backpropagation algorithm and a gradient descent algorithm, and therefore recites a judicial exception, namely an abstract idea.
See the August 4, 2025 Memorandum from Charles Kim, Deputy Commissioner for Patents, to Technology Centers 2100, 2600 and 3600 re: Reminders on evaluating subject matter eligibility of claims under 35 U.S.C. 101, pages 2 and 3 (hereinafter, "Memo"; emphasis added).
The examiner respectfully acknowledges that the August 4, 2025 Memorandum established that claim limitations that encompass AI in a way that cannot be practically performed in the human mind do not fall within the abstract idea grouping. Furthermore, even though “training the neural network” involves a broad array of techniques and/or activities that may involve or rely upon mathematical concepts, the limitation does not set forth or describe any mathematical relationships, calculations, formulas, or equations using words or mathematical symbols.
Regarding claims 1, 11, and 14, the Applicant notes that these claims recite a specific framework that determines a risk of an unexpected movement of at least one medical device during a vascular intervention by applying a trained machine learning model to input data that includes an image sequence of successive images that map a vascular structure and at least one medical device that is moving in the vascular structure. See, Applicants' originally filed specification, paras. [0017] and [0029]. The claimed limitations, specifically that determining the risk characteristic value includes applying a trained machine learning model to input data that contains the image sequence, are not merely directed to an abstract idea. As noted with regard to the Memo above, the claimed limitations may involve or rely upon mathematical concepts, but the claimed limitations "do not set forth or describe any mathematical relationships, calculations, formulas, or equations using words or mathematical symbols." Additionally, the claimed limitations cannot be practically performed in the human mind, e.g., by pen and paper, as applying a trained machine learning model is not associated with human activity. In other words, a human cannot apply a "trained machine learning model." Therefore, the claimed limitations go beyond "Mental Processes" or "Mathematical Concepts," and do not recite a judicial exception.
The examiner respectfully agrees that claims 1, 11 and 14 recite a specific framework that determines a risk of an unexpected movement of at least one medical device during a vascular intervention by applying a trained machine learning model to input data that includes an image sequence of successive images that map a vascular structure and at least one medical device that is moving in the vascular structure. Additionally, the examiner acknowledges that the claimed limitations, specifically that determining the risk characteristic value includes applying a trained machine learning model to input data that contains the image sequence, are not merely directed to an abstract idea. Furthermore, the examiner recognizes that while the claimed limitations may involve or rely upon mathematical concepts, these claimed limitations "do not set forth or describe any mathematical relationships, calculations, formulas, or equations using words or mathematical symbols”.
Even assuming arguendo the claimed limitations are directed to a judicial exception, which they are not, the claimed limitations integrate the alleged judicial exception into a practical application by providing a specific tool for assessing a risk of an unexpected movement of a medical device during a vascular intervention through an improved machine learning model. Specifically, the claimed limitations present a specific, concrete technical improvement in machine learning, such as a machine learning model processing not only items of information contained in individual images of an image sequence, but also a temporal order of images within the image sequence. See, para. [0022]. Additionally, the claimed limitations provide a technical improvement to the problem of inadvertent and uncontrolled movements inside the vascular structure caused by slippage of the medical device. See, para. [0005]. By using a trained machine learning model on an image sequence of successive images, a risk characteristic value for the risk of an unexpected correlation existing or being imminent between a causal movement and a resulting movement of the medical device is assessed. See, para. [0013]. The claimed limitations provide a framework that identifies a risk of an unexpected movement of a medical device during a vascular intervention that may perforate, rupture, or dissect a vessel. For example, "the risk of an unexpected movement of the at least one medical device may be monitored automatically and live during a vascular intervention, and such an unexpected movement may be avoided thereby." See, para. [0029].
For example, the claimed limitations enable the system to detect how high the risk is of an unexpected correlation existing or being imminent, not after perforation, rupture, or dissection has occurred, but through the specific computational arrangement associated with the targeted training of an untrained machine learning model. See, para. [0028]. This specific technical configuration solves a problem in vascular intervention. As such, the claimed limitations require improved machine learning model application, such that an individual or a robot may react accordingly in order to prevent a sudden sliding or the like of the medical device. See, para. [0029].
The examiner respectfully agrees that the claimed limitations integrate the alleged judicial exception into a practical application by providing a specific tool for assessing a risk of an unexpected movement of a medical device during a vascular intervention through an improved machine learning model. The examiner recognizes that the claimed limitations present a specific, concrete technical improvement in machine learning, such as a machine learning model processing not only items of information contained in individual images of an image sequence, but also a temporal order of images within the image sequence (see [0022] of Applicant’s specification).
Furthermore, the examiner acknowledges that the claimed limitations provide a technical improvement to the problem of inadvertent and uncontrolled movement inside the vascular structure caused by slippage of the medical device (see [0005] of Applicant’s specification). Additionally, by using a trained machine learning model on an image sequence of successive images, a risk characteristic value for the risk of an unexpected correlation existing or being imminent between a casual movement and a resulting movement of the medical device is assessed (see [0013] of Applicant’s specification). The examiner agrees that the claimed limitations provide a framework that identifies a risk of an unexpected movement of a medical device during a vascular intervention that may perforate, rupture, or dissect a vessel. For example, “the risk of an unexpected movement of the at least one medical device may be monitored automatically and live during a vascular intervention, and such an unexpected movement may be avoided thereby (see [0029] of Applicant’s specification).
The examiner recognizes that the claimed limitations enable the system to detect how high the risk is of an unexpected correlation existing or being imminent, not after perforation, rupture, or dissection has occurred, but through the specific computational arrangement associated with the targeted training of an untrained machine learning model (see [0028] of Applicant’s specification). The examiner agrees that this specific technical configuration solves a problem in vascular intervention and that the claimed limitations require improved machine learning model application, such that an individual or a robot may react accordingly in order to prevent a sudden sliding or the like of the medical device (See [0029] of Applicant’s specification).
