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 .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 3/9/2026 and 11/21/2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
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) 1-12, 14, 17-23 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Zhang, Ling et al. “Spatial-Temporal Convolutional LSTMs for Tumor Growth Prediction by Learning 4D Longitudinal Patient Data.” ArXiv abs/1902.08716 (2019): n. pag..
Regarding claim 1, Zhang et. al. discloses a computer-implemented method for training a machine-learning model, wherein the method comprises (Zhang et. al., the training of the “ST-ConvLSTM network” disclosed in section III.B(1) on page 1119.):
receiving training data:
wherein the training data comprise representations TR1 to TRn of an examination region for a multiplicity of examination objects, where n is an integer greater than two,
wherein each representation TR, represents the examination region in one state Z, of a sequence of states Zi to Zn, where i is an index passing through the integers from 1 to n, and
wherein each examination object is preferably a human and the examination region is preferably part of the human; (Zhang et. al. see “Our 4D longitudinal tumor imaging data set used in this study consists of dual-phase contrast-enhanced CT volumes at three time points for each patient” and “The dataset is prepared for every tumor volume at each time point, and imaging volumes at different times” in section III.A (pages 1116 and 1117), “Each patient has at least three time points (Eleven of these patients have the 4th time points) of dual-phase contrast-enhanced CT imaging, with the time interval of 398 plus or minus 90 days” in the second sentence of section IV.A (page 1119) and “We train our ST-ConvLSTM models for 5 epochs with the batch size of 16. Each data point has 5 slices at three time points” in section IV.B(1))
training the machine-learning model; (Zhang et. al. the text from section III.B(1) on page 1119 discloses the training of the “ST-ConvLSTM network”.)
wherein the model is trained to generate, starting from the representation TR1, representations TR2* to TRn* one after the other for each examination object of the multiplicity of examination objects,
wherein the representation TR2* is generated at least partly on the basis of the
representation TR1 and each further representation is generated at least partly on the basis of the respective previously generated representation TRk-1*, where k is an index passing through the numbers from 3 to n, and
wherein the representation TRk* represents the examination region in the state Zk and the representation TR.1 * represents the examination region in the state Zk.1, and the state Zk.1 directly precedes the state Zk; and (Zhang et. al. the text from section III.B(2) on pages 1117-1118 describes the function of the aforementioned “ST-ConvLSTM” network (see the left-hand column on page 1118, and figure 2 on page 1117)
storing the trained machine-learning model and/or utilizing the machine-learning model for prediction.
PNG
media_image1.png
666
1234
media_image1.png
Greyscale
PNG
media_image2.png
345
618
media_image2.png
Greyscale
PNG
media_image3.png
485
630
media_image3.png
Greyscale
It is clear from the aforementioned text and drawing of Zhang et. al. that a representation (an image of a layer) of a state of t+1 (future slice Ys, t+1) is predicted at least partially on the basis of a representation of a state of t (input slice Xs, t) by means of the “ST-ConvLSTM” network. The first input image in this time series can be regarded as the representation TR1 defined in the claimed invention. It should also be noted that the penultimate paragraph in section IV on page 1125 of Zhang et. al. (see the last sentence) discloses a possibility for recursively predicting later points in time, i.e. on the basis of predictions of earlier points in time (“Another solution for predicting further into the future is to recursively apply the two-time-input model as in [27], i.e. predicting the outcome of time 4 based on the time 2 and the predicted time 3 results.”)
Regarding claim 2, Zhang et. al. discloses the method of claim 1, further comprising:
for each generated representation calculating a loss value for a pair composed of the received representation TR and the generated representation with the aid of a loss function, where j is an index passing through the numbers from 2 to n;
calculating a total loss value with the aid of a total loss function, where the total loss function is a function of the loss values; and
minimizing the total loss value by modifying parameters of the machine-learning model (Zhang et. al. Section III.B(4) discloses the use of a total error function (objective function) for “modifying parameters of the machine learning model” on the basis of the calculated total error (see equation 3), the total error being a function of the error values calculated from the pairs of received representation Tri and a corresponding generated representation of Tri* (“loss between the predicted frames Y and the true future frames X at time 2 and time 3”), the individual error values all being weighted equally).
Regarding claim 3, Zhang et. al. discloses the method of claim 2, wherein the total loss function has the following formula:
:
L
V
=
∑
j
=
2
n
w
j
∙
L
F
j
wherein LV is the total loss value, where LFj are the loss functions for calculating the loss values for the differences between the received representation TRj and the generated representation TRj, and wj are weight factors (Zhang et. al. Section III.B(4) discloses the use of a total error function (objective function) for “modifying parameters of the machine learning model” on the basis of the calculated total error (see equation 3), the total error being a function of the error values calculated from the pairs of received representation Tri and a corresponding generated representation of Tri* (“loss between the predicted frames Y and the true future frames X at time 2 and time 3”), the individual error values all being weighted equally).
