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 Objections
Claim 12 objected to because of the following informalities: in an other should corrected to in another. Appropriate correction is required.
Claim 16 objected to because of the following informalities: flame images should corrected to frame images. Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim 1 (and dependent claims 2-4, 8-12, 16-25) rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) does/do not fall within at least one of the four categories of patent eligible subject matter because a diagnostic support program is a directed towards a software per se.
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) 1-2, 21-22, 24 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Futamura (US 20170287114 A1).
Regarding claim 1, FUTAMURA discloses acquiring a plurality of frame images of the human organ ([0038] thereby obtaining a plurality of images showing the dynamic state. A series of images obtained by dynamic imaging is called a dynamic image. Images constituting a dynamic image are called frame images.);
calculating a frequency characterizing a state of the human organ based on each of the frame images ([0076] FIG. 4 shows the result of classification of signal components which can be contained in dynamic images of the chest on a graph of a feature quantity space formed of two axes, wherein the horizontal axis represents frequency of time change in pixel signal value of the dynamic images);
calculating a phase difference between a waveform in a previously acquired organ model and a waveform corresponding to the calculated frequency ("[0021] FIG. 5 shows time change in pixel signal value accompanying pulmonary blood flow and time change in pixel signal value accompanying noise.
[0077] Examples of the feature quantity relating to time change in pixel signal value of a dynamic image include: the above-described time frequency (frequency of waveform formed by plotting pixel signal values on the vertical axis against elapsed time from start of dynamic imaging on the horizontal axis); and a feature quantity relating to a profile shape of pixel signal values of a dynamic image in the time direction (shape of the above-described waveform). In heartbeat, systole is shorter than diastole, and as shown in FIG. 5, time change in pixel signal value accompanying pulmonary blood flow shows asymmetrical peaks as if one “ascends a steep slope and descends a gentle slope”. "); and
outputting a signal indicating the phase difference ("claim 4. The dynamic analysis device according to claim 3, wherein the feature quantity relating to the time change in the pixel signal value of the dynamic image is one or more of a time frequency of the pixel signal value of the dynamic image, and a feature quantity relating to a profile shape of the pixel signal value of the dynamic image in a time direction.
claim 5. The dynamic analysis device according to claim 4, wherein the feature quantity relating to the profile shape of the pixel signal value of the dynamic image in the time direction is any of (i) a peak integral, (ii) a peak distance, (iii) a skewness, (iv) a speed ratio, and (v) an acceleration ratio, each of which is calculated based on the profile shape, and (vi) an output result obtained by inputting the profile shape to a machine learning classifier.").
Regarding claim 2, FUTAMURA discloses dividing the images of the human organ and determining an organ model by an average value of pixel values within each divided area ([0120] Alternatively, the control unit 31 may perform filtering with the spatial frequency by: dividing the lung field region of each of the frame images into small regions having a size according to the spatial frequency with the set filtering parameters; calculating, in each small region, a measure of central tendency (e.g., the mean, the median, etc.) of pixel signal values).
Regarding claim 21, FUTAMURA discloses calculating a maximum value of pixel value ("[0079] The peak integral is a statistic relating to a signal integral value Sup, which is a signal integral value during signal value increase, and a signal integral value Sdown, which is a signal integral value during signal value decrease, in each cycle (see FIG. 6), and can be obtained, for example, by any one of the following Formula 1 to Formula 3. In the formulae, j represents a cycle number, MAX represents a maximum value, and MED represents a median. These apply to Formula 4 to Formula 12 too.
[0124] (2) difference between the maximum pixel signal value and the minimum pixel signal value;"); and
acquiring the waveform, based on a signal after the calculated maximum value ([0077] Examples of the feature quantity relating to time change in pixel signal value of a dynamic image include: the above-described time frequency (frequency of waveform formed by plotting pixel signal values on the vertical axis against elapsed time from start of dynamic imaging on the horizontal axis); and a feature quantity relating to a profile shape of pixel signal values of a dynamic image in the time direction (shape of the above-described waveform).).