Therefore, the rejection of claims 1-14 under 35 U.S.C. 101 in the non-final rejection of 04/13/2026 has been withdrawn.
Applicant’s arguments, see Remarks page 14-16, filed 07/13/2026, with respect to the rejection of the claims under 35 U.S.C. 102 and 35 U.S.C. 103 have been fully considered and are not persuasive.
Regarding claim 1, the claim recites “a computer-implemented method for assessing a risk of an unexpected movement of at least one medical device during a vascular intervention," the computer-implemented method including obtaining an image sequence of successive images that map a vascular structure and at least one medical device that is moving in the vascular structure”, and "determining a risk characteristic value for an unexpected correlation existing or being imminent between a causal movement of the at least one medical device at an end, proximal with respect to the orifice, of the at least one medical device and a resulting movement of the at least one medical device at an end, distal with respect to the orifice, of the at least one medical device”.
The Applicant argues that Sinha does not teach or disclose "a computer-implemented method for assessing a risk of an unexpected movement of at least one medical device during a vascular intervention" that includes determining a risk characteristic value for an unexpected correlation existing or being imminent between a causal movement of the at least one medical device at an end, proximal with respect to the orifice, of the at least one medical device and a resulting movement of the at least one medical device at an end, distal with respect to the orifice, of the at least one medical device," as recited by independent claim 1.
As shown in Figure 2, Sinha discloses a method for predictive motion mapping for flexible devices that includes training S210 artificial intelligence. See, paras. [0035] and [0036]. At S220, the method of Figure 2 includes identifying motion at a proximal end of an interventional medical device. See, para. [0042]. At S225, medical imagery of the interventional medical device is obtained. See, para. [0043]. The medical imagery obtained at S225 may be used to obtain at least one location of the distal end of the interventional medical device from images of the distal end of the interventional medical device. See, para. [0043]. At S230, trained first artificial intelligence is applied to the identified motion at the proximal end of the interventional medical device and the medical image of the distal end. See, para. [0045]. At S250, images of the interventional medical device are obtained from a medical imaging device. See, para. [0046]. At S257, actual motion is detected. See, para. [0048]. At S260, the detected actual motion of the interventional medical device is compared to predicted motion of the interventional medical device. See, para. [0049]. Sinha discloses determining whether the actual motion deviates from the predicted motion. See, para. [0050]. The determination is related to a current motion, not a future motion, as required by independent claim 1.
The examiner respectfully disagrees with the Applicant’s argument that Sinha does not teach or disclose "a computer-implemented method for assessing a risk of an unexpected movement of at least one medical device during a vascular intervention" that includes determining a risk characteristic value for an unexpected correlation existing or being imminent between a causal movement of the at least one medical device at an end, proximal with respect to the orifice, of the at least one medical device and a resulting movement of the at least one medical device at an end, distal with respect to the orifice, of the at least one medical device," as recited by independent claim 1.
The examiner acknowledges that Sinha discloses a method for predictive motion mapping for flexible devices that includes training S210 artificial intelligence (See FIG. 2: Steps S210-S250, S255, S257, S260, S270, S271, S280 and S281). The examiner respectfully agrees that Sinha discloses determining whether the actual motion deviates from the predicted motion. The examiner recognizes that this determination is related to a current motion.
However, the examiner does not agree with the Applicant’s argument that claim 1 requires a determination of a risk characteristic value which is related to future motion.
As written claim 1 recites: “determining a risk characteristic value for an unexpected correlation existing or being imminent because a causal movement of the at least one medical device at an end, proximal with respect to the orifice, of the at least one medical device and a resulting movement of the at least one medical device at an end, distal with respect to the orifice, of the at least one medical device”.
In this case, when it is determined, by Sinah, that actual motion deviates from the predicted motion, an unexpected correlation exists. The inclusion of the phrase “an unexpected correlation existing or being imminent” indicates that a prior art reference must satisfy either the first condition (i.e. unexpected correlation exists, corresponding to current motion) or the second condition (i.e. unexpected correlation is imminent, corresponding to future motion). The examiner respectfully asserts that Sinha satisfies the first condition (i.e. unexpected correlation exists) when it determines that actual motion deviates from the predicted motion.
Further, Sinha discloses a method to predict coarse localization of motion. Localization motion is "where unexpected behavior such as buckling outside of the fluoroscopy FOV may be occurring based on the disagreement between predicted and observed motion within the fluoroscopy FOV." See, para. [0032]. The coarse localization of motion is again related to a current motion, not a future motion, as required by independent claim 1. Sinha does not teach or disclose predicting the risk of a future movement. Accordingly, Sinha does not teach or disclose "a computer-implemented method for assessing a risk of an unexpected movement of at least one medical device during a vascular intervention" that includes determining a risk characteristic value for an unexpected correlation existing or being imminent between a causal movement of the at least one medical device at an end, proximal with respect to the orifice, of the at least one medical device and a resulting movement of the at least one medical device at an end, distal with respect to the orifice, of the at least one medical device," as recited by independent claim 1. Therefore, independent claim 1 is allowable over the cited prior art reference.
The examiner acknowledges that Sinha discloses a method to predict coarse localization of motion, which is “where unexpected behavior such as buckling outside of the fluoroscopy FOV may be occurring based on the disagreement between predicted and observed motion within the fluoroscopy FOV” (see Sinha: [0032]). The examiner agrees that the coarse localization of motion is related to a current motion.
