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 .
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) 1, 2, 4-6, 8-10, 12-14, 16-18 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over D1 (U.S. PG-PUB NO. 2013/0294670) in view of D2 (U.S. PG-PUB NO. 2022/0398717).
-Regarding claim 1, D1 discloses a method for gating positron emission tomography (PET) data (see abstract), the method comprising: receiving tomography data acquired by imaging an object using a PET apparatus (signal detector 10 detects the gamma rays, and transmits data about the detected gamma rays to the computer 20 in a form of line of response (LOR), [0054]); segmenting the received tomography data into a plurality of bins of tomography data (divides the obtained signal into sections at a predetermined time interval, and generates a unit signal for each section by accumulating divided signals from each section, [0060]); generating a latent feature vector for each bin of the plurality of bins of tomography data (classifier 220 may calculate a feature value of a sinogram to determine similarity between sinograms based on characteristics of the sinograms of the unit signals, [0075]); clustering the generated latent feature vectors; and reconstructing an image using the received tomography data based on the clustering of the generated latent feature vectors (K-mean clustering method, [0077]).
D1 is silent to teaching that using a feature extraction neural network, the feature extraction neural network being pre-trained to extract latent feature vectors on a set of training data. However, the claimed limitation is well known in the art as evidenced by D2.
In the same field of endeavor, D2 teaches using a feature extraction neural network, the feature extraction neural network being pre-trained to extract latent feature vectors on a set of training data (trained model 708 can then be used during a deep learning testing or inference stage 712 to generate feature vectors for subsequently received medical images, [0097]).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of D1 with the teaching of D2 in order to provide faster computation for image labelling and consumption of fewer computational resources.
-Regarding claim 2, the combination further discloses the segmenting step includes segmenting the received tomography data into a plurality of bins, each bin of the plurality of bins being approximately 0.1 seconds to approximately 0.5 seconds in length (D1, an amount of time for each predetermined time interval may be determined considering a degree of the movement of the target, a movement period of the target, or a time interval for scanner to detect the LOR; the sections are short times, for example, times less than or equal to 1 second, [0061]).
-Regarding claim 4, the combination further discloses the generating step includes using a feature extraction neural network that is pre-trained to minimize a loss function between a reconstructed image and a target image (D2, loss function, [0097]), the target image being at least one of an input image of the set of training data input to the feature extraction network, another image of the set of training data different from the input image, or a difference image between the input image and another image of the set of training data (D2, A deviation is computed based on a comparison of the training data and the reconstructed training data and parameters of the DL model 708 (e.g., the neural network autoencoder) are updated based on the computed deviation, [0096]).
-Regarding claim 5, the combination further discloses the generating step further comprises generating the latent feature vector based on one or more latent features extracted by the feature extraction neural network (D2, to generate a plurality of feature vectors that include the low-dimensional feature space representation, such as by extracting features from the plurality of training data, [0069]).
-Regarding claim 6, the combination further discloses the clustering step further comprises clustering the generated latent feature vectors using a machine-learning method (D1, k-means clustering, [0077]).
-Regarding claim 8, the combination further discloses the clustering step further comprises clustering the generated latent feature vectors according to one or more phases of respiratory motion (D1, the 3D optical flow technique based on GVF features of gated sinograms may be suitable to 3D non-rigid body motion of the respiration, [0080]).
-Regarding claim 9, D1 discloses a positron emission tomography (PET) apparatus (FIG. 1-2), comprising: processing circuitry configured to acquire tomography data by imaging an object using PET (signal detector 10 detects the gamma rays, and transmits data about the detected gamma rays to the computer 20 in a form of line of response (LOR), [0054]), segment the acquired tomography data into a plurality of bins of tomography data (divides the obtained signal into sections at a predetermined time interval, and generates a unit signal for each section by accumulating divided signals from each section, [0060]), generate a latent feature vector for each bin of the plurality of bins of tomography data (classifier 220 may calculate a feature value of a sinogram to determine similarity between sinograms based on characteristics of the sinograms of the unit signals, [0075]), cluster the generated latent feature vectors, and reconstruct an image using the acquired tomography data based on the clustering of the generated latent feature vectors (K-mean clustering method, [0077]).