Regarding claim 22, FUTAMURA discloses wherein Fourier-transforming processing is carried out by inputting data having periodicity ([0120] For example, when the feature quantities set in Step S11 are the time frequency and the spatial frequency, the control unit 31 first performs, for each frame image, (i) Fourier transform, (ii) filtering with a bandpass filter, high-pass filter or low-pass filter based on the filtering parameters of the spatial frequency, and (iii) inverse Fourier transform.), and
inverse Fourier transform processing is carried out by performing filtering processing by which a specific frequency is extracted ([0120] For example, when the feature quantities set in Step S11 are the time frequency and the spatial frequency, the control unit 31 first performs, for each frame image, (i) Fourier transform, (ii) filtering with a bandpass filter, high-pass filter or low-pass filter based on the filtering parameters of the spatial frequency, and (iii) inverse Fourier transform.).
Regarding claim 24, FUTAMURA discloses wherein the human organ is a lung and the lung image is divided into a plurality of areas ([0120] Alternatively, the control unit 31 may perform filtering with the spatial frequency by: dividing the lung field region of each of the frame images into small regions having a size according to the spatial frequency with the set filtering parameters), and
an average and a distribution of intensity values in the respective areas are calculated to obtain a correlation with a count value according to lung scintigraphy in between ("[0004] Meanwhile, for local analysis, measurement of the ventilation function by lung ventilation scintigraphy and measurement of the pulmonary blood flow function by lung perfusion scintigraphy can be used.
[0041] There are an indirect conversion type FPD which converts X-rays into electric signals with photoelectric conversion element(s) via scintillator(s) and a direct conversion type FPD which directly converts X-rays into electric signals. Either of them can be used.").
Claim Rejections - 35 USC § 103
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 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) 3 and 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Futamura (US 20170287114 A1) and further in view of Abe (US 20220398720 A1).
Regarding claim 3, Futamura does not disclose but in a similar field of endeavor of abnormal lung detection, Abe teaches wherein the frame images of the human organ are divided thereinto using a Voronoi tessellation method ([0093] To divide a region, Voronoi tessellation (Thiessen tessellation) can be applied).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention in order to combine the known system of Futamura’s disclosure of human organ medical imaging and image division, with the known technique of Voronoi tessellation method, as taught by Abe, in order to yield the predictable results of precise cell segmentation without clear membrane markers, quantitative mapping of tissue architecture, and efficient 3D volume partitioning.
Regarding claim 4, Futamura discloses wherein when the organ is a lung ([0038] The imaging device 1 is an imaging unit which images a cyclic dynamic state of a human body. Examples of the cyclic dynamic state include: change in shape of the lungs, i.e., expansion and contraction of the lungs, accompanying respiration) and implicitly discloses and a lung field area is divided according to a change rate of a lung volume ([0122] Next, the control unit 31 divides the lung field region of the filtered frame images into small regions for analysis, and calculates, for each small region of the frame images, a feature quantity relating to the dynamic state of the lung field (Step S17). For example, the control unit 31 calculates, for each small region thereof, time change in measure of central tendency (e.g., the mean, the median, etc.) of pixel signal values, and calculates, based on this time change, one or more of the following (1) to (8) feature quantities as the feature quantity relating to the dynamic state of the lung field. Note that the small regions for analysis each may even be formed of one pixel.).
Futamura does not explicitly disclose but Abe teaches and a lung field area is divided according to a change rate of a lung volume ([0094] In this way, after dividing a region to a plurality of block areas, a change in an image in each block area is calculated based on the relative position of each block area to a dynamic region such as a heart. Herein, not only the range of the mass itself as a pixel is taken as a unit got the difference of signals, but also the difference of signals can be taken in a range smaller than the mass, or in a larger range that surrounds the mass. Further, it is also possible to increase the range in the vertical direction only in the vicinity of the diaphragm, increase the range in the horizontal direction only in other dynamic regions, deform the shape of the range, or connect the regions of pixels. In addition, after calculating one or more differences, it is desirable to define the form of the mass again to match the form of the entire lung field and heart.).
