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 .
DETAIL OFFICE ACTIONS
The United States Patent & Trademark Office appreciates the response filed for the current application that is submitted on 06/19/2026. The United States Patent & Trademark Office reviewed the following documents submitted and has made the following comments below.
Amendment
Applicant submitted amendments on 06/19/2026. The Examiner acknowledges the amendment and has reviewed the claims accordingly.
Examiner’s Responses:
Applicant’s arguments, see Remarks, filed 06/19/2026, with respect to the rejection(s) of claim(s) 1 under 35 U.S.C. 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, a new ground(s) of rejection is made in view of new elements from Ahn et al. (US-20170053423-A1, hereinafter Ahn_2017) in view of Ahn et al. (US-20140126794-A1, hereinafter Ahn_2014). Since the new ground(s) is not necessitated by an amendment. This is a second non-final action.
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 text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
The factual inquiries for establishing a background for determining obviousness under pre-AIA 35 U.S.C. 103(a) are summarized as follows:
Determining the scope and contents of the prior art.
Ascertaining the differences between the prior art and the claims at issue.
Resolving the level of ordinary skill in the pertinent art.
Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-2, 5, 8-9, 11-12, 14 and 17-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ahn et al. (US-20170053423-A1, hereinafter Ahn_2017) in view of Ahn et al. (US-20140126794-A1, hereinafter Ahn_2014).
CLAIM 1
In regards to Claim 1, Ahn_2017 teaches a computer-implemented (Ahn_2017, ¶ [0074]: “… may be implemented as part of one or more computers or processors. The computer or processor may include a computing device”) method for accessing and correcting system responses (Ahn_2017, ¶ [0004-0006]: “a method is provided … includes determining … one or more aspects of a quantitation imaging algorithm for generating a quantitation image, wherein the one or more aspects of the quantitation imaging algorithm are selected to optimize a quantitation figure of merit for lesion quantitation”. Ahn_2017discloses determining and optimizing parameters of image reconstruction algorithm), comprising:
obtaining, at a processor, raw scan data from a clinical scan of a subject with a medical imaging system (Ahn_2017, ¶ [0019]: “emission scan data is acquired. For example, the emission scan data may be acquired using an emission tomography scanner, such as a PET scanning system or a SPECT scanning system”; ¶ [0016]: “a medical imaging system may acquire data for a subject (e.g., patient or object)”);
inserting, via the processor, synthetic raw scan data with one or more known lesion values into the raw scan data to generate modified raw scan data (Ahn_2017, ¶ [0024 and 0048]: “generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset”);
separately reconstructing, via the processor, the raw scan data and the modified raw scan data to respectively generate a first reconstructed image and a second reconstructed image (Ahn_2017, ¶ [0024 and 0048]: “An exemplary method to reconstruct the quantitation images with and without a lesion is to generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset, and then to reconstruct quantitation images from the derived synthetic scan dataset and the original acquired scan dataset, respectively”; Ahn_2017 teaches reconstructing image without lesion from original scan data, and reconstructing image with lesion from derived synthetic scan data);
determining, via the processor, a system response to the inserted synthetic raw data. (Ahn_2017, ¶ [0024]: “An exemplary method to reconstruct the quantitation images with and without a lesion is to generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset, and then to reconstruct quantitation images from the derived synthetic scan dataset and the original acquired scan dataset, respectively. Various penalty function types, penalty strengths and/or penalty parameter values may be utilized to optimize the quantitation figure of merit that measures quantitative accuracy such as contrast recovery coefficient, recovery coefficient, and bias in reconstructed activity, which may be calculated by comparison with the known activity concentration of the digitally inserted lesion. This approach may be called hybrid lesion insertion”. Ahn_2017 teaches calculating contrast recovery coefficient (CRC) for the digitally inserted lesion, the Examiner notes CRC is system-dependent, see CRC’s definition below)
Ahn_2017 does not explicitly disclose a detailed process of calculating contrast recovery coefficient for a lesion.
Ahn_2014 is in the same field of art of PET image reconstruction. Further, Ahn_2014 teaches a detailed process of calculating contrast recovery coefficient for a lesion (Ahn_2014, ¶ [0036, 0055 and 0060]: “ a CRC can be calculated by interpolation using the normalized smoothing parameter and the reconstructed LPR as index values for selecting the pre-calculated CRC from the LUT, using the normalized smoothing parameter, the FWHM of the reconstructed LPR and the measured SUV, or from other LUTs. As described above, the size of the reconstructed tumor may be used as one of the index values instead of the FWHM of the reconstructed LPR”. Ahn_2014 discloses using extracted ROIs from the two reconstructed images (one with lesion, one without lesion) to calculate local perturbation response (LPR), then using LPR and a known size of reconstructed lesion to calculate CRC)
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Ahn_2017 by substituting Ahn_2017’s method to calculate CRC with Ahn_2014’s method to calculate CRC, to make a method correcting bias errors of PET system using CRC; thus, one of ordinary skilled in the art would be motivated to combine the references since it’s a simple substitution, Ahn_2017 disclose calculating CRC by analyzing images with and without the presence of a lesion, and Ahn_2014 teaches detailed steps to perform such method (Ahn_2014, ¶ [0059-0060]. The Examiner also notes Ahn_2017 and Ahn_2014 is the same person.).