Regarding claim 4, Zhang et. al. discloses a computer-implemented method for predicting one or more representations of an examination region of an examination object, comprising:
receiving a representation Rp of the examination region:
wherein the representation Rp represents the examination region in one state Zp of a sequence of states Zi to Zn, where p is an integer less than n, where n is an integer greater than two, and
wherein the examination object is preferably a human and the examination region is preferably part of the human;
feeding the representation Rp to a trained machine-learning model:
wherein the trained machine-learning model has been trained on the basis of training data to generate, starting from a first representation TR1, a number n-1 of representationsTR2* to TRL* one after the other,
wherein the first representation TR1 represents the examination region in the first state Zi and each generated representation represents the examination region in the state Z, where j is an index passing through the numbers from 2 to n,
wherein the representation TR2* is generated at least partly on the basis of the representation TR1 and each further representation is generated at least partly on the basis of the respective previously generated representation TRkl*, where k is an index passing through the numbers from 3 to n, and
wherein the training data are the result of a radiological examination;
receiving one or more representations Rp+q* of the examination region from the machine- learning model;
wherein each of the one or more representations Rp+q* represents the examination region in the state Zp+g, where q is an index passing through the numbers from 1 to m, where m is an integer less than n-1 or equal to n-1 or greater than n-11; and
outputting and/or storing and/or transmitting the one or more representations Rp+q* (Zhang et. al. Last paragraph of section III: “In testing, each spatial sequence (at time 1 and time 2) is divided to several sub-sequences, and fed into our model to generate predictions for time 3.” See also section IV.A and IV.B.1, according to which contrast-enhanced CT images were predicted and used as training data).
It should also be noted that the penultimate paragraph in section IV on page 1125 of Zhang et. al. (see the last sentence) discloses a possibility for recursively predicting later points in time, i.e. on the basis of predictions of earlier points in time (“Another solution for predicting further into the future is to recursively apply the two-time-input model as in [27], i.e. predicting the outcome of time 4 based on the time 2 and the predicted time 3 results.”)
Regarding claim 5, Zhang et. al. discloses the method of claim 4, wherein the method comprises:
receiving the representation Rp of the examination region, where the representation R, represents the examination region in the state Zp from the sequence of states Z1 to Zn, where p is an integer less than n,
feeding the representation Rp to the trained machine-learning model,
receiving the one or more representations Rp+q* of the examination region from the trained machine-learning model, where each of the one or more representations Rp+q* represents the examination region in the state Zp+q*, where q is an index passing through the numbers from 1 to m, where m is an integer less than n-1 or equal to n-1 or greater than n-1,and
outputting and/or storing and/or transmitting the one or more representations Rp+q*.
(Zhang et. al. Last paragraph of section III: “In testing, each spatial sequence (at time 1 and time 2) is divided to several sub-sequences, and fed into our model to generate predictions for time 3.” See also section IV.A and IV.B.1, according to which contrast-enhanced CT images were predicted and used as training data).
It should also be noted that the penultimate paragraph in section IV on page 1125 of Zhang et. al. (see the last sentence) discloses a possibility for recursively predicting later points in time, i.e. on the basis of predictions of earlier points in time (“Another solution for predicting further into the future is to recursively apply the two-time-input model as in [27], i.e. predicting the outcome of time 4 based on the time 2 and the predicted time 3 results.”)
Regarding claim 6, Zhang et. al. discloses the method of claim 4, wherein each representation is calculated according to the following formula:
M
q
R
1
=
R
1
+
q
*
wherein M represents a transformation which is applied by the machine-learning model to input data of the machine-learning model, where Mq means the q-times application of the transformation, where in a first step the transformation is applied to a first representation R1, in a second step the transformation is applied to the result of the application in the first step in that the result is passed back into the machine- learning model and the procedure is repeated with each further result of a transformation until the transformation has been applied a total of q times, where q is an integer which may assume the values of 1 to m, where m is an integer less than n-1 or equal to n-1 or greater than n-1 (It should also be noted that the penultimate paragraph in section IV on page 1125 of Zhang et. al. (see the last sentence) discloses a possibility for recursively predicting later points in time, i.e. on the basis of predictions of earlier points in time (“Another solution for predicting further into the future is to recursively apply the two-time-input model as in [27], i.e. predicting the outcome of time 4 based on the time 2 and the predicted time 3 results.”).