Claim(s) 8-12, 16-20, 23, 25 is/are rejected under 35 U.S.C. 103 as being unpatentable over Futamura (US 20170287114 A1) and further in view of J. Mantilla et al., "Classification of LV wall motion in cardiac MRI using kernel Dictionary Learning with a parametric approach”.
Regarding claim 8, Futamura discloses acquiring the signal output from the diagnostic support program according to claim 1 (please refer to the discussion of claim 1).
Futamura does not disclose but in a similar field of endeavor of abnormal lung detection, Mantilla teaches making AI (Artificial Intelligence) learn a signal indicating a normal organ or a signal indicating an abnormal organ according to the acquired signal ("page 3, sec. III Classification Based on Dictionary Learning:
We aim at classifying whether a segment presents LV wall motion abnormality or not using parameters extracted from FTSICs in the radial image profiles. To this end, we proposed to analyze a DL approach for classification based on kernels [12]. Using an overcomplete dictionary A∈Rn×K that contains K elementary signals or atoms for columns, {aj}Kj=1, with K>n and usually K>>n, a signal b∈Rn can be represented as a linear combination of these atoms. Given training data D∈Rn×N, learning the dictionary A, the sparse coefficient matrix Y([y1, y2, …, yN]∈RK×N are the sparse codes coefficients of input data D), and the number of dictionary atoms K is called dictionary learning (DL). The DL-based classification approach consists of two steps: a training step based on a DL model and a prediction step based on the sparse codes coefficients Y obtained in the training step. "); and
recording learning results obtained by the AI (page 3, SECTION IV.Experiments and Results).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention in order to combine the known system of Futamura’s disclosure of human organ medical imaging and image division, with the known technique of AI determination of normal and abnormal organs/cells, as taught by Mantilla, in order to yield the predictable results of reducing processing time and having an automated system that determines and abnormal/normal organ based on comparisons with a human diagnosis.
Regarding claim 9, Futamura discloses acquiring the plurality of frame images ([0038] thereby obtaining a plurality of images showing the dynamic state. A series of images obtained by dynamic imaging is called a dynamic image. Images constituting a dynamic image are called frame images.); and
specifying the organ from the acquired frame images ([0038] The imaging device 1 is an imaging unit which images a cyclic dynamic state of a human body. Examples of the cyclic dynamic state include: change in shape of the lungs, i.e., expansion and contraction of the lungs, accompanying respiration).
Futamura does not disclose but Mantilla teaches outputting a ratio of an abnormal value by comparing the specified organ with the learning results ("page 3, sec. III Classification Based on Dictionary Learning:
We aim at classifying whether a segment presents LV wall motion abnormality or not using parameters extracted from FTSICs in the radial image profiles. To this end, we proposed to analyze a DL approach for classification based on kernels [12]. Using an overcomplete dictionary A∈Rn×K that contains K elementary signals or atoms for columns, {aj}Kj=1, with K>n and usually K>>n, a signal b∈Rn can be represented as a linear combination of these atoms. Given training data D∈Rn×N, learning the dictionary A, the sparse coefficient matrix Y([y1, y2, …, yN]∈RK×N are the sparse codes coefficients of input data D), and the number of dictionary atoms K is called dictionary learning (DL). The DL-based classification approach consists of two steps: a training step based on a DL model and a prediction step based on the sparse codes coefficients Y obtained in the training step. ").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention in order to combine the known system of Futamura’s disclosure of human organ medical imaging and image division, with the known technique of AI determination of normal and abnormal organs/cells, as taught by Mantilla, in order to yield the predictable results of reducing processing time and having an automated system that determines and abnormal/normal organ based on comparisons with a human diagnosis.
