DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-6 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 1 and 6 recite limitations – “a display controller that displays first tissue structure information, which is information related to the first tissue structure, on a display unit, wherein the tissue structure specification unit inputs the target image to the second learning models, which are other than the initial second learning model and include the second learning model associated with a cross section type other than the specific cross section, in response to an instruction indicating a position on the target image from a user who has checked the first tissue structure information and specifies a second tissue structure included in a vicinity of the position indicated by the instruction from the user in the target image on the basis of prediction results of the second learning models”, appears to be directed to determining type of tissue structure in an cross section of a target image and further second tissue structure is identified by first machine learning classifier by user within vicinity of first tissue structure and classified by second machine learning classifier. However, the position of second tissue structure is first checked and specified by user and again repeatedly identified by machine learning classifier by user which is again classified by second machine learning classifier. Therefore, the sequence of steps are not clearly recited in order to explicitly define the features and interpret accordingly.
Examiner suggests amending claims as disclosed in original specifications in order to explicitly define the discussed features in order to render the claims definite.
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 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 of this title, 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.
Claims 1-4 and 6 are rejected under 35 U.S.C. 103 as being unpatentable over Shamir et al. (US Pub No. 20210196207 A1) in view of Murphy et al. (JP 2017070751 A).
Regarding Claim 1,
Shamir discloses An ultrasound tomographic image processing apparatus capable of accessing a first learning model that has been trained to predict a cross section type of an input ultrasound tomographic image and to output the cross section type and a plurality of second learning models each of which is associated with each cross section type of ultrasound tomographic images and has been trained to predict a tissue structure included in the ultrasound tomographic image of a corresponding cross section type and to output the tissue structure, the ultrasound tomographic image processing apparatus comprising: a cross section type specification unit that inputs a target image, which is an ultrasound tomographic image to be processed, to the first learning model to specify a specific cross section which is a cross section type of the target image; (Shamir, [0033-0035], [0069], discloses methods and systems may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the methods and systems may take the form of a computer program product on a computer-readable storage medium having computer-readable program instructions (e.g., computer software) embodied in the storage medium. More particularly, the present methods and systems may take the form of web-implemented computer software. Any suitable computer-readable storage medium may be utilized including hard disks, CD-ROMs, optical storage devices, or magnetic storage devices; block diagrams and flowchart illustrations of methods, systems, apparatuses, and computer program products. It will be understood that each block of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and flowchart illustrations, respectively, can be implemented by computer program instructions. These computer program instructions may be loaded onto a general-purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions which execute on the computer or other programmable data processing apparatus create a means for implementing the functions specified in the flowchart block or blocks; computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including computer-readable instructions for implementing the function specified in the flowchart block or blocks. The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions that execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks; [0069] As shown in FIG. 10, a system 1000 may use machine learning techniques to train, based on an analysis of one or more training data sets 1010A-100N by a training module 1020, at least one machine learning-based classifier 1030 that is configured to classify features extracted from images (e.g., medical images, etc.), such as three-dimensional (3D) images, comprising a plurality of voxels. The images may include images derived from magnetic resonance imaging (MRI), radiography, ultrasound, elastography, photoacoustic imaging, positron emission tomography, echocardiography, magnetic particle imaging, functional near-infrared spectroscopy, and/or any other imaging technique. The machine learning-based classifier 1030 may classify features extracted from 3D MRI images to enable fast approximation of electric field distribution based on a predictive model; [0068] In some instances, the patient modeling application 608 may use artificial intelligence and/or machine learning to associate dielectric properties with a patient model and/or determine dielectric (e.g., standard electrical properties, etc.) of tissues that may be used in simulations, numerical simulations of TTFields delivery to a patient. For example, medical images from a plurality of patients may be used to train the patient modeling application 608 (or any other predictive model) to map one or more dielectric properties (e.g., conductivity, relative permittivity, etc.) to a tissue type (e.g., combined skin