DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 10, 12, and 16 is/are rejected under 35 U.S.C. 103 as being anticipated by Zhang {Xuming} et al. (US 20230196528) in view of Tsukagoshi et al. (US 20140132597).
Regarding claim 1.
Zhang {Xuming} teaches:
A computer-implemented method for single rendering at least two sets of medical images of a patient (Zhang {Xuming} [0001] The present invention relates to the field of image fusion technologies in image processing and analysis, and more specifically, to a multimodal medical image fusion method based on a differentiable architecture search (DARTS) network.), the at least two sets of medical images covering an area of the patient (Zhang {Xuming} [0002] With the development of medical imaging technology, more and more medical imaging techniques such as ultrasound imaging (US), computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and single photon emission computed tomography (SPECT) have been applied to diagnosis and evaluation of diseases of various organs of the human body. Each medical imaging technique has advantages and disadvantages. For example, CT imaging covers all anatomical parts of the human body with high density resolution, but has low spatial resolution, poor joint and muscle display, and artifacts. MR imaging has high soft tissue resolution with no bone artifacts and overlap artifacts, but has the disadvantage of long scan time and lower spatial resolution than that of CT. Multimodal medical image fusion can integrate information specific to images with different modalities into one image, thereby facilitating observation and diagnosis by doctors. Therefore, multimodal medical image fusion plays an important role in clinical practice. For example, US and MRI are fused to implement prostate puncture biopsy, and PET and CT are fused to implement lung cancer detection.), the method comprising:
obtaining the at least two sets of medical images, each set of medical images covering one or more respective regions of interest (Zhang {Xuming} [0002] With the development of medical imaging technology, more and more medical imaging techniques such as ultrasound imaging (US), computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and single photon emission computed tomography (SPECT) have been applied to diagnosis and evaluation of diseases of various organs of the human body. Each medical imaging technique has advantages and disadvantages. For example, CT imaging covers all anatomical parts of the human body with high density resolution, but has low spatial resolution, poor joint and muscle display, and artifacts. MR imaging has high soft tissue resolution with no bone artifacts and overlap artifacts, but has the disadvantage of long scan time and lower spatial resolution than that of CT. Multimodal medical image fusion can integrate information specific to images with different modalities into one image, thereby facilitating observation and diagnosis by doctors. Therefore, multimodal medical image fusion plays an important role in clinical practice. For example, US and MRI are fused to implement prostate puncture biopsy, and PET and CT are fused to implement lung cancer detection.);
extracting the one or more respective regions of interest of each of the obtained at least two sets of medical images (Zhang {Xuming} [0027] FIG. 3(a) shows a source CT image used in an embodiment of the present invention and a compared method; [0028] FIG. 3(b) shows a source MR image used in an embodiment of the present invention and a compared method; [0029] FIG. 4(a) shows a fused image obtained through NSCT-SR in Compared Method 1;);
and assembling the extracted respective regions of interest into a single set of images (Zhang {Xuming} [0002] Therefore, multimodal medical image fusion plays an important role in clinical practice. For example, US and MRI are fused to implement prostate puncture biopsy, and PET and CT are fused to implement lung cancer detection. [0006] In view of the deficiencies and improvement requirements in the prior art, the present invention provides a multimodal medical image fusion method based on a differentiable architecture search (DARTS) network, thereby improving image quality after multimodal medical image fusion.).
Zhang fails to teach:
extracting the one or more respective regions of interest of each of the obtained at least two sets of medical images (Tsukagoshi [0113] It is possible to extract a region of interest by using a PET image in the manner described above, not only when three-dimensional CT images corresponding to mutually-different time phases are superimposed together, but also when three-dimensional fused images corresponding to mutually-different time phases are superimposed together. When the fused images corresponding to the mutually-different time phases are superimposed together, the viewer is able to not only assess whether the tumor is malignant or not, but also spatially understand the manner in which the malignant tumor metastasizes.);
Tsukagoshi teaches:
extracting the one or more respective regions of interest of each of the obtained at least two sets of medical images (Tsukagoshi [0113] It is possible to extract a region of interest by using a PET image in the manner described above, not only when three-dimensional CT images corresponding to mutually-different time phases are superimposed together, but also when three-dimensional fused images corresponding to mutually-different time phases are superimposed together. When the fused images corresponding to the mutually-different time phases are superimposed together, the viewer is able to not only assess whether the tumor is malignant or not, but also spatially understand the manner in which the malignant tumor metastasizes.);
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to combine the teachings of Zhang {Xuming} with ref1. Extracting regions in images and then fusing, as in Tsukagoshi, would benefit the Zhang {Xuming} teachings by allowing for the ability to fuse a certain region of interest. Additionally, this is the application of a known technique, extracting regions in images and then fusing, to yield predictable results.