Regarding claim 10, Futamura does not explicitly disclose but Mantilla teaches outputting a phase difference between a waveform representing a cyclic motion of the normal organ and a waveform representing a cyclic motion of the abnormal organ (fig. 2 and section II C-1: The LV cavity at the mid-slice level is divided into 6 anatomical segments according to the AHA (American Heart Association) [10] representation. Each segment is divided into 6 angular subregions of ten consecutives profiles. A multisignal 1-D clustering process based on wavelets [11], splits the set of FTSICs into two clusters, then the average of the signals in the largest cluster is computed representing the largest group of signals with a similar contraction pattern. Thus, each image profile in an angular subregion is represented by a reference clustered signal of length 20. Fig. 2 shows an example of the reference average clustered FTSICs per segment in two subjects. As we can see, in the case of healthy subjects (on the left), all the maximum peak of signals seem to focus on a single phase in time with a relative small variation, reflecting a synchronous contraction of all segments. On the other hand, the maximum peak of signals in patients (on the right), appears in different phases or instants reflecting a dyssynchronous contraction among segments. For example in the patient shown in the Fig. 2-right, lateral segments contract early compared with the other segments.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention in order to combine the known system of Futamura’s disclosure of human organ medical imaging and image division, with the known technique of AI determination of normal and abnormal organs/cells, as taught by Mantilla, in order to yield the predictable results of reducing processing time and having an automated system that determines and abnormal/normal organ based on comparisons with a human diagnosis.
Regarding claim 11, Futamura does not explicitly disclose but Mantilla teaches adding/subtracting a signal in one region exhibiting different permeability therefrom to/from a signal in an other region, according to each of the plurality of frame images (section II C-1: The LV cavity at the mid-slice level is divided into 6 anatomical segments according to the AHA (American Heart Association) [10] representation. Each segment is divided into 6 angular subregions of ten consecutives profiles. A multisignal 1-D clustering process based on wavelets [11], splits the set of FTSICs into two clusters, then the average of the signals in the largest cluster is computed representing the largest group of signals with a similar contraction pattern. Thus, each image profile in an angular subregion is represented by a reference clustered signal of length 20. Fig. 2 shows an example of the reference average clustered FTSICs per segment in two subjects. As we can see, in the case of healthy subjects (on the left), all the maximum peak of signals seem to focus on a single phase in time with a relative small variation, reflecting a synchronous contraction of all segments. On the other hand, the maximum peak of signals in patients (on the right), appears in different phases or instants reflecting a dyssynchronous contraction among segments. For example in the patient shown in the Fig. 2-right, lateral segments contract early compared with the other segments.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention in order to combine the known system of Futamura’s disclosure of human organ medical imaging and image division, with the known technique of AI determination of normal and abnormal organs/cells, as taught by Mantilla, in order to yield the predictable results of reducing processing time and having an automated system that determines and abnormal/normal organ based on comparisons with a human diagnosis.
Regarding claim 12, Futamura and Mantilla do not explicitly disclose converting a waveform of a cyclic signal into a trigonometric function; and
outputting a signal indicating the waveform converted into the trigonometric function. However, the examiner states that it is obvious to one of ordinary skill in the art to convert a time-domain waveform of a cyclic signal into a trigonometric function—such as a sine or cosine wave—to allow a user to apply Fourier analysis, unlocking several powerful mathematical and practical benefits.
Regarding claim 16, FUTAMURA discloses acquiring the plurality of frame images ([0038] thereby obtaining a plurality of images showing the dynamic state. A series of images obtained by dynamic imaging is called a dynamic image. Images constituting a dynamic image are called frame images.); and
specifying the organ and blood flow flowing through the organ from the acquired frame images ([0077] In heartbeat, systole is shorter than diastole, and as shown in FIG. 5, time change in pixel signal value accompanying pulmonary blood flow shows asymmetrical peaks as if one “ascends a steep slope and descends a gentle slope”. Meanwhile, time change in pixel signal value of a noise component does not show such behavior as shown in FIG. 5. Hence, if it is desired to extract a signal component of pulmonary blood flow (blood flow signal component), a feature quantity representing asymmetry of peaks in a profile shape of pixel signal values of a dynamic image in the time direction can be a feature quantity to be used in filtering.), and
outputting a feature amount of the blood flow in the organ by comparing the specified organ and blood flow with the recorded learning results ([0078] Examples of the feature quantity representing asymmetry of peaks in a profile shape of pixel signal values of a dynamic image in the time direction include: peak integral; peak distance; a speed ratio; an acceleration ratio; skewness; and a value representing a degree of likeness to blood flow (likelihood) output from a machine learning classifier when the above-described profile shape is input to the classifier.).