Regarding claim 7, Zhang et. al. discloses the method of claim 4, wherein the sequence of states comprises one or more of the following states:
a first state of the examination region at a first time point before the administration of a contrast agent,
a second state of the examination region at a second time point, after the administration of the contrast agent,
a third state of the examination region at a third time point, after the administration of the contrast agent,
a fourth state of the examination region at a fourth time point, after the administration of the contrast agent, and
a fifth state of the examination region at a fifth time point, after the administration of the contrast agent, wherein the first time point, the second time point, the third time point, the fourth time point, and the fifth time point form a chronological sequence (Zhang et. al. see the first sentence in section III.A).
Regarding claim 8, Zhang et. al. discloses the method of claim 4, wherein the examination region is the human liver or is part of the human liver (Zhang et. al. discloses that the examination region is the human pancreas. However, it would be obvious for a person skilled in the art to apply the method of Zhang et. al. to the human liver. An application of hepatobiliary contrast agent at a later point in time (even in the very far future) after the capturing of one or more CT images of a patient in Zhang et. al. is a simple substitution of regions of interest).
Regarding claim 9, Zhang et. al. discloses the method of claim 8, wherein the sequence of states comprises one or more of the following states:
the liver or part of the liver before the administration of a hepatobiliary contrast agent,
the liver or part of the liver during the arterial phase after the administration of the hepatobiliary contrast agent,
the liver or part of the liver during the portal venous phase after the administration of the hepatobiliary contrast agent,
the liver or part of the liver during the transitional phase after the administration of the hepatobiliary contrast agent, and
the liver or part of the liver during the hepatobiliary phase after the administration of the hepatobiliary contrast agent (Zhang et. al. discloses that the examination region is the human pancreas. However, it would be obvious for a person skilled in the art to apply the method of Zhang et. al. to the human liver. An application of hepatobiliary contrast agent at a later point in time (even in the very far future) after the capturing of one or more CT images of a patient in Zhang et. al. is a simple substitution of regions of interest).
.
Regarding claim 10, Zhang et. al. discloses the method of claim 4, wherein each representation Rp+q* and[[/or]] generated by the machine-learning model is returned to the trained machine-learning model in order to generate a representation Rp+q+i* and/or TRp+q+i* ((It should also be noted that the penultimate paragraph in section IV on page 1125 of Zhang et. al. (see the last sentence) discloses a possibility for recursively predicting later points in time, i.e. on the basis of predictions of earlier points in time (“Another solution for predicting further into the future is to recursively apply the two-time-input model as in [27], i.e. predicting the outcome of time 4 based on the time 2 and the predicted time 3 results.”).
Regarding claim 11, Zhang et. al. discloses the method of claim 4, wherein m is in the range from n to n+2 (It should also be noted that the penultimate paragraph in section IV on page 1125 of Zhang et. al. (see the last sentence) discloses a possibility for recursively predicting later points in time, i.e. on the basis of predictions of earlier points in time (“Another solution for predicting further into the future is to recursively apply the two-time-input model as in [27], i.e. predicting the outcome of time 4 based on the time 2 and the predicted time 3 results.”). It is assumed that in the recursive application of the model, it would have been obvious for a person skilled in the art to predict the same or a larger number of points in time than were used in training.
Regarding claim 12, Zhang et. al. discloses the method of claim 4, wherein the received representation Rp is a CT image, MRI image or ultrasound image (Zhang et. al. Figure 1, CT images are used).
Regarding claim 14, which is a computer program product comprising a computer program that can be loaded into a working memory of a computer system, where it causes the computer system to execute the following steps: corresponding to the method of claim 4, which the rejection analysis is incorporated herein.
Regarding claim 17, Zhang et. al. discloses a kit comprising a contrast agent and a computer program product, wherein the computer program product of claim 14, which the rejection analysis is incorporated herein.
Regarding claim 18, Zhang et. al. discloses the method of claim 5, where the trained machine-learning model has been trained, according to a computer-implemented method comprising: receiving training data: wherein the training data comprise representations TR1 to TRn of an examination region for a multiplicity of examination objects, where n is an integer greater than two, wherein each representation TR, represents the examination region in one state Z, of a sequence of states Zi to Zn, where i is an index passing through the integers from 1 to n, and wherein each examination object is preferably a human and the examination region is preferably part of the human; training the machine-learning model: wherein the model is trained to generate, starting from the representation TR1, representations TR2* to TRn* one after the other for each examination object of the multiplicity of examination objects, wherein the representation TR2* is generated at least partly on the basis of the representationTR1 and each further representation is generated at least partly on the basis of the respective previously generated representation TRk.1*, where k is an index passing through the numbers from 3 to n, and wherein the representation represents the examination region in the state Zk and the representation TRkl * represents the examination region in the state Zk.1, and the state Zk.1 directly precedes the state Zk; and storing the trained machine-learning model and/or utilizing the machine-learning model for prediction. (Zhang et. al. Last paragraph of section III: “In testing, each spatial sequence (at time 1 and time 2) is divided to several sub-sequences, and fed into our model to generate predictions for time 3.” See also section IV.A and IV.B.1, according to which contrast-enhanced CT images were predicted and used as training data).