and muscle tissue, skull/bone, cerebrospinal fluid, gray matter, white, tumor/cancerous tissue, etc.). The medical images may include images derived from magnetic resonance imaging (MRI), radiography, ultrasound, elastography, photoacoustic imaging, positron emission tomography, echocardiography, magnetic particle imaging, functional near-infrared spectroscopy, and/or any other imaging technique. The medical images may each include dielectric property information, such as conductivity values, at a set of points (e.g., different tissue locations, etc.). In some instances, the dielectric property information may be determined for (mapped to) each image by excising tissue samples from a patient associated with the image and measuring the dielectric properties of the tissue samples. Each location, area, and/or region of the patient's body from which a tissue sample is excised/collected may correlate, correspond, and/or be associated with the same location, area, and/or region of the patient's body represented in the image. Any technique may be used to track, correlate, correspond, and/or associate each location, area, and/or region of the patient's body from which a tissue sample is excised/collected and the same location, area, and/or region of the patient's body represented in the image, such as surgical navigation methods, and/or the like. Methods such as connected component labeling and/or the like may be used to map dielectric properties to different structures (e.g., tumors, etc.) and/or tissue types represented in a medical image. For example, a marker in an image, such as a voxel, pixel, and/or the like may be correlated to a point in a patient's anatomy from which a tissue sample is excised. The measured/determined dielectric/electrical properties of the tissue sample can form data/information that is associated with the marker voxel/pixel in the image; ultrasound image cross-sections are input as target image and machine learning model classifies as initial classification being type of tissue being e.g., combined skin and muscle tissue, skull/bone, cerebrospinal fluid, gray matter, white, tumor/cancerous tissue)
a tissue structure specification unit that inputs the target image to an initial second learning model, which is the second learning model associated with the specific cross section, to specify a first tissue structure included in the target image; (Shamir, [0068], discloses the patient modeling application 608 may use artificial intelligence and/or machine learning to associate dielectric properties with a patient model and/or determine dielectric (e.g., standard electrical properties, etc.) of tissues that may be used in simulations, numerical simulations of delivery to a patient. For example, medical images from a plurality of patients may be used to train the patient modeling application 608 (or any other predictive model) to map one or more dielectric properties (e.g., conductivity, relative permittivity, etc.) to a tissue type (e.g., combined skin and muscle tissue, skull/bone, cerebrospinal fluid, gray matter, white, tumor/cancerous tissue, etc.). The medical images may include images derived from magnetic resonance imaging (MRI), radiography, ultrasound, elastography, photoacoustic imaging, positron emission tomography, echocardiography, magnetic particle imaging, functional near-infrared spectroscopy, and/or any other imaging technique. The medical images may each include dielectric property information, such as conductivity values, at a set of points (e.g., different tissue locations, etc.). In some instances, the dielectric property information may be determined for (mapped to) each image by excising tissue samples from a patient associated with the image and measuring the dielectric properties of the tissue samples. Each location, area, and/or region of the patient's body from which a tissue sample is excised/collected may correlate, correspond, and/or be associated with the same location, area, and/or region of the patient's body represented in the image. Any technique may be used to track, correlate, correspond, and/or associate each location, area, and/or region of the patient's body from which a tissue sample is excised/collected and the same location, area, and/or region of the patient's body represented in the image, such as surgical navigation methods, and/or the like. Methods such as connected component labeling and/or the like may be used to map dielectric properties to different structures (e.g., tumors, etc.) and/or tissue types represented in a medical image. For example, a marker in an image, such as a voxel, pixel, and/or the like may be correlated to a point in a patient's anatomy from which a tissue sample is excised. The measured/determined dielectric/electrical properties of the tissue sample can form data/information that is associated with the marker voxel/pixel in the image. The contrast levels, for example of the marker voxel/pixel can be used to determine other voxels/pixels in the image associated with the marker voxel/pixel. The other voxels/pixels may represent the same tissue type represented by the marker voxel/pixel, such as gray matter, cerebral spinal fluid, and/or the like. The measured/determined dielectric/electrical properties associated with the marker voxel/pixel may also be associated with and/or used to label the other voxels/pixels in the image. The associated contrast levels of the marker voxel/pixel and the other voxels/pixels may be used to identify various tissue structures and/or types represented in the image. The medical images, the associated dielectric properties determined for each image, and features extracted from each image may form datasets that may train a machine learning model (e.g., a predictive model, the patient modeling application 608, etc.) to map one or more dielectric properties (e.g., conductivity, relative