As established above, the inclusion of the phrase “an unexpected correlation existing or being imminent” indicates that a prior art reference must satisfy either the first condition (i.e. unexpected correlation exists, corresponding to current motion) or the second condition (i.e. unexpected correlation is imminent, corresponding to future motion).
While Sinah may not satisfy the second condition (i.e. unexpected correlation is imminent, corresponding to future motion), the examiner respectfully maintains that Sinah satisfies the first condition (i.e. unexpected correlation exists, corresponding to current motion) because Sinah determines that actual motion deviates from the predicted motion (See FIG. 2).
Thus, the examiner respectfully maintains that Sinah teaches the limitations of claim 1 for the reasons stated in the Response to Arguments section above and the 35 U.S.C. 102 section below.
Therefore, the rejection of claim 1 and its corresponding dependent claims (i.e. claims 2-10 and 13) under 35 U.S.C. 102 and 35 U.S.C. 103 are respectfully maintained (see the 35 U.S.C. 102 and 35 U.S.C. 103 sections below).
Regarding claims 11 and 14, the examiner acknowledges that these claims include features consistent with those discussed above for claim 1. Therefore, these claims are subject to the reasoning provided therein.
Thus, the examiner respectfully maintains the rejection of claims 11 and 14 along with their corresponding dependent claims (i.e. claim 12) under 35 U.S.C. 102 for the reasons stated in the Response to Arguments section above and the 35 U.S.C. 102 section below.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-3, and 8-14 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Sinha et al. US 2024/0045404 A1 “Sinha”.
Regarding claims 1 and 14, Sinha teaches “A computer-implemented method for assessing a risk of an unexpected movement of at least one medical device during a vascular intervention, the computer-implemented method comprising:” (Claim 1) (See steps S210-S28 in FIG. 2 and “FIG. 2 illustrates a method for predictive motion mapping for flexible devices, in accordance with a representative embodiment” [0035]; “At S210, the method of FIG. 2 starts by training artificial intelligence” [0036]; “Embodiments based on FIG. 2 include obtaining images of the distal end of the interventional medical device before S230, such as when segmented representations of the interventional medical device are used as inputs to the first artificial intelligence applied at S230” [0043]. Therefore, since the method shown in FIG. 2 involves training an artificial intelligence (i.e. model) and applying/inputting obtained images into the first artificial intelligence (i.e. model), the method of FIG. 2 represents a computer-implemented method for assessing a risk of an unexpected movement (i.e. actual motion deviates from predicted motion, see step S270) of at least one medical device (i.e. interventional medical device 101, see FIG. 1) during a vascular intervention (see [0034] below).).
“A data processing system comprising: a processor configured to assess a risk of an unexpected movement of at least one medical device during a vascular intervention, the processor being configured to assess the risk of the unexpected movement of the at least one medical device during the vascular intervention comprising the processor being configured to:” (Claim 14) (See steps S230-S281 of FIG. 2 and “FIG. 1 illustrates a system for predictive motion mapping for flexible devices, in accordance with a representative embodiment” [0022]; “In FIG. 1, a control system 100 is shown along with an interventional medical device 101. […] The distal end D may correspond to a portion of the interventional medical device 101 that is first inserted into the anatomy of a patient in an interventional medical procedure” [0023]; “The control system 100 includes a medical imaging system 120, a motion detector 130, a workstation 140, a robot 160, and an artificial intelligence controller 180. The workstation 140 includes a controller 150, an interface 153, a monitor 155 and a touch panel 156. The controller 150 includes a memory 151 that stores instructions and a processor 152 that executes the instructions. The interface 153 interfaces the monitor 155 to a main body of the workstation 140. The artificial intelligence controller 180 includes a memory 181 that stores instructions and a processor 182 that executes the instructions to implement one or more aspects of methods described herein” [0024]; “The control system 100 may be used for various fluoroscopy-based interventional medical procedures, including but not limited to interventional vascular procedures” [0034].
Therefore, Sinha discloses a data processing system (i.e. system 100) comprising: a processor (i.e. processors 152, 158) configured to assess a risk of an unexpected movement of at least one medical device during a vascular intervention (i.e. see [0034]), the processor being configured to assess the risk of the unexpected movement (i.e. actual motion deviates from predicted motion, see step S270) of the at least one medical device (i.e. interventional medical device 101, see FIG. 1) during the vascular intervention i.e. see [0034]) comprising the processor being configured to perform method steps (i.e. see steps of FIG. 2).);
“obtain(ing) an image sequence of successive images that map a vascular structure and at least one medical device that is moving in the vascular structure, wherein the at least one medical device is introduced into the body of a patient at an orifice” (Claims 1 and 14) (See [0034] above and “At S225, the method of FIG. 2 includes obtaining medical imagery of the interventional medical device. The medical imagery obtained at S225 may be obtained by the medical imaging system 120. The medical imagery obtained at S225 may be used to obtain at least one location of the distal end of the interventional medical device 101 from images of the distal end of the interventional medical device 101. The medical imagery may be fluoroscopy images of the part of the interventional medical device within the field of view of the medical imaging system. The medical imagery obtained at S225 is of part of the interventional medical device towards the distal end” [0043]. Therefore, the method carried out by the system involves obtaining an image sequence (i.e. fluoroscopy images) or successive images that map a vascular structure and at least one medical device (i.e. interventional medical device 101, see FIG. 1) that is moving in the vascular structure, wherein the at least one medical device is introduced into the body of a patient at an orifice.); and
“determine(ing) a risk characteristic value for an unexpected correlation existing or being imminent between a causal movement of the at least one medical device at an end, proximal with respect to the orifice, of the at least one medical device and a resulting movement of the at least one medical device at an end, distal with respect to the orifice, of the at least one medical device” (Claims 1 and 14) (“At S240, the first artificial intelligence predicts motion along the interventional medical device towards the distal end based on the motion identified at the proximal end of the interventional medical device 101 at S220 and images of the interventional medical device toward the distal end at S225. The first artificial intelligence may be implemented by receiving fluoroscopy images of a segmented representation of the interventional medical device covering images of the interventional medical device 101 initially without unexpected/unintended behavior such as buckling at S225” [0045]; “At S250, the method of FIG. 2 includes obtaining images of the interventional medical device from a medical imaging system. The images of the interventional medical device obtained at S250 may be images of the distal end of the interventional medical device and/or towards the distal end of the interventional medical device” [0046]; “At S255, the method of FIG. 2 includes segmenting the interventional medical device in the images from the medical imaging system” [0047]; “At S257, actual motion is detected from the images from the medical imaging system” [0048]; “At S260, the detected actual motion of the interventional medical device is compared to predicted motion of the interventional medical device” [0049]; “At S270, a determination is made whether the actual motion deviates from the predicted motion. The deviation may be identified from a binary classification process, or may be based on one or more thresholds, scoring algorithms, or other processes that determine whether the actual motion of the interventional medical device is within expectations from the predicted motion” [0050]; “If the actual motion deviates from the predicted motion (S270=Yes), an alarm is generated at S280” [0051].