The combination of Ahn_2017 and Ahn_2014 then teaches extracting, via the processor, information from the first reconstructed image and the second reconstructed image (Ahn_2014, ¶ [0036 and 0055]: “.... The local perturbation response, srecon, may be defined as the difference of the reconstructed image, xrecon, when the tumor is present and the reconstructed image, brecon, when the tumor is absent”; ¶ [0059]: “A reconstructed LPR can be calculated by segmenting the tumor in the region of interest and then subtracting the estimated background activity from the segmented tumor (step 404). The region used for calculating LPR may be large enough to include the reconstructed tumor” Ahn teaches extracting region of interest from two images, one with lesion and one without lesion, then perform a subtraction using two extracted ROIs; the two extracted ROIs are then used to calculate LPR); determining, via the processor, a system response to the inserted synthetic raw data (Ahn_2017, ¶ [0024]: “An exemplary method to reconstruct the quantitation images with and without a lesion is to generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset, and then to reconstruct quantitation images from the derived synthetic scan dataset and the original acquired scan dataset, respectively. Various penalty function types, penalty strengths and/or penalty parameter values may be utilized to optimize the quantitation figure of merit that measures quantitative accuracy such as contrast recovery coefficient, recovery coefficient, and bias in reconstructed activity, which may be calculated by comparison with the known activity concentration of the digitally inserted lesion. This approach may be called hybrid lesion insertion”. Ahn_2017 teaches calculating contrast recovery coefficient (CRC) for the digitally inserted lesion, the Examiner notes CRC is system-dependent, see CRC’s definition below) based on the information extracted from the first reconstructed image and the second reconstructed image and one or more target lesion values (Ahn_2014, ¶ [0036,0055, and 0060]: “ a CRC can be calculated by interpolation using the normalized smoothing parameter and the reconstructed LPR as index values for selecting the pre-calculated CRC from the LUT, using the normalized smoothing parameter, the FWHM of the reconstructed LPR and the measured SUV, or from other LUTs. As described above, the size of the reconstructed tumor may be used as one of the index values instead of the FWHM of the reconstructed LPR”. Ahn_2014 discloses using ROIs from two reconstructed images to calculate LPR, then using LPR and a known size of reconstructed lesion (corresponds to lesion value) to calculate contrast recovery coefficient (CRC)), and wherein the system response is specific to the medical imaging system and a reconstruction technique utilized by the medical imaging system (The Examiner attaches a definition of CRC from Google below, see section Influencing
PNG
media_image1.png
888
809
media_image1.png
Greyscale
Factors, CRC depends on scanner and reconstruction algorithm);
and utilizing, via the processor, the system response to correct the raw scan data. (Ahn_2014, ¶ [0044 and 0060-0061]: “The calculated CRC can be used to correct the uncorrected quantitation, for example, uncorrected SUV (step 414). The final corrected quantitation, e.g., the final corrected SUV, can be calculated (e.g., in step 110 of FIG. 1) by the following equation: ((uncorrected quantitation−the estimated background activity)/the calculated CRC)+the estimated background activity”; see FIG. 5 below; Ahn_2014 teaches
PNG
media_image2.png
932
1280
media_image2.png
Greyscale
correcting standardized uptake value (SUV) for a PET scan data)
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
CLAIM 2
Regarding claim 2, the combination of Ahn_2017 and Ahn_2014 teaches the method of Claim 1. In addition, the combination of Ahn_2017 and Ahn_2014 teaches the synthetic raw scan data is derived from the raw scan data. (Ahn_2017, ¶ [0024 and 0048]: “An exemplary method to reconstruct the quantitation images with and without a lesion is to generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset, and then to reconstruct quantitation images from the derived synthetic scan dataset and the original acquired scan dataset, respectively”)
CLAIM 5
Regarding claim 5, the combination of Ahn_2017 and Ahn_2014 teaches the method of Claim 1. In addition, the combination of Ahn_2017 and Ahn_2014 teaches determining the system response comprises performing fitting and establishing a conversion model between the information extracted from the first reconstructed image and the second reconstructed image and the one or more target lesion values. (Ahn_2017, ¶ [0048]: “for a given acquired scan dataset, the particular values for one or more aspects (e.g., at least one of a penalty function type, a penalty strength or a penalty parameter value) of the display imaging algorithm may be determined based on a lesion detectability index from a computer observer model. The inputs for the computer observer model are two image volumes, one with a lesion present and another without a lesion present. An exemplary method to reconstruct the two image volumes with and without a lesion is to generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset, and then to reconstruct images from the derived synthetic scan dataset and the original acquired scan dataset, respectively. Various penalty function types, penalty strengths and/or penalty parameter values may be utilized to optimize the lesion detection index” Ahn_2017 disclose establishing and optimize a computer observer model, the input is 2 images, one with lesion of known size and activity concentration)
CLAIM 8
Regarding claim 8, the combination of Ahn_2017 and Ahn_2014 teaches the method of Claim 5. In addition, the combination of Ahn_2017 and Ahn_2014 teaches the one or more target lesion values comprise actual activity value, actual feature size, or (The Examiner notes since a listing with “or” is disjunctive, any one of the elements found in the prior art is sufficient to reject the claim. While citations have been provided for completeness and rapid prosecution, only one element is required.) both. (Ahn_2017, ¶ [0024 and 0048]: “An exemplary method to reconstruct the quantitation images with and without a lesion is to generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset, and then to reconstruct quantitation images from the derived synthetic scan dataset and the original acquired scan dataset, respectively”)
CLAIM 9
Regarding claim 9, the combination of Ahn_2017 and Ahn_2014 teaches the method of Claim 5. In addition, the combination of Ahn_2017 and Ahn_2014 teaches the information extracted from the first reconstructed image and the second reconstructed image comprises image derived values (Ahn_2014, ¶ [0059]: “Using the reconstructed PET image produced from clinical data, the background activity near the tumor can be estimated by taking background ROIs manually or semi-manually with the aid of a computer (step 402). A reconstructed LPR can be calculated by segmenting the tumor in the region of interest and then subtracting the estimated background activity from the segmented tumor (step 404)” Ahn_2014 teaches extracting ROIs from reconstructed images and obtaining the background activity) and reconstruction derived values. (Ahn_2014, ¶ [0031]: “…in PET, an image reconstruction process estimates the three-dimensional spatial distribution of a radiotracer in the patient body from measured sinogram data. The radiotracer distribution is called an object or an (activity or emission) image” The Examiner notes the ROI extracted from reconstructed images also a representation of radiotracer’s spatial distribution)
CLAIM 11