permittivity, etc.) to a tissue type (e.g., combined skin and muscle tissue, skull/bone, cerebrospinal fluid, gray matter, white, tumor/cancerous tissue, etc.) represented in an image. Features may include, for example, intensity/color/illumination and/or any other component related features associated with each voxel (or pixel) of an image, texture maps/information, and/or geometrical features (e.g., volume, roundness, skewness, etc.) represented in an image (e.g., describing, for instance, the tumor, etc.). In some instances, features extracted from each image may indicate a specific area of a patient's body, such as a head or torso, where voxels are labeled to indicate segmentation of a tumor and different tissue types, such as: combined skin and muscle tissue, skull/bone, cerebrospinal fluid, gray matter, and white matter. Unlabeled voxels of the image may be considered air. It should be noted that the datasets (or large dataset) may be changed, modified, and/or the like to include any data relevant to computing electric fields for transducer array layouts. The features may include any features, data, and/or information extracted from the medical images. The machine learning model may be trained according to a multiple datasets (or a large dataset) created from dielectric property information and features from medical images from a wide variety of patients. The machine learning model may associate dielectric properties with a patient model; tissue structure is output from second machine learning model of the input target image) and
a display controller that displays first tissue structure information, which is information related to the first tissue structure, on a display unit, wherein the tissue structure specification unit inputs the target image to the second learning models, which are other than the initial second learning model and include the second learning model associated with a cross section type other than the specific cross section, in response to an instruction indicating a position on the target image from a user who has checked the first tissue structure information and specifies a second tissue structure included in a vicinity of the position indicated by the instruction from the user in the target image on the basis of prediction results of the second learning models. (Shamir, [0099], Fig. 10, discloses I/O interfaces 1212 can be used to receive user input from and/or for providing system output to one or more devices or components. User input can be provided via, for example, a keyboard and/or a mouse. System output can be provided via a display device and a printer (not shown). I/O interfaces 1212 can include, for example, a serial port, a parallel port, a Small Computer System Interface (SCSI), an IR interface, an RF interface, and/or a universal serial bus (USB) interface; user may input at various stages of classification of tissue type and structure classifications using user I/O interfaces and multiple machine learning based classification models (1040B onwards to 1040N) to specific classification of tissue structure other than then initial classification machine learning model (1040A)).
Shamir does not explicitly disclose a display controller that displays first tissue structure information, which is information related to the first tissue structure, on a display unit, wherein the tissue structure specification unit inputs the target image to the second learning models, which are other than the initial second learning model and include the second learning model associated with a cross section type other than the specific cross section, in response to an instruction indicating a position on the target image from a user who has checked the first tissue structure information and specifies a second tissue structure included in a vicinity of the position indicated by the instruction from the user in the target image on the basis of prediction results of the second learning models.
Murphy discloses a display controller that displays first tissue structure information, which is information related to the first tissue structure, on a display unit, wherein the tissue structure specification unit inputs the target image to the second learning models, which are other than the initial second learning model and include the second learning model associated with a cross section type other than the specific cross section, in response to an instruction indicating a position on the target image from a user who has checked the first tissue structure information and specifies a second tissue structure included in a vicinity of the position indicated by the instruction from the user in the target image on the basis of prediction results of the second learning models. (Murphy, Description, discloses areas 201, 202, and 203 in FIG. 6a correspond to areas 211, 212, and 213 in FIG. 6b, respectively. Since higher threshold values are used in FIG. 6a, each region will contain more voxels. Regions 201, 202, 203 may represent follicles that are better segmented at threshold 45 than are segmented at threshold 25. Each region of FIG. 6a contains a greater proportion of follicle size than the region of FIG. 6b; Region 204 in FIG. 6a has been identified as a single connected region. However, in FIG. 6b, the two regions 214 and 215 may be seen to correspond to the region 204 of FIG. 6a. Using a threshold of 45 leads to regions being merged incorrectly. Regions 214 and 215 may be better segmented at the 25 threshold than they are segmented at the 45 threshold, since the follicles will be mistakenly fused at the 45 threshold; For multiple sets of ultrasound image data or other medical imaging data, the optimal threshold for segmentation of all follicles in the image data may not be a single threshold. There can be a gradient in brightness across a single image. The image may have a shadow. Ultrasound