Therefore, since the method includes predicting motion along interventional medical device towards the distal end and obtains images to determine actual motion such that it can be determined whether actual motion deviates from predicted motion (i.e. triggering alarm generation, see S280), the method involves determining a risk characteristic value for an unexpected correlation (i.e. deviation from actual motion) existing or being imminent between a causal movement of the at least one medical device at an end, proximal with respect to the orifice, of the at least one medical device and a resulting movement of the at least one medical device at an end, distal with respect to the orifice, of the at least one medical device.);
“wherein determining the risk characteristic value includes applying a trained machine learning model to input data that contains the image sequence” (Claim 1); “wherein the determination of the risk characteristic value includes application of a trained machine learning model to input data that contains the image sequence” (Claim 14) (See steps S230-S281 in FIG. 2 and “Additionally, at S271, the method of FIG. 2 includes predicting the coarse localization of motion along the interventional medical device outside the field of view of the images from the interventional medical device. Additionally, the second artificial intelligence may predict a predicted confidence in the predicted coarse localization. The coarse localization predicted at S271 may be predicted by the second artificial intelligence described herein. The second artificial intelligence may be implemented by the artificial intelligence controller 180, and implements a localization neural network” [0052]. As shown in step S230, specifically a trained first artificial intelligence (i.e. model) is applied to the obtained images. Furthermore, step S271 involves utilizing a second artificial intelligence model. Therefore, the step of determining the risk characteristic value includes applying a trained machine learning model in input data that contains the image sequence.).
Regarding claim 2, Sinha discloses all features of the claimed invention as discussed with respect to claim 1 above, and Sinha further teaches “wherein the input data includes metadata that includes patient properties of the patient, device properties of the at least one medical device, intervention data relating to a previous course of the vascular intervention, or any combination thereof” (“In still another embodiment, an endovascular robotic system measures the force being applied at the tip of a catheter to either display the measurements of force on the console or incorporate the measurements of force into the control loop. This feature may alert the clinician to the danger of continued force and, therefore, decrease the likelihood of perforation or other damage to the vessel wall” [0106]. Therefore, since the force being applied at the tip of a catheter (i.e. feed force) is measured and incorporated into the control loop (i.e. trained machine learning model/first artificial intelligence/first neural network), the input data includes metadata that includes intervention data relating to a previous course of the vascular intervention.).
Regarding claim 3, Sinha discloses all features of the claimed invention as discussed with respect to claim 2 above, and Sinha further teaches “wherein the intervention data includes a length of a part, located in the body during generation of the image sequence, of the at least one medical device, data relating to a feed force or pulling force applied to the at least one medical device during generation of the image sequence or a torque applied to the at least one medical device during generation of the image sequence, or a combination thereof” (See [0106] as discussed in claim 2 above. Therefore, since the force being applied at the tip of a catheter (i.e. feed force) is measured and incorporated into the control loop (i.e. trained machine learning model/first artificial intelligence/first neural network), the intervention data includes data relating to a feed force or pulling force applied to the at least one medical device (i.e. interventional medical device 101) during generation of the image sequence.).
Regarding claim 8, Sinha discloses all features of the claimed invention as discussed with respect to claim 1 above, and Sinha further teaches “wherein a nominal correlation between the causal movement and the resulting movement is a linear correlation, and wherein the unexpected correlation between the causal movement and the resulting movement corresponds to a correlation that deviates from the nominal correlation by more than a predefined tolerance” (See [0050] as discussed in claim 1 above. Therefore, since deviation between the actual motion and predicted motion may be identified from a binary classification process or based on one or more thresholds/scoring algorithms or other processes, this deviation identification involves a nominal correlation between the causal movement (i.e. predicted motion) and the resulting movement (i.e. actual motion) which is a linear correlation. Furthermore, the unexpected correlation between the casual movement (i.e. predicted motion) and the resulting movement (i.e. actual motion) corresponds to a correlation at deviated from the nominal correlation by more than a predefined tolerance (i.e. threshold).).
Regarding claim 9, Sinha discloses all features of the claimed invention as discussed with respect to claim 1 above, and Sinha further teaches “wherein the at least one medical device includes one or more vessel catheters, one or more guide wires, or the one or more vessel catheters and the one or more guide wires” (“Accordingly, characteristics of the interventional medical device 101 may be used as a basis or one of multiple bases of compensating for the unintended motion. Examples of an interventional medical device 101 include a guidewire, a catheter, a microcatheter and a sheath” [0025]. Therefore, the at least one medical device includes one or more vessel catheters, one or more guide wires, or the one or more vessel catheters and the one or more guide wires.).