Regarding claim 11, Ahn_2017 teaches A system for accessing and correcting system responses (Ahn_2017, ¶ [0016]: “methods and systems for generating a visual display image for diagnostic use, as well as for generating a quantitation value (e.g., a lesion quantitation value for a region of interest of the visual display image)”), comprising: a memory encoding processor-executable routines (Ahn_2017, ¶ [0062]: “a memory 332. The memory 332 may include one or more computer readable storage media (e.g., tangible and non-transitory storage media)… the process flows and/or flowcharts discussed herein (or aspects thereof) may represent one or more sets of instructions that are stored in the memory”); a processing system comprising one or more processors and configured to access the memory and to execute the processor-executable routines (Ahn_2017, ¶ [0060]: “ processing unit 330 is operably coupled to the detector unit 305. The depicted processing unit 330 is configured (e.g., may include one or more ASIC's and/or FPGA's, and/or includes or is associated with a tangible and non-transitory memory having stored thereon instructions configured to direct the processor)”), wherein the processor-executable routines, when executed by the processing system, cause the processing system to:
obtaining, at a processor, raw scan data from a clinical scan of a subject with a medical imaging system (Ahn_2017, ¶ [0019]: “emission scan data is acquired. For example, the emission scan data may be acquired using an emission tomography scanner, such as a PET scanning system or a SPECT scanning system”; ¶ [0016]: “a medical imaging system may acquire data for a subject (e.g., patient or object)”);
inserting, via the processor, synthetic raw scan data with one or more known lesion values into the raw scan data to generate modified raw scan data (Ahn_2017, ¶ [0024 and 0048]: “generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset”);
separately reconstructing, via the processor, the raw scan data and the modified raw scan data to respectively generate a first reconstructed image and a second reconstructed image (Ahn_2017, ¶ [0024 and 0048]: “An exemplary method to reconstruct the quantitation images with and without a lesion is to generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset, and then to reconstruct quantitation images from the derived synthetic scan dataset and the original acquired scan dataset, respectively”; Ahn teaches reconstructing image without lesion from original scan data, and reconstructing image with lesion from derived synthetic scan data);
determining, via the processor, a system response to the inserted synthetic raw data. (Ahn_2017, ¶ [0024]: “An exemplary method to reconstruct the quantitation images with and without a lesion is to generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset, and then to reconstruct quantitation images from the derived synthetic scan dataset and the original acquired scan dataset, respectively. Various penalty function types, penalty strengths and/or penalty parameter values may be utilized to optimize the quantitation figure of merit that measures quantitative accuracy such as contrast recovery coefficient, recovery coefficient, and bias in reconstructed activity, which may be calculated by comparison with the known activity concentration of the digitally inserted lesion. This approach may be called hybrid lesion insertion”. Ahn_2017 teaches calculating contrast recovery coefficient (CRC) for the digitally inserted lesion, the Examiner notes CRC is system-dependent, see CRC’s definition below)
Ahn_2017 does not explicitly disclose a detailed process of calculating contrast recovery coefficient for a lesion.
Ahn_2014 is in the same field of art of PET image reconstruction. Further, Ahn_2014 teaches a detailed process of calculating contrast recovery coefficient for a lesion (Ahn_2014, ¶ [0036, 0055 and 0060]: “ a CRC can be calculated by interpolation using the normalized smoothing parameter and the reconstructed LPR as index values for selecting the pre-calculated CRC from the LUT, using the normalized smoothing parameter, the FWHM of the reconstructed LPR and the measured SUV, or from other LUTs. As described above, the size of the reconstructed tumor may be used as one of the index values instead of the FWHM of the reconstructed LPR”. Ahn_2014 discloses using extracted ROIs from the two reconstructed images (one with lesion, one without lesion) to calculate local perturbation response (LPR), then using LPR and a known size of reconstructed lesion to calculate CRC)
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Ahn_2017 by substituting Ahn_2017’s method to calculate CRC with Ahn_2014’s method to calculate CRC, to make a method correcting bias errors of PET system using CRC; thus, one of ordinary skilled in the art would be motivated to combine the references since it’s a simple substitution, Ahn_2017 disclose calculating CRC by analyzing images with and without the presence of a lesion, and Ahn_2014 teaches detailed steps to perform such method (Ahn_2014, ¶ [0059-0060]. The Examiner also notes Ahn_2017 and Ahn_2014 is the same person.).
The combination of Ahn_2017 and Ahn_2014 then teaches extracting, via the processor, information from the first reconstructed image and the second reconstructed image (Ahn_2014, ¶ [0036 and 0055]: “.... The local perturbation response, srecon, may be defined as the difference of the reconstructed image, xrecon, when the tumor is present and the reconstructed image, brecon, when the tumor is absent”; ¶ [0059]: “A reconstructed LPR can be calculated by segmenting the tumor in the region of interest and then subtracting the estimated background activity from the segmented tumor (step 404). The region used for calculating LPR may be large enough to include the reconstructed tumor” Ahn teaches extracting region of interest from two images, one with lesion and one without lesion, then perform a subtraction using two extracted ROIs; the two extracted ROIs are then used to calculate LPR); determining, via the processor, a system response to the inserted synthetic raw data (Ahn_2017, ¶ [0024]: “An exemplary method to reconstruct the quantitation images with and without a lesion is to generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset, and then to reconstruct quantitation images from the derived synthetic scan dataset and the original acquired scan dataset, respectively. Various penalty function types, penalty strengths and/or penalty parameter values may be utilized to optimize the quantitation figure of merit that measures quantitative accuracy such as contrast recovery coefficient, recovery coefficient, and bias in reconstructed activity, which may be calculated by comparison with the known activity concentration of the digitally inserted lesion. This approach may be called hybrid lesion insertion”. Ahn_2017 teaches calculating contrast recovery coefficient (CRC) for the digitally inserted lesion, the Examiner notes CRC is system-dependent, see CRC’s definition below) based on the information extracted from the first reconstructed image and the second reconstructed image and one or more target lesion values (Ahn_2014, ¶ [0036,0055, and 0060]: “ a CRC can be calculated by interpolation using the normalized smoothing parameter and the reconstructed LPR as index values for selecting the pre-calculated CRC from the LUT, using the normalized smoothing parameter, the FWHM of the reconstructed LPR and the measured SUV, or from other LUTs. As described above, the size of the reconstructed tumor may be used as one of the index values instead of the FWHM of the reconstructed LPR”. Ahn_2014 discloses using ROIs from two reconstructed images to calculate LPR, then using LPR and a known size of reconstructed lesion (corresponds to lesion value) to calculate contrast recovery coefficient (CRC)), and wherein the system response is specific to the medical imaging system and a reconstruction technique utilized by the medical imaging system (The Examiner attaches a definition of CRC from Google below, see section Influencing
PNG
media_image1.png
888
809
media_image1.png
Greyscale
Factors, CRC depends on scanner and reconstruction algorithm);