can have various artifacts, such as echo reflections. Echo reflection artifacts can unnaturally increase the brightness of the subject; Using multiple thresholds means that the optimal threshold for segmenting one follicle is the optimal threshold for segmenting another follicle while each follicle is segmented using the appropriate threshold It is possible even if different; the threshold processing circuit 34 uses a predetermined set of threshold luminance values, which are luminance values ranging from 5 to 50 in five increments. The volume to be filtered is thresholded at several predetermined brightness levels. In other embodiments, the threshold processing circuit 34 may receive a set of thresholds from the memory 50, from another data store, or from user input. In some embodiments, the threshold processing circuit 34 may determine a set of thresholds. For example, the maximum and minimum luminance values for the preprocessed data set may be determined, and the result width of the value by a predetermined increment may be divided; the threshold processing circuit 34 executes threshold processing that is used to extract a region for each threshold, and then specifies connected component analysis and morphological hole filling processing using the threshold. Applicable to candidate follicular voxels. In other embodiments, the regions may be extracted based on threshold processing in any suitable manner. Connected component analysis and morphological hole filling may or may not be used. Any optimal morphological operation may be performed on the voxels identified as candidate follicular voxels. Morphological operations may be performed before or after connected component analysis; output of stage 108 is a set of extracted regions for each threshold. As described above, a higher threshold may result in a more widely extracted region and / or more extracted region than a region acquired for a lower threshold. Sometimes there may be a threshold that no extracted region is acquired; the selection circuit 36 uses a simple classifier to classify the extracted regions, which in this case are box classifiers (or also known as linear classifiers). If the predetermined extracted region is classified as a follicle by the classifier, it is selected by the selection circuit 36. If the extracted region is not classified as a follicle, it is not selected; the threshold processing circuit 34 uses a predetermined set of threshold luminance values, which are luminance values ranging from 5 to 50 in five increments. The volume to be filtered is thresholded at several predetermined brightness levels. In other embodiments, the threshold processing circuit 34 may receive a set of thresholds from the memory 50, from another data store, or from user input. In some embodiments, the threshold processing circuit 34 may determine a set of thresholds. For example, the maximum and minimum luminance values for the preprocessed data set may be determined, and the result width of the value by a predetermined increment may be divided; different classifiers may be used in different embodiments. For example, multivariate Gaussian, instruction vector machines, or other machine learning classifiers may be used; multiple candidate regions of tissue structures are selected by user other than initial tissue structure, and its location is output by plurality of learning classifiers (models) in a display based on location of tissue structures in its vicinities).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Shamir in view of Murphy having a method of detecting a type of tissue and its structure within a target image, with the teachings of Murphy having, by the system of determining multiple type of tissue structures within a target image that are in the vicinity of the other tissue structures classified by multiple machine learning models and marked by user with use of interface and displayed in applications including medical imaging.
Regarding Claim 2,
The combination of Shamir and Murphy further discloses wherein the display controller displays cross section information indicating the specific cross section on the display unit, and in a case where the specific cross section is different from a cross section type associated with the second learning model that has contributed to the specification of the second tissue structure, the display controller displays corrected cross section information indicating the cross section type corresponding to the second learning model that has contributed to the specification of the second tissue structure on the display unit, instead of the cross section information indicating the specific cross section. (Murphy, Description, discloses areas 201, 202, and 203 in FIG. 6a correspond to areas 211, 212, and 213 in FIG. 6b, respectively. Since higher threshold values are used in FIG. 6a, each region will contain more voxels. Regions 201, 202, 203 may represent follicles that are better segmented at threshold 45 than are segmented at threshold 25. Each region of FIG. 6a contains a greater proportion of follicle size than the region of FIG. 6b; Region 204 in FIG. 6a has been identified as a single connected region. However, in FIG. 6b, the two regions 214 and 215 may be seen to correspond to the region 204 of FIG. 6a. Using a threshold of 45 leads to regions being merged incorrectly. Regions 214 and 215 may be better segmented at the 25 threshold than they are segmented at the 45 threshold, since the follicles will be mistakenly fused at the 45 threshold; For multiple sets of ultrasound image data or other medical imaging data, the optimal threshold for segmentation of all follicles in the image data may not be a single threshold. There can be a gradient in brightness across a single image. The image may have a shadow. Ultrasound can have various artifacts, such as echo reflections. Echo reflection