Regarding claim 10, Sinha discloses all features of the claimed invention as discussed with respect to claim 1 above, and Sinha further teaches “further comprising: generating a user output; and outputting the user output as a function of the risk characteristic value” (See [0051] as disclosed in claim 1 above and “The training data may contain only normal or expected motion at the distal ends of the multiple different interventional medical devices, so that the artificial intelligence will learn to predict the normal motion at the distal ends of the different interventional medical devices, and during inference, if subsequent observed motion is not similar to predicted normal motion so that an alarm or alert can be generated and issued” [0039]. Therefore, the method further comprises generating a user output (i.e. alarm or alert); and outputting the user output as a function of the risk characteristic value.).
Regarding claim 11, Sinha teaches “A computer-implemented training method for supplying a trained machine learning model for use in a computer-implemented method for assessing a risk of an unexpected movement of at least one medical device during a vascular intervention, the computer- implemented training method comprising:” (“FIG. 3 illustrates another method for predictive motion mapping for flexible devices, in accordance with another representative embodiment” [0008]; “At S330, first artificial intelligence is trained to predict motion along the interventional medical device towards the distal end” [0058], “At S380, the method of FIG. 3 includes determining a loss function based on the difference between the predicted motion and the actual motion toward the distal end of the interventional medical device” [0061]; “At S385, the first neural network is updated based on the determined loss function, and the process returns to S330” [0062]. Thus, since the method shown in FIG. 3 includes a step of training a first artificial intelligence (i.e. model), the method of FIG. 3 represents a computer-implemented training method for supplying a trained machine learning model for use in a computer-implemented method for assessing a risk of an unexpected movement (i.e. difference between predicted motion and actual motion, see [0061]) of at least one medical device (i.e. interventional medical device) during a vascular intervention (See [0034] as discussed in claim 1 above.).);
“obtaining a machine learning model in an untrained or partially trained state” (See FIG. 3, steps S330 and S385. In this case, in order to perform the steps of training first artificial intelligence to predict motion along interventional medical device towards distal end and update the first neural network (i.e. step S385) the method must first perform the step of obtaining a machine learning model in an untrained or partially trained state.);
“obtaining a training image sequence of successive training images that map or simulate a vascular structure, as well as at least one device that is moving in the vascular structure, wherein the at least one medical device is introduced into the body of a patient at an orifice” (“At S320, at least one location of the distal ends of the interventional medical device is detected” [0057]; “At S225, the method of FIG. 2 includes obtaining medical imagery of the interventional medical device. The medical imagery obtained at S225 may be obtained by the medical imaging system 120. The medical imagery obtained at S225 may be used to obtain at least one location of the distal end of the interventional medical device 101 from images of the distal end of the interventional medical device 101” [0043]. Therefore, since step S320 involves detecting the interventional medical device and medical imagery can be used to obtain at least one location of the distal end of the interventional medical device (see step S225), the method involves obtaining a training image sequence of successive training images that map or simulate a vascular structure, as well as at least one device (i.e. interventional medical device 101) that is moving in the vascular structure (i.e. see [0034]), wherein the at least one medical device is introduced into the body of a patient at an orifice.);
“determining a training risk characteristic value for an unexpected correlation existing or being imminent between a causal movement of the at least one medical device at an end, proximal with respect to the orifice, of the at least one medical device and a resulting movement at an end, distal with respect to the orifice, of the at least one medical device, wherein determining the training risk characteristic value comprises applying the machine learning model to training input data that contains the image sequence” (See [0061] above and “At S330, first artificial intelligence is trained to predict motion along the interventional medical device towards the distal end” [0058]; “At S360, motion along the interventional medical device towards the distal end is predicted based on the motion at the proximal end and the medical image of the distal end of the interventional medical device prior to application of motion at the proximal end of the interventional medical device” [0059]; “At S370, actual motion along the interventional medical device towards the distal end is detected. The actual motion is detected from a medical image of or a segmented representation of the part of the interventional medical device within the field of view of the medical imaging system” [0060]. Therefore, the method involves determining a training risk characteristic value for an unexpected correlation (i.e. difference between predicted motion and actual motion, see [0061]) existing or being imminent between a causal movement (i.e. predicted motion) of the at least one medical device (i.e. interventional medical device 101) at an end, proximal with respect to the orifice, of the at least one medical device and a resulting movement (i.e. actual motion) at an end, distal with respect to the orifice, of the at least one medical device, wherein determining the training risk characteristic value comprises applying the machine learning model (i.e. first artificial intelligence) to training input data that contains the image sequence (i.e. data from step S320).);
“evaluating a predefined loss function as a function of the training risk characteristic value and a predefined ground truth value for the training image sequence” (See [0061] above and “The predicted and observed (ground truth) motions are compared by computing a loss function such as mean square error, or mean absolute error, or Huber loss, or any loss that calculates difference between two motion vectors (R.sup.2, R.sup.3), for instance geodesic loss” [0041]. Therefore, the method involves evaluating a predefined loss function as a function of the training risk characteristic value and a predefined ground truth value (see [0041]) for the training image sequence.); and
“updating the machine learning model as a function of a result of the evaluating of the predefined loss function” (See [0062] above. Therefore, the method involves updating the machine learning model (i.e. first neural network) as a function of a result of the evaluating of the predefined loss function.).