and utilizing, via the processor, the system response to correct the raw scan data. (Ahn_2014, ¶ [0044 and 0060-0061]: “The calculated CRC can be used to correct the uncorrected quantitation, for example, uncorrected SUV (step 414). The final corrected quantitation, e.g., the final corrected SUV, can be calculated (e.g., in step 110 of FIG. 1) by the following equation: ((uncorrected quantitation−the estimated background activity)/the calculated CRC)+the estimated background activity”; see FIG. 5 below; Ahn_2014 teaches correcting standardized uptake value (SUV) for a PET scan data)
PNG
media_image2.png
932
1280
media_image2.png
Greyscale
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
CLAIM 12
Regarding claim 12, the combination of Ahn_2017 and Ahn_2014 teaches the system of Claim 11. In addition, the combination of Ahn_2017 and Ahn_2014 teaches the synthetic raw scan data is derived from the raw scan data. (Ahn_2017, ¶ [0024 and 0048]: “An exemplary method to reconstruct the quantitation images with and without a lesion is to generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset, and then to reconstruct quantitation images from the derived synthetic scan dataset and the original acquired scan dataset, respectively”)
CLAIM 14
Regarding claim 14, the combination of Ahn_2017 and Ahn_2014 teaches the system of Claim 11. In addition, the combination of Ahn_2017 and Ahn_2014 teaches determining the system response comprises performing fitting and establishing a conversion model between the information extracted from the first reconstructed image and the second reconstructed image and the one or more target lesion values. (Ahn_2017, ¶ [0048]: “for a given acquired scan dataset, the particular values for one or more aspects (e.g., at least one of a penalty function type, a penalty strength or a penalty parameter value) of the display imaging algorithm may be determined based on a lesion detectability index from a computer observer model. The inputs for the computer observer model are two image volumes, one with a lesion present and another without a lesion present. An exemplary method to reconstruct the two image volumes with and without a lesion is to generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset, and then to reconstruct images from the derived synthetic scan dataset and the original acquired scan dataset, respectively. Various penalty function types, penalty strengths and/or penalty parameter values may be utilized to optimize the lesion detection index” Ahn_2017 disclose establishing and optimize a computer observer model, the input is 2 images, one with lesion of known size and activity concentration)
CLAIM 17
Regarding claim 17, the combination of Ahn_2017 and Ahn_2014 teaches the system of Claim 14. In addition, the combination of Ahn_2017 and Ahn_2014 teaches the one or more target lesion values comprise actual activity value, actual feature size, or (The Examiner notes since a listing with “or” is disjunctive, any one of the elements found in the prior art is sufficient to reject the claim. While citations have been provided for completeness and rapid prosecution, only one element is required.) both. (Ahn_2017, ¶ [0024 and 0048]: “An exemplary method to reconstruct the quantitation images with and without a lesion is to generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset, and then to reconstruct quantitation images from the derived synthetic scan dataset and the original acquired scan dataset, respectively”)
CLAIM 18
Regarding claim 18, the combination of Ahn_2017 and Ahn_2014 teaches the system of Claim 14. In addition, the combination of Ahn_2017 and Ahn_2014 teaches the information extracted from the first reconstructed image and the second reconstructed image comprises image derived values (Ahn_2014, ¶ [0059]: “Using the reconstructed PET image produced from clinical data, the background activity near the tumor can be estimated by taking background ROIs manually or semi-manually with the aid of a computer (step 402). A reconstructed LPR can be calculated by segmenting the tumor in the region of interest and then subtracting the estimated background activity from the segmented tumor (step 404)” Ahn_2014 teaches extracting ROIs from reconstructed images and obtaining the background activity) and reconstruction derived values. (Ahn_2014, ¶ [0031]: “…in PET, an image reconstruction process estimates the three-dimensional spatial distribution of a radiotracer in the patient body from measured sinogram data. The radiotracer distribution is called an object or an (activity or emission) image” The Examiner notes the ROIs extracted from reconstructed images are also reconstruction of radiotracer’s spatial distribution)
CLAIM 19
Regarding claim 19, Ahn_2017 teaches a non-transitory computer-readable medium, the computer-readable medium comprising processor-executable code (Ahn_2017, ¶ [0062]: “a memory 332. The memory 332 may include one or more computer readable storage media (e.g., tangible and non-transitory storage media)… the process flows and/or flowcharts discussed herein (or aspects thereof) may represent one or more sets of instructions that are stored in the memory”) that when executed by a processing system comprising one or more processors (Ahn_2017, ¶ [0060]: “ processing unit 330 is operably coupled to the detector unit 305. The depicted processing unit 330 is configured (e.g., may include one or more ASIC's and/or FPGA's, and/or includes or is associated with a tangible and non-transitory memory having stored thereon instructions configured to direct the processor)”), causes the processing system to:
obtaining, at a processor, raw scan data from a clinical scan of a subject with a medical imaging system (Ahn_2017, ¶ [0019]: “emission scan data is acquired. For example, the emission scan data may be acquired using an emission tomography scanner, such as a PET scanning system or a SPECT scanning system”; ¶ [0016]: “a medical imaging system may acquire data for a subject (e.g., patient or object)”);
inserting, via the processor, synthetic raw scan data with one or more known lesion values into the raw scan data to generate modified raw scan data (Ahn_2017, ¶ [0024 and 0048]: “generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset”);
separately reconstructing, via the processor, the raw scan data and the modified raw scan data to respectively generate a first reconstructed image and a second reconstructed image (Ahn_2017, ¶ [0024 and 0048]: “An exemplary method to reconstruct the quantitation images with and without a lesion is to generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset, and then to reconstruct quantitation images from the derived synthetic scan dataset and the original acquired scan dataset, respectively”; Ahn teaches reconstructing image without lesion from original scan data, and reconstructing image with lesion from derived synthetic scan data);
determining, via the processor, a system response to the inserted synthetic raw data. (Ahn_2017, ¶ [0024]: “An exemplary method to reconstruct the quantitation images with and without a lesion is to generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset, and then to reconstruct quantitation images from the derived synthetic scan dataset and the original acquired scan dataset, respectively. Various penalty function types, penalty strengths and/or penalty parameter values may be utilized to optimize the quantitation figure of merit that measures quantitative accuracy such as contrast recovery coefficient, recovery coefficient, and bias in reconstructed activity, which may be calculated by comparison with the known activity concentration of the digitally inserted lesion. This approach may be called hybrid lesion insertion”. Ahn_2017 teaches calculating contrast recovery coefficient (CRC) for the digitally inserted lesion, the Examiner notes CRC is system-dependent, see CRC’s definition below)
Ahn_2017 does not explicitly disclose a detailed process of calculating contrast recovery coefficient for a lesion.