Regarding claim 10.
Zhang {Xuming} and Tsukagoshi teach:
The method of claim 1,
further comprising, prior to the extracting: aligning the at least two sets of medical images, the extracting being performed on the aligned at least two sets of medical images (Zhang {Xuming} [0004] Deep learning can learn feature information from a large number of samples, and has been widely used in image processing and analysis tasks such as image segmentation, image alignment, and image fusion in recent years.).
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to combine the teachings of Zhang {Xuming} with ref1. Extracting regions in images and then fusing, as in Tsukagoshi, would benefit the Zhang {Xuming} teachings by allowing for the ability to fuse a certain region of interest. Additionally, this is the application of a known technique, extracting regions in images and then fusing, to yield predictable results.
Regarding claim 12.
Zhang {Xuming} teaches:
A non-transitory computer readable storage medium having recorded thereon a computer program having instructions for performing a method for single rendering at least two sets of medical images of a patient (Zhang {Xuming} [0001] The present invention relates to the field of image fusion technologies in image processing and analysis, and more specifically, to a multimodal medical image fusion method based on a differentiable architecture search (DARTS) network.), the at least two sets of medical images covering an area of the patient (Zhang {Xuming} [0002] With the development of medical imaging technology, more and more medical imaging techniques such as ultrasound imaging (US), computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and single photon emission computed tomography (SPECT) have been applied to diagnosis and evaluation of diseases of various organs of the human body. Each medical imaging technique has advantages and disadvantages. For example, CT imaging covers all anatomical parts of the human body with high density resolution, but has low spatial resolution, poor joint and muscle display, and artifacts. MR imaging has high soft tissue resolution with no bone artifacts and overlap artifacts, but has the disadvantage of long scan time and lower spatial resolution than that of CT. Multimodal medical image fusion can integrate information specific to images with different modalities into one image, thereby facilitating observation and diagnosis by doctors. Therefore, multimodal medical image fusion plays an important role in clinical practice. For example, US and MRI are fused to implement prostate puncture biopsy, and PET and CT are fused to implement lung cancer detection.), the method comprising:
obtaining the at least two sets of medical images, each set of medical images covering one or more respective regions of interest (Zhang {Xuming} [0002] With the development of medical imaging technology, more and more medical imaging techniques such as ultrasound imaging (US), computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and single photon emission computed tomography (SPECT) have been applied to diagnosis and evaluation of diseases of various organs of the human body. Each medical imaging technique has advantages and disadvantages. For example, CT imaging covers all anatomical parts of the human body with high density resolution, but has low spatial resolution, poor joint and muscle display, and artifacts. MR imaging has high soft tissue resolution with no bone artifacts and overlap artifacts, but has the disadvantage of long scan time and lower spatial resolution than that of CT. Multimodal medical image fusion can integrate information specific to images with different modalities into one image, thereby facilitating observation and diagnosis by doctors. Therefore, multimodal medical image fusion plays an important role in clinical practice. For example, US and MRI are fused to implement prostate puncture biopsy, and PET and CT are fused to implement lung cancer detection.);
and assembling the extracted respective regions of interest into a single set of images (Zhang {Xuming} [0006] In view of the deficiencies and improvement requirements in the prior art, the present invention provides a multimodal medical image fusion method based on a differentiable architecture search (DARTS) network, thereby improving image quality after multimodal medical image fusion.).