Regarding claim 12, Sinha discloses all features of the claimed invention as discussed with respect to claim 11 above, and Sinha further teaches “wherein the training input data includes training metadata that includes patient properties, device properties of the at least one medical device, intervention data, or any combination thereof” (“In still another embodiment, an endovascular robotic system measures the force being applied at the tip of a catheter to either display the measurements of force on the console or incorporate the measurements of force into the control loop. This feature may alert the clinician to the danger of continued force and, therefore, decrease the likelihood of perforation or other damage to the vessel wall” [0106]. Therefore, since the force being applied at the tip of a catheter (i.e. feed force) is measured and incorporated into the control loop (i.e. trained machine learning model/first artificial intelligence/first neural network), the training input data includes training metadata that includes intervention data.).
Regarding claim 13, Sinha discloses all features of the claimed invention as discussed with respect to claim 1 above, and Sinha further teaches “further comprising training the machine learning model, the training of the machine learning model comprising:” (See FIG. 3. Therefore, the computer-implemented method further comprises training the machine learning model (i.e. first neural network).);
“obtaining a machine learning model in an untrained or partially trained state” (See FIG. 3, steps S330 and S385. In this case, in order to perform the steps of training first artificial intelligence to predict motion along interventional medical device towards distal end and update the first neural network (i.e. step S385) the method must first perform the step of obtaining a machine learning model in an untrained or partially trained state.);
“obtaining a training image sequence of successive training images that map or simulate a vascular structure, as well as at least one device that is moving in the vascular structure, wherein the at least one medical device is introduced into the body of a patient at an orifice” (“At S320, at least one location of the distal ends of the interventional medical device is detected” [0057]; “At S225, the method of FIG. 2 includes obtaining medical imagery of the interventional medical device. The medical imagery obtained at S225 may be obtained by the medical imaging system 120. The medical imagery obtained at S225 may be used to obtain at least one location of the distal end of the interventional medical device 101 from images of the distal end of the interventional medical device 101” [0043]. Therefore, since step S320 involves detecting the interventional medical device and medical imagery can be used to obtain at least one location of the distal end of the interventional medical device (see step S225), the method involves obtaining a training image sequence of successive training images that map or simulate a vascular structure, as well as at least one device (i.e. interventional medical device 101) that is moving in the vascular structure (i.e. see [0034]), wherein the at least one medical device is introduced into the body of a patient at an orifice.);
“determining a training risk characteristic value for an unexpected correlation existing or being imminent between a causal movement of the at least one medical device at an end, proximal with respect to the orifice, of the at least one medical device and a resulting movement at an end, distal with respect to the orifice, of the at least one medical device, wherein determining the training risk characteristic value comprises applying the machine learning model to training input data that contains the image sequence” (See [0061] above and “At S330, first artificial intelligence is trained to predict motion along the interventional medical device towards the distal end” [0058]; “At S360, motion along the interventional medical device towards the distal end is predicted based on the motion at the proximal end and the medical image of the distal end of the interventional medical device prior to application of motion at the proximal end of the interventional medical device” [0059]; “At S370, actual motion along the interventional medical device towards the distal end is detected. The actual motion is detected from a medical image of or a segmented representation of the part of the interventional medical device within the field of view of the medical imaging system” [0060]. Therefore, the method involves determining a training risk characteristic value for an unexpected correlation (i.e. difference between predicted motion and actual motion, see [0061]) existing or being imminent between a causal movement (i.e. predicted motion) of the at least one medical device (i.e. interventional medical device 101) at an end, proximal with respect to the orifice, of the at least one medical device and a resulting movement (i.e. actual motion) at an end, distal with respect to the orifice, of the at least one medical device, wherein determining the training risk characteristic value comprises applying the machine learning model (i.e. first artificial intelligence) to training input data that contains the image sequence (i.e. data from step S320).);
“evaluating a predefined loss function as a function of the training risk characteristic value and a predefined ground truth value for the training image sequence” (See [0061] above and “The predicted and observed (ground truth) motions are compared by computing a loss function such as mean square error, or mean absolute error, or Huber loss, or any loss that calculates difference between two motion vectors (R.sup.2, R.sup.3), for instance geodesic loss” [0041]. Therefore, the method involves evaluating a predefined loss function as a function of the training risk characteristic value and a predefined ground truth value (see [0041]) for the training image sequence.); and
“updating the machine learning model as a function of a result of the evaluating of the predefined loss function” (See [0062] above. Therefore, the method involves updating the machine learning model (i.e. first neural network) as a function of a result of the evaluating of the predefined loss function.).
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.
Claim(s) 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sinha et al. US 2024/0045404 A1 “Sinha” as applied to claim 2 above, and further in view of Silverstein et al. WO 2012/0088535 A1 “Silverstein”.
Regarding claim 4, Sinha discloses all features of the claimed invention as discussed with respect to claim 2 above. However, Sinha does not teach “wherein: the device properties include an elasticity, a rigidity, a surface quality, or any combination thereof of the at least one medical device; the at least one medical device includes a first medical device and a second medical device, and the device properties include data relating to an arrangement of the first medical device and of the second medical device with respect to one another; or any combination thereof”.
Silverstein is within a related field of endeavor to the claimed invention because it involves a system, device and method to guide a rigid instrument within a patient’s body (see [Title] and [Abstract]).