Ahn_2014 is in the same field of art of PET image reconstruction. Further, Ahn_2014 teaches a detailed process of calculating contrast recovery coefficient for a lesion (Ahn_2014, ¶ [0036, 0055 and 0060]: “ a CRC can be calculated by interpolation using the normalized smoothing parameter and the reconstructed LPR as index values for selecting the pre-calculated CRC from the LUT, using the normalized smoothing parameter, the FWHM of the reconstructed LPR and the measured SUV, or from other LUTs. As described above, the size of the reconstructed tumor may be used as one of the index values instead of the FWHM of the reconstructed LPR”. Ahn_2014 discloses using extracted ROIs from the two reconstructed images (one with lesion, one without lesion) to calculate local perturbation response (LPR), then using LPR and a known size of reconstructed lesion to calculate CRC)
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Ahn_2017 by substituting Ahn_2017’s method to calculate CRC with Ahn_2014’s method to calculate CRC, to make a method correcting bias errors of PET system using CRC; thus, one of ordinary skilled in the art would be motivated to combine the references since it’s a simple substitution, Ahn_2017 disclose calculating CRC by analyzing images with and without the presence of a lesion, and Ahn_2014 teaches detailed steps to perform such method (Ahn_2014, ¶ [0059-0060]. The Examiner also notes Ahn_2017 and Ahn_2014 is the same person.).
The combination of Ahn_2017 and Ahn_2014 then teaches extracting, via the processor, information from the first reconstructed image and the second reconstructed image (Ahn_2014, ¶ [0036 and 0055]: “.... The local perturbation response, srecon, may be defined as the difference of the reconstructed image, xrecon, when the tumor is present and the reconstructed image, brecon, when the tumor is absent”; ¶ [0059]: “A reconstructed LPR can be calculated by segmenting the tumor in the region of interest and then subtracting the estimated background activity from the segmented tumor (step 404). The region used for calculating LPR may be large enough to include the reconstructed tumor” Ahn teaches extracting region of interest from two images, one with lesion and one without lesion, then perform a subtraction using two extracted ROIs; the two extracted ROIs are then used to calculate LPR); determining, via the processor, a system response to the inserted synthetic raw data (Ahn_2017, ¶ [0024]: “An exemplary method to reconstruct the quantitation images with and without a lesion is to generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset, and then to reconstruct quantitation images from the derived synthetic scan dataset and the original acquired scan dataset, respectively. Various penalty function types, penalty strengths and/or penalty parameter values may be utilized to optimize the quantitation figure of merit that measures quantitative accuracy such as contrast recovery coefficient, recovery coefficient, and bias in reconstructed activity, which may be calculated by comparison with the known activity concentration of the digitally inserted lesion. This approach may be called hybrid lesion insertion”. Ahn_2017 teaches calculating contrast recovery coefficient (CRC) for the digitally inserted lesion, the Examiner notes CRC is system-dependent, see CRC’s definition below) based on the information extracted from the first reconstructed image and the second reconstructed image and one or more target lesion values (Ahn_2014, ¶ [0036,0055, and 0060]: “ a CRC can be calculated by interpolation using the normalized smoothing parameter and the reconstructed LPR as index values for selecting the pre-calculated CRC from the LUT, using the normalized smoothing parameter, the FWHM of the reconstructed LPR and the measured SUV, or from other LUTs. As described above, the size of the reconstructed tumor may be used as one of the index values instead of the FWHM of the reconstructed LPR”. Ahn_2014 discloses using ROIs from two reconstructed images to calculate LPR, then using LPR and a known size of reconstructed lesion (corresponds to lesion value) to calculate contrast recovery coefficient (CRC)), and wherein the system response is specific to the medical imaging system and a reconstruction technique utilized by the medical imaging system (The Examiner attaches a definition of CRC from Google below, see section Influencing
PNG
media_image1.png
888
809
media_image1.png
Greyscale
Factors, CRC depends on scanner and reconstruction algorithm);
and utilizing, via the processor, the system response to correct the raw scan data. (Ahn_2014, ¶ [0044 and 0060-0061]: “The calculated CRC can be used to correct the uncorrected quantitation, for example, uncorrected SUV (step 414). The final corrected quantitation, e.g., the final corrected SUV, can be calculated (e.g., in step 110 of FIG. 1) by the following equation: ((uncorrected quantitation−the estimated background activity)/the calculated CRC)+the estimated background activity”; see FIG. 5 below; Ahn_2014 teaches correcting standardized uptake value (SUV) for a PET scan data)
PNG
media_image2.png
932
1280
media_image2.png
Greyscale
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Claim(s) 3-4 and 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ahn_2017 in view of Ahn_2014, and further in view of Berthon et al. (Berthon, Beatrice, et al. "PETSTEP: generation of synthetic PET lesions for fast evaluation of segmentation methods." Physica Medica 31.8, published 2015, hereinafter Berthon).
CLAIM 3
In regards to Claim 3, the combination of Ahn_2017 and Ahn_2014 teaches the method of Claim 2.
The combination of Ahn_2017 and Ahn_2014 does not explicitly disclose generating, via the processor, images with synthetic lesions based on the raw scan data; performing, via the processor, forward projection on the images to generate the synthetic raw scan data; applying, via the processor, corrections on the synthetic raw scan data; and performing, via the processor, Poisson noise realization on the synthetic raw scan data to add noise to the synthetic raw scan data prior to insertion into the raw scan data.