artifacts can unnaturally increase the brightness of the subject; Using multiple thresholds means that the optimal threshold for segmenting one follicle is the optimal threshold for segmenting another follicle while each follicle is segmented using the appropriate threshold It is possible even if different; the threshold processing circuit 34 uses a predetermined set of threshold luminance values, which are luminance values ranging from 5 to 50 in five increments. The volume to be filtered is thresholded at several predetermined brightness levels. In other embodiments, the threshold processing circuit 34 may receive a set of thresholds from the memory 50, from another data store, or from user input. In some embodiments, the threshold processing circuit 34 may determine a set of thresholds. For example, the maximum and minimum luminance values for the preprocessed data set may be determined, and the result width of the value by a predetermined increment may be divided; the threshold processing circuit 34 executes threshold processing that is used to extract a region for each threshold, and then specifies connected component analysis and morphological hole filling processing using the threshold. Applicable to candidate follicular voxels. In other embodiments, the regions may be extracted based on threshold processing in any suitable manner. Connected component analysis and morphological hole filling may or may not be used. Any optimal morphological operation may be performed on the voxels identified as candidate follicular voxels. Morphological operations may be performed before or after connected component analysis; output of stage 108 is a set of extracted regions for each threshold. As described above, a higher threshold may result in a more widely extracted region and / or more extracted region than a region acquired for a lower threshold. Sometimes there may be a threshold that no extracted region is acquired; the selection circuit 36 uses a simple classifier to classify the extracted regions, which in this case are box classifiers (or also known as linear classifiers). If the predetermined extracted region is classified as a follicle by the classifier, it is selected by the selection circuit 36. If the extracted region is not classified as a follicle, it is not selected; the threshold processing circuit 34 uses a predetermined set of threshold luminance values, which are luminance values ranging from 5 to 50 in five increments. The volume to be filtered is thresholded at several predetermined brightness levels. In other embodiments, the threshold processing circuit 34 may receive a set of thresholds from the memory 50, from another data store, or from user input. In some embodiments, the threshold processing circuit 34 may determine a set of thresholds. For example, the maximum and minimum luminance values for the preprocessed data set may be determined, and the result width of the value by a predetermined increment may be divided; different classifiers may be used in different embodiments. For example, multivariate Gaussian, instruction vector machines, or other machine learning classifiers may be used; multiple candidate regions of tissue structures are selected by user other than initial tissue structure, and its location is output by plurality of learning classifiers (models) in a display based on location of tissue structures in its vicinities). Additionally, the rational and motivation to combine the references Shamir and Murphy as applied in rejection of claim 1 apply to this claim.
Regarding Claim 3,
The combination of Shamir and Murphy further discloses wherein the plurality of second learning models are grouped corresponding to each part of a subject, and the tissue structure specification unit inputs the target image to the second learning model belonging to the same group as the initial second learning model among the plurality of second learning models other than the initial second learning model in response to an instruction from the user who has checked the first tissue structure information and further specifies the second tissue structure included in the target image on the basis of a prediction result of the second learning model. (Murphy, Description, discloses areas 201, 202, and 203 in FIG. 6a correspond to areas 211, 212, and 213 in FIG. 6b, respectively. Since higher threshold values are used in FIG. 6a, each region will contain more voxels. Regions 201, 202, 203 may represent follicles that are better segmented at threshold 45 than are segmented at threshold 25. Each region of FIG. 6a contains a greater proportion of follicle size than the region of FIG. 6b; Region 204 in FIG. 6a has been identified as a single connected region. However, in FIG. 6b, the two regions 214 and 215 may be seen to correspond to the region 204 of FIG. 6a. Using a threshold of 45 leads to regions being merged incorrectly. Regions 214 and 215 may be better segmented at the 25 threshold than they are segmented at the 45 threshold, since the follicles will be mistakenly fused at the 45 threshold; For multiple sets of ultrasound image data or other medical imaging data, the optimal threshold for segmentation of all follicles in the image data may not be a single threshold. There can be a gradient in brightness across a single image. The image may have a shadow. Ultrasound can have various artifacts, such as echo reflections. Echo reflection artifacts can unnaturally increase the brightness of the subject; Using multiple thresholds means that the optimal threshold for segmenting one follicle is the optimal threshold for segmenting another follicle while each follicle is segmented using the appropriate threshold It is possible even if different; the threshold processing circuit 34 uses a predetermined set of threshold luminance values, which are luminance values ranging from 5 to 50 in five