Silverstein teaches “wherein: the device properties include an elasticity, a rigidity, a surface quality, or any combination thereof of the at least one medical device;” (“In FIG. 50, a rigid medical device 2110 is being tracked in a patient's body 2114, and concurrently, another rigid medical device 2112 is also being tracked in the patient' s body. In such embodiments, a particular target area can be envisioned by a medical practitioner and multiple methods of diagnosis or therapy can be employed to provide care to the patient” [000272]. In this case, the rigid medical devices “can be straight, curved, spiraled, or may be another shape” [000217]. Therefore, since rigid medical devices are tracked within the patient, these rigid medical devices possess device properties including a rigidity of the at least one medical device.);
“the at least one medical device includes a first medical device and a second medical device, and the device properties include data relating to an arrangement of the first medical device and of the second medical device with respect to one another; or any combination thereof” (See [000272] above and FIG. 50. As shown in FIG. 50, the rigid medical device 2110 and 2112 are positioned within the patient’s body 214 and their distal tips are arranged at approximately the same location. Therefore, since the rigid medical devices 2110 and 2112 are both tracked, the arrangement between the two is readily apparent. This, the at least one medical device include a first medical device and a second medical device and the device properties include data relating to an arrangement of the first medical device and of the second medical device with respect to one another.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the computer-implemented method such that the device properties include an elasticity, a rigidity, a surface quality or any combination thereof (i.e. rigidity) of the at least one medical device; the at least one medical device including a first medical device and a second medical device, and the device properties including data relating to an arrangement of the first medical device and of the second medical device with respect to one another as disclosed in Silverstein in order to easily track and observe the position of multiple medical devices within a patient when performing a procedure. Utilizing multiple rigid medical devices is one of a finite number of techniques which can be used to perform a procedure within a patient with a reasonable expectation of success. Thus, modifying the computer-implemented method such that the device properties include an elasticity, a rigidity, a surface quality or any combination thereof (i.e. rigidity) of the at least one medical device; the at least one medical device including a first medical device and a second medical device, and the device properties including data relating to an arrangement of the first medical device and of the second medical device with respect to one another as disclosed in Silverstein would yield the predictable result of easily tracking and observing the position of multiple medical devices within a patient when performing a procedure.
Claim(s) 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sinha et al. US 2024/0045404 A1 “Sinha” as applied to claim 2 above, and further in view of Kunio et al. US 2022/0346885 A1 “Kunio”.
Regarding claim 5, Sinha discloses all features of the claimed invention as discussed with respect to claim 2 above. Although Sinha discloses “The first artificial intelligence may be a neural network such as a convolutional neural network, encoder-decoder network, generative adversarial network, capsule network, regression network, reinforcement learning agent” [0041], “The second artificial intelligence may be implemented by a trained neural network such as a convolutional neural network, encoder-decoder network, generative adversarial network, capsule network, regression network, reinforcement learning agent” [0053].
However, Sinha does not teach “wherein the trained machine learning model includes a recurrent convolutional neural network”.
Kunio is within the same field of endeavor as the claimed invention because it involves an intravascular imaging system with a catheter for insertion into a blood vessel of a patient (see [0088]) and utilizes a deep (recurrent) convolutional neural network (see [0173]).
Kunio teaches “wherein the trained machine learning model includes a recurrent convolutional neural network” (“One or more embodiments of the present disclosure may automatically detect (predict a spatial location of) a radiodense OCT marker in a time series of X-ray images to co-register the X-ray images with the corresponding OCT images (at least one example of a reference point of two different coordinate systems). One or more embodiments may use deep (recurrent) convolutional neural network(s), which may improve marker detection and image co-registration significantly” [0173]; “(v) insert an intravascular imaging catheter that has a marker or radiopaque marker into an object or sample; and/or (vi) acquire or receive the angiography image data during a pullback operation of the intravascular imaging catheter” [Claim 11]. Therefore, one or more embodiments may use deep (recurrent) convolutional neural network(s) to improve marker detection, said marker being attached to an intravascular imaging catheter. Therefore, the trained machine learning model includes a recurrent convolutional neural network.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the computer-implemented method of Sinha such that the trained machine learning model includes a recurrent convolutional neural network as disclosed in Kunio in order to improve marker detection and thus the detection of at least one medical device (i.e. intravascular imaging catheter, see Claim 11). A (deep) recurrent convolutional neural network is one of a finite number of neural networks which can be used analyze images and identify features included therein with a reasonable expectation of success. Thus, modifying the computer-implemented method of Sinha such that the trained machine learning model includes a recurrent convolutional neural network as disclosed in Kunio would yield the predictable result of improving marker detection and thus the detection of at least one medical device (i.e. intravascular imaging catheter, see Claim 11).
Claim(s) 6-7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sinha et al. US 2024/0045404 A1 “Sinha” and Kunio et al. US 2022/0346885 A1 “Kunio” as applied to claim 5 above, and further in view of Jaganathan et al. US 2020/0302297 A1 “Jaganathan”.
Regarding claim 6, Sinha in view of Kunio discloses all features of the claimed invention as discussed with respect to claim 5 above, however, Sinha in view of Kunio does not teach “further comprising: converting the image sequence into a sequence of feature sets, the converting comprising applying a convolution module of the recurrent convolutional neural network to the image sequence; and generating a shared feature set, the generating comprising applying a recurrence module of the recurrent convolutional neural network to the sequence of feature sets; wherein determining the risk characteristic value comprises predicting the risk characteristic value as a function of the shared feature set by a prediction module of the recurrent convolutional neural network”.
Jaganathan is within a related field of endeavor to the claimed invention because it involves a hybrid neural network featuring a convolution module and a recurrent module (See [0453]).