Berthon is in the same field of art of generation of synthetic PET lesions. Further, Berthon teaches generating, via the processor, images with synthetic lesions based on the raw scan data (Berthon, page 970, section Methods: “PETSTEP allows the generation of synthetic PET images based on inserting a lesion-like sub-image into an image representing the background. The background image may be a reconstructed PET scan of a patient or phantom … 1. The lesion is added to or used to replace the background at its location, as specified by the user.”);
performing, via the processor, forward projection on the images to generate the synthetic raw scan data; (Berthon, page 970, right col: “3. The blurred image is then forward-projected via a radon transform to produce noise free projection data.”)
applying, via the processor, corrections on the synthetic raw scan data (Berthon, page 970, right col, steps 4-5: “The resulting projection data are attenuated by a forward-projection of the attenuation map derived from the computed tomography (CT) image. The attenuated data are then scaled, …”); and
performing, via the processor, Poisson noise realization on the synthetic raw scan data to add noise to the synthetic raw scan data prior to insertion into the raw scan data. (Berthon, page 970, right col, steps 6-7: “Noise is added to the data as a Poisson distribution of values with mean value corresponding to the forward projected data with added random and scatter counts…”)
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Ahn_2017 and Ahn_2014 by incorporating the tool to generate synthetic PET images that is taught by Berthon, to make a system to generate synthetic PET images from original PET data; thus, one of ordinary skilled in the art would be motivated to combine the references since among its several aspects, the present invention recognizes there is a need for a fast, flexible, and accessible simulation tool to generate simulated lesion images (Berthon, page 970-971, Introduction: “…the large variation of observed lesion geometries and uptake distributions requires a large number of test images to provide clinically relevant and robust results. For such applications, there is a need for a fast, flexible, and accessible simulation tool dedicated to the generation of large datasets …”; page 977, Conclusion: “This tool is open source and designed to be extensible to other isotope and image studies including kinetic modeling. The open source nature of PETSTEP allows user defined uptake distributions that can, in principle, be as complex as desired. We have shown that PETSTEP allows the fast generation of images reproducing scanner-acquired data and can be calibrated to accurately reproduce high quality MC simulated images”).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
CLAIM 4
In regards to Claim 4, the combination of Ahn_2017 and Ahn_2014 teaches the method of Claim 1.
The combination of Ahn_2017 and Ahn_2014 does not explicitly disclose receiving, at the processor, input of the one or more target lesion values.
Berthon is in the same field of art of generation of synthetic PET lesions. Further, Berthon teaches receiving, at the processor, input of the one or more target lesion values. (Berthon, page 971, right col: “The following parameters can be set by the user via a graphical user interface: The maximum lesion SUV …”)
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Ahn_2017 and Ahn_2014 by incorporating the tool to generate synthetic PET images that is taught by Berthon, to make a system to generate synthetic PET images from original PET data; thus, one of ordinary skilled in the art would be motivated to combine the references since among its several aspects, the present invention recognizes there is a need for a fast, flexible, and accessible simulation tool to generate simulated lesion images (Berthon, page 970-971, Introduction: “…the large variation of observed lesion geometries and uptake distributions requires a large number of test images to provide clinically relevant and robust results. For such applications, there is a need for a fast, flexible, and accessible simulation tool dedicated to the generation of large datasets … ”; page 977, Conclusion: “This tool is open source and designed to be extensible to other isotope and image studies including kinetic modeling. The open source nature of PETSTEP allows user defined uptake distributions that can, in principle, be as complex as desired. We have shown that PETSTEP allows the fast generation of images reproducing scanner-acquired data and can be calibrated to accurately reproduce high quality MC simulated images”).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
CLAIM 13
In regards to Claim 13, the combination of Ahn_2017 and Ahn_2014 teaches the system of Claim 12.
The combination of Ahn_2017 and Ahn_2014 does not explicitly disclose generating, via the processor, images with synthetic lesions based on the raw scan data; performing, via the processor, forward projection on the images to generate the synthetic raw scan data; applying, via the processor, corrections on the synthetic raw scan data; and performing, via the processor, Poisson noise realization on the synthetic raw scan data to add noise to the synthetic raw scan data prior to insertion into the raw scan data.
Berthon is in the same field of art of generation of synthetic PET lesions. Further, Berthon teaches generating, via the processor, images with synthetic lesions based on the raw scan data (Berthon, page 970, section Methods: “PETSTEP allows the generation of synthetic PET images based on inserting a lesion-like sub-image into an image representing the background. The background image may be a reconstructed PET scan of a patient or phantom … 1. The lesion is added to or used to replace the background at its location, as specified by the user.”);
performing, via the processor, forward projection on the images to generate the synthetic raw scan data; (Berthon, page 970, right col: “3. The blurred image is then forward-projected via a radon transform to produce noise free projection data.”)
applying, via the processor, corrections on the synthetic raw scan data (Berthon, page 970, right col, steps 4-5: “The resulting projection data are attenuated by a forward-projection of the attenuation map derived from the computed tomography (CT) image. The attenuated data are then scaled, …”); and
performing, via the processor, Poisson noise realization on the synthetic raw scan data to add noise to the synthetic raw scan data prior to insertion into the raw scan data. (Berthon, page 970, right col, steps 6-7: “Noise is added to the data as a Poisson distribution of values with mean value corresponding to the forward projected data with added random and scatter counts…”)
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Ahn_2017 and Ahn_2014 by incorporating the tool to generate synthetic PET images that is taught by Berthon, to make a system to generate synthetic PET images from original PET data; thus, one of ordinary skilled in the art would be motivated to combine the references since among its several aspects, the present invention recognizes there is a need for a fast, flexible, and accessible simulation tool to generate simulated lesion images (Berthon, page 970-971, Introduction: “…the large variation of observed lesion geometries and uptake distributions requires a large number of test images to provide clinically relevant and robust results. For such applications, there is a need for a fast, flexible, and accessible simulation tool dedicated to the generation of large datasets … ”; page 977, Conclusion: “This tool is open source and designed to be extensible to other isotope and image studies including kinetic modeling. The open source nature of PETSTEP allows user defined uptake distributions that can, in principle, be as complex as desired. We have shown that PETSTEP allows the fast generation of images reproducing scanner-acquired data and can be calibrated to accurately reproduce high quality MC simulated images”).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Claim(s) 6-7, 15-16 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ahn_2017 in view of Ahn_2014, and further in view of Goedicke et al. (US-20210398329-A1, hereinafter Goedicke).