D1 is silent to teaching that using a feature extraction neural network, the feature extraction neural network being pre-trained to extract latent feature vectors on a set of training data. However, the claimed limitation is well known in the art as evidenced by D2.
In the same field of endeavor, D2 teaches using a feature extraction neural network, the feature extraction neural network being pre-trained to extract latent feature vectors on a set of training data (trained model 708 can then be used during a deep learning testing or inference stage 712 to generate feature vectors for subsequently received medical images, [0097]).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of D1 with the teaching of D2 in order to provide faster computation for image labelling and consumption of fewer computational resources.
-Regarding claim 10, the combination further discloses the processing circuitry is further configured to segment the acquired tomography data into bins are approximately 0.1 seconds to approximately 0.5 seconds in length (D1, an amount of time for each predetermined time interval may be determined considering a degree of the movement of the target, a movement period of the target, or a time interval for scanner to detect the LOR; the sections are short times, for example, times less than or equal to 1 second, [0061]).
-Regarding claim 12, the combination further discloses the processing circuitry is configured to generate the latent feature vector for each bin using the feature extraction neural network that is trained to minimize a loss function between a reconstructed image and a target image (D2, loss function, [0097]), the target image being at least one of an input image from the set of training data input to the feature extraction network, another image of the set of training data different from the input image, or a difference image between the input image and another image of the set of training data (D2, A deviation is computed based on a comparison of the training data and the reconstructed training data and parameters of the DL model 708 (e.g., the neural network autoencoder) are updated based on the computed deviation, [0096]).
-Regarding claim 13, the combination further discloses the processing circuitry is configured to generate the latent feature vector based on one or more latent features extracted by the feature extraction neural network (D2, to generate a plurality of feature vectors that include the low-dimensional feature space representation, such as by extracting features from the plurality of training data, [0069]).
-Regarding claim 14, the combination further discloses the processing circuitry is configured to cluster the generated latent feature vectors using a machine-learning method (D1, k-means clustering, [0077]).
-Regarding claim 16, the combination further discloses the processing circuitry is configured to cluster the generated latent feature vectors according to one or more phases of respiratory motion (D1, the 3D optical flow technique based on GVF features of gated sinograms may be suitable to 3D non-rigid body motion of the respiration, [0080]).
-Regarding claim 17, D1 discloses a non-transitory computer-readable storage medium for storing computer readable instructions that (memory, [0115]), when executed by a computer (computer 20, FIG. 2), cause the computer to perform a method, the method comprising: receiving tomography data acquired by imaging an object using a PET apparatus (signal detector 10 detects the gamma rays, and transmits data about the detected gamma rays to the computer 20 in a form of line of response (LOR), [0054]); segmenting the received tomography data into a plurality of bins of tomography data (divides the obtained signal into sections at a predetermined time interval, and generates a unit signal for each section by accumulating divided signals from each section, [0060]); generating a latent feature vector for each of the bins (classifier 220 may calculate a feature value of a sinogram to determine similarity between sinograms based on characteristics of the sinograms of the unit signals, [0075]); clustering the generated latent feature vectors; and reconstructing an image using the received tomography data based on the clustering of the latent feature vectors (K-mean clustering method, [0077]).
D1 is silent to teaching that using a feature extraction neural network, the feature extraction neural network being trained on a set of training data. However, the claimed limitation is well known in the art as evidenced by D2.
In the same field of endeavor, D2 teaches using a feature extraction neural network, the feature extraction neural network being trained on a set of training data (trained model 708 can then be used during a deep learning testing or inference stage 712 to generate feature vectors for subsequently received medical images, [0097]).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of D1 with the teaching of D2 in order to provide faster computation for image labelling and consumption of fewer computational resources.