increments. The volume to be filtered is thresholded at several predetermined brightness levels. In other embodiments, the threshold processing circuit 34 may receive a set of thresholds from the memory 50, from another data store, or from user input. In some embodiments, the threshold processing circuit 34 may determine a set of thresholds. For example, the maximum and minimum luminance values for the preprocessed data set may be determined, and the result width of the value by a predetermined increment may be divided; the threshold processing circuit 34 executes threshold processing that is used to extract a region for each threshold, and then specifies connected component analysis and morphological hole filling processing using the threshold. Applicable to candidate follicular voxels. In other embodiments, the regions may be extracted based on threshold processing in any suitable manner. Connected component analysis and morphological hole filling may or may not be used. Any optimal morphological operation may be performed on the voxels identified as candidate follicular voxels. Morphological operations may be performed before or after connected component analysis; output of stage 108 is a set of extracted regions for each threshold. As described above, a higher threshold may result in a more widely extracted region and / or more extracted region than a region acquired for a lower threshold. Sometimes there may be a threshold that no extracted region is acquired; the selection circuit 36 uses a simple classifier to classify the extracted regions, which in this case are box classifiers (or also known as linear classifiers). If the predetermined extracted region is classified as a follicle by the classifier, it is selected by the selection circuit 36. If the extracted region is not classified as a follicle, it is not selected; the threshold processing circuit 34 uses a predetermined set of threshold luminance values, which are luminance values ranging from 5 to 50 in five increments. The volume to be filtered is thresholded at several predetermined brightness levels. In other embodiments, the threshold processing circuit 34 may receive a set of thresholds from the memory 50, from another data store, or from user input. In some embodiments, the threshold processing circuit 34 may determine a set of thresholds. For example, the maximum and minimum luminance values for the preprocessed data set may be determined, and the result width of the value by a predetermined increment may be divided; different classifiers may be used in different embodiments. For example, multivariate Gaussian, instruction vector machines, or other machine learning classifiers may be used; multiple candidate regions of tissue structures are selected by user other than initial tissue structure, and its location is output by plurality of learning classifiers (models) in a display based on location of tissue structures in its vicinities). Additionally, the rational and motivation to combine the references Shamir and Murphy as applied in rejection of claim 1 apply to this claim.
Regarding Claim 4,
The combination of Shamir and Murphy further discloses wherein the tissue structure specification unit inputs the target image to each of a plurality of the second learning models other than the initial second learning model in response to an instruction from the user who has checked the first tissue structure information and calculates an order of prediction accuracy for each of labels of a plurality of tissue structures predicted by the plurality of second learning models, the display controller displays the labels of the plurality of tissue structures predicted by the plurality of second learning models on the display unit in a display mode in which the order of the prediction accuracy is represented, and the tissue structure specification unit specifies, as the second tissue structure, a tissue structure related to a label selected by the user among the plurality of tissue structures predicted by the plurality of second learning models. (Murphy, Description, discloses areas 201, 202, and 203 in FIG. 6a correspond to areas 211, 212, and 213 in FIG. 6b, respectively. Since higher threshold values are used in FIG. 6a, each region will contain more voxels. Regions 201, 202, 203 may represent follicles that are better segmented at threshold 45 than are segmented at threshold 25. Each region of FIG. 6a contains a greater proportion of follicle size than the region of FIG. 6b; Region 204 in FIG. 6a has been identified as a single connected region. However, in FIG. 6b, the two regions 214 and 215 may be seen to correspond to the region 204 of FIG. 6a. Using a threshold of 45 leads to regions being merged incorrectly. Regions 214 and 215 may be better segmented at the 25 threshold than they are segmented at the 45 threshold, since the follicles will be mistakenly fused at the 45 threshold; For multiple sets of ultrasound image data or other medical imaging data, the optimal threshold for segmentation of all follicles in the image data may not be a single threshold. There can be a gradient in brightness across a single image. The image may have a shadow. Ultrasound can have various artifacts, such as echo reflections. Echo reflection artifacts can unnaturally increase the brightness of the subject; Using multiple thresholds means that the optimal threshold for segmenting one follicle is the optimal threshold for segmenting another follicle while each follicle is segmented using the appropriate threshold It is possible even if different; the threshold processing circuit 34 uses a predetermined set of threshold luminance values, which are luminance values ranging from 5 to 50 in five increments. The volume to be filtered is thresholded at several predetermined brightness levels. In other embodiments, the threshold processing circuit 34 may receive