Jaganathan teaches “further comprising: converting the image sequence into a sequence of feature sets, the converting comprising applying a convolution module of the recurrent convolutional neural network to the image sequence” (“FIG. 31a depicts one implementation of a hybrid neural network 3100a that is used as the neural network-based base caller 218. The hybrid neural network 3100a comprises at least one convolution module 3104 (or convolutional neural network (CNN)) and at least one recurrent module 3108 (or recurrent neural network (RNN)). “The recurrent module 3108 uses and/or receives inputs from the convolution module 3104” [0453]; “The convolution module 3104 processes input data 3102 through one or more convolution layers and produces convolution output 3106. In one implementation, the input data 3102 includes only image channels or image data as the main input, as discussed above in the Section entitled “Input”. The image data fed to the hybrid neural network 3100a can be the same as the image data 202 described above” [0454]. As shown in FIG. 31A, input data (i.e. image data, distance data, and scaling data) is input to the convolution module to produce a convolution output 3106. Therefore, the method further comprises converting the image sequence (i.e. image data) into a sequence of feature sets (i.e. included within the convolution output 3106), the converting comprising applying a convolution module of the recurrent convolutional neural network (i.e. CNN-RNN-based hybrid neural network) to the image sequence (i.e. image data).).; and
“generating a shared feature set, the generating comprising applying a recurrence module of the recurrent convolutional neural network to the sequence of feature sets” (“The recurrent module 3110 convolves the convolved output 3106 and produces recurrent output 3110. In particular, the recurrent module 3110 produces current hidden state representations (i.e., the recurrent output 3110) based on convolving the convolved representations and previous hidden state representations” [0458]. As shown in FIG. 31A, the recurrent module 3108 receives the convolution output 3106 and utilizes it to form a recurrent output 3110. Therefore, the method involves generating a shared feature set (i.e. recurrent output 3110), the generating comprising applying a recurrence module of the recurrent convolutional neural network (i.e. CNN-RNN-based hybrid neural network) to the sequence of feature sets.);
“wherein determining the risk characteristic value comprises predicting the risk characteristic value as a function of the shared feature set by a prediction module of the recurrent convolutional neural network” (“An output module 3112 then produces base calls 3114 based on the recurrent output 3110. In some implementations, the output module 3112 comprises one or more fully-connected layers and a classification layer (e.g., softmax). In such implementations, the current hidden state representations are processed through the fully-connected layers and the outputs of the fully-connected layers are processed through the classification layer to produce the base calls 3114” [0461]. In this case, since the output module 3112 receives the recurrent output 3110 it represents a prediction module. Therefore, the step of determining the risk characteristic value comprises predicting the risk characteristic value as a function of the shared feature set by a prediction module (i.e. output module 3112) of the recurrent convolutional neural network (i.e. CNN-RNN-based hybrid neural network).).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method of Sinha in view of Kunio such that it further includes converting the image sequence into a sequence of feature sets, the converting comprising applying a convolution module of the recurrent convolutional neural network to the image sequence; and generating a shared feature set, the generating comprising applying a recurrence module of the recurrent convolutional neural network to the sequence of feature sets; wherein determining the risk characteristic value comprises predicting the risk characteristic value as a function of the shared feature set by a prediction module of the recurrent convolutional neural network as disclosed in Jaganathan in order to effectively process the input data. A hybrid neural network featuring a convolution module and a recurrent module is one of a finite number of neural network configurations which can be used to effectively process image data with a reasonable expectation of success. Thus, modifying the method of Sinha in view of Kunio such that it further includes converting the image sequence into a sequence of feature sets, the converting comprising applying a convolution module of the recurrent convolutional neural network to the image sequence; and generating a shared feature set, the generating comprising applying a recurrence module of the recurrent convolutional neural network to the sequence of feature sets; wherein determining the risk characteristic value comprises predicting the risk characteristic value as a function of the shared feature set by a prediction module of the recurrent convolutional neural network as disclosed in Jaganathan would yield the predictable result of effectively processing the input data.
Regarding claim 7, Sinha in view of Kunio and Jaganathan discloses all features of the claimed invention as discussed with respect to claim 6 above, and Jaganathan further teaches “further comprising generating a supplemented feature set, the generating of the supplemented feature set comprising combining the shared feature set and the metadata, wherein predicting the risk characteristic value comprises applying the prediction module to the supplemented feature set” (“Tile data for a sensing cycle as described herein can comprise an array of sensor data having one or more features. For example, the sensor data can comprise two images which are analyzed to identify one of four bases at a base position in a genetic sequence of DNA, RNA, or other genetic material. The tile data can also include metadata about the images and the sensors. For example, in embodiments of the base calling operation, the tile data can comprise information about alignment of the images with the clusters such as distance from center information indicating the distance of each pixel in the array of sensor data from the center of a cluster of genetic material on the tile” [0644]. In this case, the tile data represents a supplemental feature set since it contains images and metadata. Thus, the method further comprises generating a supplemented feature set, the generating of the supplemented feature set comprising combining the shared feature set and the metadata, wherein predicting the risk characteristic value (i.e. performing base calling with the CNN-RNN-based hybrid neural network) comprises applying the prediction module to the supplemented feature set (i.e. tile data).).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method of Sinha in view of Kunio such that it further includes generating a supplemented feature set, the generating of the supplemented feature set comprising combining the shared feature set and the metadata, wherein predicting the risk characteristic value comprises applying the prediction module to the supplemented feature set as disclosed in Jaganathan in order to effectively process the input data. Generating a supplemental feature set by combining the shared feature set and the metadata (i.e. tile data) is one of a finite number of techniques which can be used to process image data with a reasonable expectation of success. Thus, modifying the method of Sinha in view of Kunio such that it further includes generating a supplemented feature set, the generating of the supplemented feature set comprising combining the shared feature set and the metadata, wherein predicting the risk characteristic value comprises applying the prediction module to the supplemented feature set as disclosed in Jaganathan in order to effectively process the input data
Conclusion
THIS ACTION IS MADE FINAL. 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 KAITLYN E SEBASTIAN whose telephone number is (571)272-6190. The examiner can normally be reached Mon.- Fri. 7:30-4:30 (Alternate Fridays Off).
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, Anne M Kozak can be reached at (571) 270-0552. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/KAITLYN E SEBASTIAN/Examiner, Art Unit 3797
Prosecution Insights