-Regarding claim 18, the combination further discloses the segmenting step includes segmenting the received tomography data into a plurality of bins, each bin of the plurality of bins being approximately 0.1 seconds to approximately 0.5 seconds in length (D1, an amount of time for each predetermined time interval may be determined considering a degree of the movement of the target, a movement period of the target, or a time interval for scanner to detect the LOR; the sections are short times, for example, times less than or equal to 1 second, [0061]).
-Regarding claim 20, the combination further discloses the generating step includes using a feature extraction neural network that is pre-trained to minimize a loss function between a reconstructed image and a target image (D2, loss function, [0097]), the target image being at least one of an input image of the set of training data input to the feature extraction network, another image of the set of training data different from the input image, or a difference image between the input image and another image of the set of training data (D2, A deviation is computed based on a comparison of the training data and the reconstructed training data and parameters of the DL model 708 (e.g., the neural network autoencoder) are updated based on the computed deviation, [0096]).
Claim(s) 3, 11 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over D1 (U.S. PG-PUB NO. 2013/0294670) in view of D2 (U.S. PG-PUB NO. 2022/0398717) and further in view of D3 (U.S. PG-PUB NO. 2024/0249450).
-Regarding claim 3, the combination further discloses the generating step includes encoding a bin of tomography data with a feature extraction neural network including a convolutional autoencoder (D2, deep convolutional neural network (DCNN), [0092]; autoencoder, [0069]).
The combination is silent to teaching that having a self-attention module. However, the claimed limitation is well known in the art as evidenced by D3.
In the same field of endeavor, D3 teaches having a self-attention module (multi-head self-attention layer, [0041]).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of the combination with the teaching of D3 in order to give the convolutional autoencoder feature extractor the ability to model and characterize long-distance dependence in PET images – applying a known feature-extraction technique (self-attention) to improve a similar PET feature-extraction network in the same predictable way.
-Regarding claim 11, the combination further discloses the processing circuitry is further configured to generate the latent feature vector for each bin using the feature extraction neural network including a convolutional autoencoder having a self-attention module (D2, deep convolutional neural network (DCNN), [0092]; autoencoder, [0069]; D3, multi-head self-attention layer, [0041]).
-Regarding claim 19, the combination further discloses the generating step includes encoding a bin of tomography data with a feature extraction neural network including a convolutional autoencoder having a self-attention module (D2, deep convolutional neural network (DCNN), [0092]; autoencoder, [0069]; D3, multi-head self-attention layer, [0041]).
Claim(s) 7 and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over D1 (U.S. PG-PUB NO. 2013/0294670) in view of D2 (U.S. PG-PUB NO. 2022/0398717) and further in view of D4 (U.S. PG-PUB NO. 2013/0303898).
-Regarding claim 7, the combination is silent to teaching that the reconstructing step further comprises performing filtered back projection (FBP) or ordered subset expectation maximization (OSEM). However, the claimed limitation is well known in the art as evidenced by D4.
In the same field of endeavor, D4 teaches the reconstructing step further comprises performing filtered back projection (FBP) or ordered subset expectation maximization (OSEM) (based on the external motion signal acquired by the external motion monitor 120, imaging data (e.g., PET listmode data) can be binned into a number of phase frames with equal counts and each frame can be reconstructed).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of the combination with the teaching of D4 in order to improve quantification and delineation of known tumors for assessing response to therapy and treatment planning Compared to conventional motion correction methods.
-Regarding claim 15, the combination further discloses the processing circuitry is configured to reconstruct the image by performing filtered back projection (FBP) or ordered subset expectation maximization (OSEM) (D4, based on the external motion signal acquired by the external motion monitor 120, imaging data (e.g., PET listmode data) can be binned into a number of phase frames with equal counts and each frame can be reconstructed).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PING Y HSIEH whose telephone number is (571)270-3011. The examiner can normally be reached Monday-Friday, 9am-4pm.
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, Jennifer Mehmood can be reached at (571) 272-2976. 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.
/PING Y HSIEH/ Primary Examiner, Art Unit 2664
Prosecution Insights