a set of thresholds from the memory 50, from another data store, or from user input. In some embodiments, the threshold processing circuit 34 may determine a set of thresholds. For example, the maximum and minimum luminance values for the preprocessed data set may be determined, and the result width of the value by a predetermined increment may be divided; the threshold processing circuit 34 executes threshold processing that is used to extract a region for each threshold, and then specifies connected component analysis and morphological hole filling processing using the threshold. Applicable to candidate follicular voxels. In other embodiments, the regions may be extracted based on threshold processing in any suitable manner. Connected component analysis and morphological hole filling may or may not be used. Any optimal morphological operation may be performed on the voxels identified as candidate follicular voxels. Morphological operations may be performed before or after connected component analysis; output of stage 108 is a set of extracted regions for each threshold. As described above, a higher threshold may result in a more widely extracted region and / or more extracted region than a region acquired for a lower threshold. Sometimes there may be a threshold that no extracted region is acquired; the selection circuit 36 uses a simple classifier to classify the extracted regions, which in this case are box classifiers (or also known as linear classifiers). If the predetermined extracted region is classified as a follicle by the classifier, it is selected by the selection circuit 36. If the extracted region is not classified as a follicle, it is not selected; the threshold processing circuit 34 uses a predetermined set of threshold luminance values, which are luminance values ranging from 5 to 50 in five increments. The volume to be filtered is thresholded at several predetermined brightness levels. In other embodiments, the threshold processing circuit 34 may receive a set of thresholds from the memory 50, from another data store, or from user input. In some embodiments, the threshold processing circuit 34 may determine a set of thresholds. For example, the maximum and minimum luminance values for the preprocessed data set may be determined, and the result width of the value by a predetermined increment may be divided; different classifiers may be used in different embodiments. For example, multivariate Gaussian, instruction vector machines, or other machine learning classifiers may be used; multiple candidate regions of tissue structures are selected by user other than initial tissue structure, and its location is output by plurality of learning classifiers (models) in a display based on location of tissue structures in its vicinities). Additionally, the rational and motivation to combine the references Shamir and Murphy as applied in rejection of claim 1 apply to this claim.
Claim 6 recite computer readable storage medium with instructions corresponding to the apparatus elements recited in Claim 1. Therefore, the
recited instructions of storage medium claim 6 are mapped to the proposed combination in the same manner as the corresponding elements of Claim 1. Additionally, the rationale and motivation to combine the Shamir and Murphy references presented in rejection of Claim 1, apply to this claim.
The combination of Shamir and Murphy further discloses A non-transitory computer-readable storage medium storing an ultrasound tomographic image processing program causing a computer, which is capable of accessing a first learning model that has been trained to predict a cross section type of an input ultrasound tomographic image and to output the cross section type and a plurality of second learning models each of which is associated with each cross section type of ultrasound tomographic images and has been trained to predict a tissue structure included in an ultrasound tomographic image of a corresponding cross section type and to output the tissue structure, to function (Shamir, ). Additionally, the rational and motivation to combine the references Shamir and Murphy as applied in rejection of claim 1 apply to this claim.
Allowable Subject Matter
Claim 5 would be allowable if rewritten to overcome the rejection(s) under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), 2nd paragraph, set forth in this Office action and to include all of the limitations of the base claim and any intervening claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
US-20160007972-A1 (Nishiura et al., To provide an ultrasonic imaging apparatus and an ultrasound image display method capable of preventing a three-dimensional ultrasound image from flickering due to an inappropriate ROI being calculated and improving the image quality of the ultrasound image. An ultrasonic imaging apparatus of the present invention is provided with: an ROI calculating section configured to calculate an ROI from ultrasound image data; a judgment section configured to judge whether the calculation of the ROI is successful or not on the basis of at least one of a position with a predetermined brightness difference and the number of positions with the brightness difference in the ultrasound image data; and a compensation section configured to compensate a failed ultrasound image based on the ROI judged to be failed by the judgment section with a successful ultrasound image based on the ROI judged to be successful by the judgment section, Abstract).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PINALBEN V PATEL whose telephone number is (571)270-5872. The examiner can normally be reached M-F: 10am - 8pm.
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, Chineyere Wills-Burns can be reached at 571-272-9752. 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.
/Pinalben Patel/Examiner, Art Unit 2673
Prosecution Insights