CLAIM 6
Regarding claim 6, the combination of Ahn_2017 and Ahn_2014 teaches the method of Claim 5. In addition, the combination of Ahn_2017 and Ahn_2014 teaches defining, via the processor, within the first reconstructed image a location with a clinical feature (Ahn_2014, ¶ [0044 and 0059-0060]: “From the reconstructed image, a region of interest (e.g., a tumor) for quantitative analysis can be identified … Using the reconstructed PET image produced from clinical data, the background activity near the tumor can be estimated by taking background ROIs manually or semi-manually with the aid of a computer (step 402)”); and
extracting, via the processor, data information associated with the clinical feature (Ahn_2014, ¶ [0059-0060]: “A reconstructed LPR can be calculated by segmenting the tumor in the region of interest and then subtracting the estimated background activity from the segmented tumor (step 404).” Ahn_2014 discloses segmenting the ROI and perform image subtraction); and
PNG
media_image2.png
932
1280
media_image2.png
Greyscale
estimating, via the processor, a respective actual value for the one or more target lesion values for the clinical feature to correct the raw scan data associated with the clinical feature (Ahn_2014, ¶ [0044 and 0060-0061]: “The calculated CRC can be used to correct the uncorrected quantitation, for example, uncorrected SUV (step 414). The final corrected quantitation, e.g., the final corrected SUV, can be calculated (e.g., in step 110 of FIG. 1) by the following equation: ((uncorrected quantitation−the estimated background activity)/the calculated CRC)+the estimated background activity”; see FIG. 5 below; Ahn_2014 teaches correcting standardized uptake value (SUV) for a PET scan data)
The combination of Ahn_2017 and Ahn_2014 does not explicitly disclose estimating, via the processor, a respective actual value for the one or more target lesion values for the clinical feature utilizing the conversion model.
Goedicke is in the same field of art of standardized uptake value (suv) correction for PET imaging. Further, Goedicke teaches estimating, via the processor, a respective actual value for the one or more target lesion values for the clinical feature utilizing the conversion model. (Goedicke, ¶ [0042 and 0063-0066]: “The image processing also employs a neural network (NN) 28 to correct the SUV values as disclosed herein. The NN 28 can be a regression NN that is trained to determine an SUV correction factor for a lesion in images acquired by the PET gantry 12”. Goedicke teaches a neural network to generate a correction value for PET scan data)
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Ahn_2017 and Ahn_2014 by incorporating the machine learning model that is taught by Goedicke, to make a system that can correct SUV value of PET scan data using machine learning model; thus, one of ordinary skilled in the art would be motivated to combine the references since a neural network trained with large dataset improve SUV accuracy (Goedicke, ¶ [0015]: “Another advantage resides in providing improved SUV accuracy using a neural network efficiently trained with a large pool of clinical datasets with synthetically inserted lesions with known specifications and a mathematical model of the lesion”).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
CLAIM 7
Regarding claim 7, the combination of Ahn_2017, Ahn_2014 and Goedicke teaches the method of Claim 6. In addition, the combination of Ahn_2017, Ahn_2014 and Goedicke teaches the medical imaging system comprises a positron emission tomography imaging (Ahn_2017, ¶ [2017]: “…the emission scan data may be acquired using an emission tomography scanner, such as a PET scanning system or a SPECT scanning system”) system and the one or more target lesion values comprise standardized uptake value. (Ahn_2014, ¶ [0044]: “a region of interest (e.g., a tumor) for quantitative analysis can be identified manually or semi-manually with the aid of a computer (step 106). Then, an activity concentration can be quantified for the region of interest to produce an uncorrected quantitation (e.g., a standardized uptake value (SUV)) (step 108). The uncorrected quantitation can be corrected based on a pre-calculated contract recovery coefficient (CRC),”)
CLAIM 15
Regarding claim 15, the combination of Ahn_2017 and Ahn_2014 teaches the system of Claim 14. In addition, the combination of Ahn_2017 and Ahn_2014 teaches defining, via the processor, within the first reconstructed image a location with a clinical feature (Ahn_2014, ¶ [0044 and 0059-0060]: “From the reconstructed image, a region of interest (e.g., a tumor) for quantitative analysis can be identified … Using the reconstructed PET image produced from clinical data, the background activity near the tumor can be estimated by taking background ROIs manually or semi-manually with the aid of a computer (step 402)”); and
extracting, via the processor, data information associated with the clinical feature (Ahn_2014, ¶ [0059-0060]: “A reconstructed LPR can be calculated by segmenting the tumor in the region of interest and then subtracting the estimated background activity from the segmented tumor (step 404).” Ahn_2014 discloses segmenting the ROI and perform image subtraction); and
PNG
media_image2.png
932
1280
media_image2.png
Greyscale
estimating, via the processor, a respective actual value for the one or more target lesion values for the clinical feature to correct the raw scan data associated with the clinical feature (Ahn_2014, ¶ [0044 and 0060-0061]: “The calculated CRC can be used to correct the uncorrected quantitation, for example, uncorrected SUV (step 414). The final corrected quantitation, e.g., the final corrected SUV, can be calculated (e.g., in step 110 of FIG. 1) by the following equation: ((uncorrected quantitation−the estimated background activity)/the calculated CRC)+the estimated background activity”; see FIG. 5 below; Ahn_2014 teaches correcting standardized uptake value (SUV) for a PET scan data)
The combination of Ahn_2017 and Ahn_2014 does not explicitly disclose estimating, via the processor, a respective actual value for the one or more target lesion values for the clinical feature utilizing the conversion model.