It should also be noted that the penultimate paragraph in section IV on page 1125 of Zhang et. al. (see the last sentence) discloses a possibility for recursively predicting later points in time, i.e. on the basis of predictions of earlier points in time (“Another solution for predicting further into the future is to recursively apply the two-time-input model as in [27], i.e. predicting the outcome of time 4 based on the time 2 and the predicted time 3 results.”).
Regarding claim 19, Zhang et. al. discloses the method of claim 1, wherein each representation is calculated according to the following formula:
Mq (TR1) = TR1+q*
wherein M represents a transformation which is applied by the machine-learning model to input data of the machine-learning model, where Mq means the q-times application of the transformation, where in a first step the transformation is applied to a first representation TR1, in a second step the transformation is applied to the result of the application in the first step in that the result is passed back into the machine- learning model and the procedure is repeated with each further result of a transformation until the transformation has been applied a total of q times, where q is an integer which may assume the values of 1 to m, where m is an integer less than n-1 or equal to n-1 or greater than n-1 (It should also be noted that the penultimate paragraph in section IV on page 1125 of Zhang et. al. (see the last sentence) discloses a possibility for recursively predicting later points in time, i.e. on the basis of predictions of earlier points in time (“Another solution for predicting further into the future is to recursively apply the two-time-input model as in [27], i.e. predicting the outcome of time 4 based on the time 2 and the predicted time 3 results.”).
Regarding claim 20, Zhang et. al. discloses the method of claim 1, wherein the sequence of states comprises one or more of the following states:
a first state of the examination region at a first time point before the administration of a contrast agent,
a second state of the examination region at a second time point, after the administration of the contrast agent,
a third state of the examination region at a third time point, after the administration of the contrast agent,
a fourth state of the examination region at a fourth time point, after the administration of the contrast agent, and
a fifth state of the examination region at a fifth time point, after the administration of the contrast agent;
where the first time point, the second time point, the third time point, the fourth time point, and the fifth time point form a chronological sequence (Zhang et. al. see the first sentence in section III.A).
Regarding claim 21, Zhang et. al. discloses the method of claim 1, wherein the examination region is the human liver or is part of the human liver (Zhang et. al. discloses that the examination region is the human pancreas. However, it would be obvious for a person skilled in the art to apply the method of Zhang et. al. to the human liver. An application of hepatobiliary contrast agent at a later point in time (even in the very far future) after the capturing of one or more CT images of a patient in Zhang et. al. is a simple substitution of regions of interest).
Regarding claim 22, Zhang et. al. discloses the method of claim 1, wherein each representation TRp+q* generated by the machine- learning model is returned to the machine-learning model in order to generate a representation TRp+q+i* ((It should also be noted that the penultimate paragraph in section IV on page 1125 of Zhang et. al. (see the last sentence) discloses a possibility for recursively predicting later points in time, i.e. on the basis of predictions of earlier points in time (“Another solution for predicting further into the future is to recursively apply the two-time-input model as in [27], i.e. predicting the outcome of time 4 based on the time 2 and the predicted time 3 results.”).
Regarding claim 23, Zhang et. al. discloses the method of claim 1, wherein the representations TR1 to TRn are CT images, MRI images or ultrasound images (Zhang et. al. Figure 1, CT images are used).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Luc, Pauline et al. “Predicting Deeper into the Future of Semantic Segmentation.” 2017 IEEE International Conference on Computer Vision (ICCV) (2017): 648-657. Is relevant to the claimed invention because it discloses the machine learning model, computer system, and computer program product designed to make the predictions.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JESSICA YIFANG LIN whose telephone number is (571)272-6435. The examiner can normally be reached M-F 7:00am-6:15pm, with optional day 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, Vu Le can be reached at 571-272-7332. 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.
/JESSICA YIFANG LIN/Examiner, Art Unit 2668 May 29, 2026
/VU LE/Supervisory Patent Examiner, Art Unit 2668
Prosecution Insights