Regarding claim 17, FUTAMURA discloses outputting a feature amount of blood flow in main blood vessels of the lung, or blood flow in capillaries and peripheral pulmonary vessels of the lung ([0103] For example, because motion of the heart wall and pulmonary blood flow occur by heartbeat, it can be considered that motion frequency of the heart wall substantially matches the time frequency of the pulmonary blood flow signal component in a dynamic image.).
Regarding claim 18, FUTAMURA discloses comparing movement during lung respiration with movement of lung blood flow, and outputting a feature amount indicating a linkage between both the movements ("[0103] For example, because motion of the heart wall and pulmonary blood flow occur by heartbeat, it can be considered that motion frequency of the heart wall substantially matches the time frequency of the pulmonary blood flow signal component in a dynamic image.
[0111] If the analysis target is pulmonary blood flow, the filtering parameters for the time frequency are set to extract a range which contains the motion frequency f of the heart wall but does not contain the motion frequency f of the diaphragm (or thorax or body-surface skin boundary face) and the motion frequency f of the main axis of the mediastinum. Meanwhile, if the analysis target is ventilation, the filtering parameters for the time frequency are set to extract a range which contains the motion frequency f of the diaphragm (or thorax or body-surface skin boundary face) but does not contain the motion frequency f of the heart wall and the motion frequency f of the main axis of the mediastinum.").
Regarding claim 19, FUTAMURA discloses acquiring the plurality of frame images ([0038] thereby obtaining a plurality of images showing the dynamic state. A series of images obtained by dynamic imaging is called a dynamic image. Images constituting a dynamic image are called frame images.); and
specifying a lung field area from the acquired frame images ([0114] When finishing setting the filtering parameters, the control unit 31 performs local matching and warping (nonlinear distortion transformation) on each frame image so as to align the frame images in terms of the lung field region (lung regions) (Step S13). For example, points (landmarks) as anatomical feature positions each shared by the frame images are extracted from each frame image, and a shift value of each landmark in each frame image from its corresponding landmark in a reference image is calculated.),
comparing a wave indicating movement in the specified lung field area with a reference wave ("[0122] Next, the control unit 31 divides the lung field region of the filtered frame images into small regions for analysis, and calculates, for each small region of the frame images, a feature quantity relating to the dynamic state of the lung field (Step S17). For example, the control unit 31 calculates, for each small region thereof, time change in measure of central tendency (e.g., the mean, the median, etc.) of pixel signal values, and calculates, based on this time change, one or more of the following (1) to (8) feature quantities as the feature quantity relating to the dynamic state of the lung field. Note that the small regions for analysis each may even be formed of one pixel.
[0123] (1) difference between the pixel signal values of the frame images which are adjacent to one another in terms of time."), and
outputting a feature amount indicating a linkage between the waves ([0131] Next, the control unit 31 displays the feature quantity calculation result performed in Step S17 on the display unit 34 (Step S18), and then ends the image analysis process.).
Regarding claim 20, FUTAMURA discloses wherein the reference wave is a wave indicating a respiratory cycle ("[0114] The frame image taken first is the reference image.
[0115] In this embodiment, imaging is performed during quiet breathing. During quiet breathing, position shift of the lung field region by respiration is a little.").
Regarding claim 23, Futamura does not explicitly disclose but Mantilla teaches wherein a plurality of waveforms are superimposed ("Fig. 2. Clustered reference signal by segments in a control subject (left) and patient (right)."), and
a phase peak in one cycle of any waveform is detected to calculate a phase difference of any other waveform ("Fig. 2. Clustered reference signal by segments in a control subject (left) and patient (right).
section II C-1: As we can see, in the case of healthy subjects (on the left), all the maximum peak of signals seem to focus on a single phase in time with a relative small variation, reflecting a synchronous contraction of all segments. On the other hand, the maximum peak of signals in patients (on the right), appears in different phases or instants reflecting a dyssynchronous contraction among segments. For example in the patient shown in the Fig. 2-right, lateral segments contract early compared with the other segments.").