Goedicke is in the same field of art of standardized uptake value (suv) correction for PET imaging. Further, Goedicke teaches estimating, via the processor, a respective actual value for the one or more target lesion values for the clinical feature utilizing the conversion model. (Goedicke, ¶ [0042 and 0063-0066]: “The image processing also employs a neural network (NN) 28 to correct the SUV values as disclosed herein. The NN 28 can be a regression NN that is trained to determine an SUV correction factor for a lesion in images acquired by the PET gantry 12”. Goedicke teaches a neural network to generate a correction value for PET scan data)
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Ahn_2017 and Ahn_2014 by incorporating the machine learning model that is taught by Goedicke, to make a system that can correct SUV value of PET scan data using machine learning model; thus, one of ordinary skilled in the art would be motivated to combine the references since a neural network trained with large dataset improve SUV accuracy (Goedicke, ¶ [0015]: “Another advantage resides in providing improved SUV accuracy using a neural network efficiently trained with a large pool of clinical datasets with synthetically inserted lesions with known specifications and a mathematical model of the lesion”).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
CLAIM 16
Regarding claim 16, the combination of Ahn_2017, Ahn_2014 and Goedicke teaches the system of Claim 15. In addition, the combination of Ahn_2017, Ahn_2014 and Goedicke teaches the medical imaging system comprises a positron emission tomography imaging (Ahn_2017, ¶ [2017]: “…the emission scan data may be acquired using an emission tomography scanner, such as a PET scanning system or a SPECT scanning system”) system and the one or more target lesion values comprise standardized uptake value. (Ahn_2014, ¶ [0044]: “a region of interest (e.g., a tumor) for quantitative analysis can be identified manually or semi-manually with the aid of a computer (step 106). Then, an activity concentration can be quantified for the region of interest to produce an uncorrected quantitation (e.g., a standardized uptake value (SUV)) (step 108). The uncorrected quantitation can be corrected based on a pre-calculated contract recovery coefficient (CRC),”)
CLAIM 20
Regarding claim 20, the combination of Ahn_2017 and Ahn_2014 teaches the medium of Claim 19. In addition, the combination of Ahn_2017 and Ahn_2014 teaches determining the system response comprises performing fitting and establishing a conversion model between the information extracted from the first reconstructed image and the second reconstructed image and the one or more target lesion values. (Ahn_2017, ¶ [0048]: “for a given acquired scan dataset, the particular values for one or more aspects (e.g., at least one of a penalty function type, a penalty strength or a penalty parameter value) of the display imaging algorithm may be determined based on a lesion detectability index from a computer observer model. The inputs for the computer observer model are two image volumes, one with a lesion present and another without a lesion present. An exemplary method to reconstruct the two image volumes with and without a lesion is to generate a derived synthetic scan dataset by digitally inserting a lesion of known size and activity concentration into the acquired scan dataset, and then to reconstruct images from the derived synthetic scan dataset and the original acquired scan dataset, respectively. Various penalty function types, penalty strengths and/or penalty parameter values may be utilized to optimize the lesion detection index” Ahn_2017 disclose establishing and optimize a computer observer model, the input is 2 images, one with lesion of known size and activity concentration)
defining, via the processor, within the first reconstructed image a location with a clinical feature (Ahn_2014, ¶ [0044 and 0059-0060]: “From the reconstructed image, a region of interest (e.g., a tumor) for quantitative analysis can be identified … Using the reconstructed PET image produced from clinical data, the background activity near the tumor can be estimated by taking background ROIs manually or semi-manually with the aid of a computer (step 402)”); and
extracting, via the processor, data information associated with the clinical feature (Ahn_2014, ¶ [0059-0060]: “A reconstructed LPR can be calculated by segmenting the tumor in the region of interest and then subtracting the estimated background activity from the segmented tumor (step 404).” Ahn_2014 discloses segmenting the ROI and perform image subtraction); and
PNG
media_image2.png
932
1280
media_image2.png
Greyscale
estimating, via the processor, a respective actual value for the one or more target lesion values for the clinical feature to correct the raw scan data associated with the clinical feature (Ahn_2014, ¶ [0044 and 0060-0061]: “The calculated CRC can be used to correct the uncorrected quantitation, for example, uncorrected SUV (step 414). The final corrected quantitation, e.g., the final corrected SUV, can be calculated (e.g., in step 110 of FIG. 1) by the following equation: ((uncorrected quantitation−the estimated background activity)/the calculated CRC)+the estimated background activity”; see FIG. 5 below; Ahn_2014 teaches correcting standardized uptake value (SUV) for a PET scan data)
The combination of Ahn_2017 and Ahn_2014 does not explicitly disclose estimating, via the processor, a respective actual value for the one or more target lesion values for the clinical feature utilizing the conversion model.
Goedicke is in the same field of art of standardized uptake value (suv) correction for PET imaging. Further, Goedicke teaches estimating, via the processor, a respective actual value for the one or more target lesion values for the clinical feature utilizing the conversion model. (Goedicke, ¶ [0042 and 0063-0066]: “The image processing also employs a neural network (NN) 28 to correct the SUV values as disclosed herein. The NN 28 can be a regression NN that is trained to determine an SUV correction factor for a lesion in images acquired by the PET gantry 12”. Goedicke teaches a neural network to generate a correction value for PET scan data)
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Ahn_2017 and Ahn_2014 by incorporating the machine learning model that is taught by Goedicke, to make a system that can correct SUV value of PET scan data using machine learning model; thus, one of ordinary skilled in the art would be motivated to combine the references since a neural network trained with large dataset improve SUV accuracy (Goedicke, ¶ [0015]: “Another advantage resides in providing improved SUV accuracy using a neural network efficiently trained with a large pool of clinical datasets with synthetically inserted lesions with known specifications and a mathematical model of the lesion”).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Allowable Subject Matter
Claim 10 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NHUT HUY (JEREMY) PHAM whose telephone number is (703)756-5797. The examiner can normally be reached Mo - Fr. 8:30am - 6pm ET.
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, O'Neal Mistry can be reached on (313)446-4912. 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.
/NHUT HUY PHAM/Examiner, Art Unit 2674
/ONEAL R MISTRY/Supervisory Patent Examiner, Art Unit 2674
Prosecution Insights