Regarding claim 25, Futamura does not explicitly disclose but Mantilla teaches wherein a basic waveform is generated by superposing a plurality of original waveforms obtained from the images, respectively ("sec II c-1: The LV cavity at the mid-slice level is divided into 6 anatomical segments according to the AHA (American Heart Association) [10] representation. Each segment is divided into 6 angular subregions of ten consecutives profiles. A multisignal 1-D clustering process based on wavelets [11], splits the set of FTSICs into two clusters, then the average of the signals in the largest cluster is computed representing the largest group of signals with a similar contraction pattern.
sec II c-3: A parameter based on cross-correlation analysis is calculated between each average clustered curve (CI) and a patient-specific reference. To define this reference we perform a global multisignal 1-D clustering based on wavelets [11] overall the FTSICs from the image profiles that belong to the control subjects. The average of the cluster with maximum size is a patient-specific reference from the healthy population. Cross-correlation is then computed between each average clustered curve (CI) and the normal reference."); and
the original waveforms are subjected to setting of a band width thereof or weighting, while generating a master waveform based on the basic waveform to generate a waveform corresponding to the organ in each of the images ("sec II c-1: The LV cavity at the mid-slice level is divided into 6 anatomical segments according to the AHA (American Heart Association) [10] representation. Each segment is divided into 6 angular subregions of ten consecutives profiles. A multisignal 1-D clustering process based on wavelets [11], splits the set of FTSICs into two clusters, then the average of the signals in the largest cluster (master waveform) is computed representing the largest group of signals with a similar contraction pattern.
sec II c-3: A parameter based on cross-correlation analysis is calculated between each average clustered curve (CI) and a patient-specific reference. To define this reference we perform a global multisignal 1-D clustering based on wavelets [11] overall the FTSICs from the image profiles that belong to the control subjects. The average of the cluster with maximum size is a patient-specific reference from the healthy population. Cross-correlation is then computed between each average clustered curve (CI) and the normal reference. Thus, every spatio-temporal image profile is represented by a single value of correlation. Average values for cross-correlation were 0.76 ±0.11 for patients and 0.92 ±0.02 for control subjects, reflecting a noticeable contrast between the two populations.").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention in order to combine the known system of Futamura’s disclosure of human organ medical imaging and image division, with the known technique of AI determination of normal and abnormal organs/cells, as taught by Mantilla, in order to yield the predictable results of reducing processing time and having an automated system that determines and abnormal/normal organ based on comparisons with a human diagnosis.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Wael M, Ibrahim el-SH, Fahmy AS. Detection of Cardiac Function Abnormality from MRI Images Using Normalized Wall Thickness Temporal Patterns. Int J Biomed Imaging. 2016;2016:4301087. doi: 10.1155/2016/4301087. Epub 2016 Mar 1. PMID: 27034648; PMCID: PMC4791492 with regards to claim 10: "figure 2: Normalized wall thickness (NWT) throughout the cardiac cycle for all segments in a midventricular slice from (a) normal volunteer and (b) patient with hypertrophic cardiomyopathy (HCM).
Section 4: a novel feature vector, namely, the normalized wall thickness, which can be used to detect wall motion abnormality. This feature considers the variations between normal and abnormal contraction by tracking the normalized thickness of all segments between the endo- and epicardium during the whole cardiac cycle. The proposed method provides a simple tool for the assessment of the regional abnormality for each segment in each slice; therefore, it could be a valuable tool for automatic and fast determination of regional wall motion abnormality from conventional untagged cine images."
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AHMED A NASHER whose telephone number is (571)272-1885. The examiner can normally be reached Mon - Fri 0800 - 1700.
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, Emily Terrell can be reached at (571) 270-3717. 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.
/AHMED A NASHER/Examiner, Art Unit 2675
/EMILY C TERRELL/Supervisory Patent Examiner, Art Unit 2666
Prosecution Insights