Zhang fails to teach:
extracting the one or more respective regions of interest of each of the obtained at least two sets of medical images (Tsukagoshi [0113] It is possible to extract a region of interest by using a PET image in the manner described above, not only when three-dimensional CT images corresponding to mutually-different time phases are superimposed together, but also when three-dimensional fused images corresponding to mutually-different time phases are superimposed together. When the fused images corresponding to the mutually-different time phases are superimposed together, the viewer is able to not only assess whether the tumor is malignant or not, but also spatially understand the manner in which the malignant tumor metastasizes.);
Tsukagoshi teaches:
extracting the one or more respective regions of interest of each of the obtained at least two sets of medical images (Tsukagoshi [0113] It is possible to extract a region of interest by using a PET image in the manner described above, not only when three-dimensional CT images corresponding to mutually-different time phases are superimposed together, but also when three-dimensional fused images corresponding to mutually-different time phases are superimposed together. When the fused images corresponding to the mutually-different time phases are superimposed together, the viewer is able to not only assess whether the tumor is malignant or not, but also spatially understand the manner in which the malignant tumor metastasizes.);
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to combine the teachings of Zhang {Xuming} with ref1. Extracting regions in images and then fusing, as in Tsukagoshi, would benefit the Zhang {Xuming} teachings by allowing for the ability to fuse a certain region of interest. Additionally, this is the application of a known technique, extracting regions in images and then fusing, to yield predictable results.
Regarding claim 16.
Zhang {Xuming} teaches:
A computer system comprising:a processor coupled to a memory, the memory having recorded thereon a computer program having instructions for single rendering at least two sets of medical images of a patient (Zhang {Xuming} [0001] The present invention relates to the field of image fusion technologies in image processing and analysis, and more specifically, to a multimodal medical image fusion method based on a differentiable architecture search (DARTS) network.),
the at least two sets of medical images covering an area of the patient (Zhang {Xuming} [0002] With the development of medical imaging technology, more and more medical imaging techniques such as ultrasound imaging (US), computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and single photon emission computed tomography (SPECT) have been applied to diagnosis and evaluation of diseases of various organs of the human body. Each medical imaging technique has advantages and disadvantages. For example, CT imaging covers all anatomical parts of the human body with high density resolution, but has low spatial resolution, poor joint and muscle display, and artifacts. MR imaging has high soft tissue resolution with no bone artifacts and overlap artifacts, but has the disadvantage of long scan time and lower spatial resolution than that of CT. Multimodal medical image fusion can integrate information specific to images with different modalities into one image, thereby facilitating observation and diagnosis by doctors. Therefore, multimodal medical image fusion plays an important role in clinical practice. For example, US and MRI are fused to implement prostate puncture biopsy, and PET and CT are fused to implement lung cancer detection.),
the method comprising: obtaining the at least two sets of medical images, each set of medical images covering one or more respective regions of interest (Zhang {Xuming} [0002] With the development of medical imaging technology, more and more medical imaging techniques such as ultrasound imaging (US), computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and single photon emission computed tomography (SPECT) have been applied to diagnosis and evaluation of diseases of various organs of the human body. Each medical imaging technique has advantages and disadvantages. For example, CT imaging covers all anatomical parts of the human body with high density resolution, but has low spatial resolution, poor joint and muscle display, and artifacts. MR imaging has high soft tissue resolution with no bone artifacts and overlap artifacts, but has the disadvantage of long scan time and lower spatial resolution than that of CT. Multimodal medical image fusion can integrate information specific to images with different modalities into one image, thereby facilitating observation and diagnosis by doctors. Therefore, multimodal medical image fusion plays an important role in clinical practice. For example, US and MRI are fused to implement prostate puncture biopsy, and PET and CT are fused to implement lung cancer detection.);
and assembling the extracted respective regions of interest into a single set of images (Zhang {Xuming} [0006] In view of the deficiencies and improvement requirements in the prior art, the present invention provides a multimodal medical image fusion method based on a differentiable architecture search (DARTS) network, thereby improving image quality after multimodal medical image fusion.).
Zhang fails to teach:
extracting the one or more respective regions of interest of each of the obtained at least two sets of medical images (Tsukagoshi [0113] It is possible to extract a region of interest by using a PET image in the manner described above, not only when three-dimensional CT images corresponding to mutually-different time phases are superimposed together, but also when three-dimensional fused images corresponding to mutually-different time phases are superimposed together. When the fused images corresponding to the mutually-different time phases are superimposed together, the viewer is able to not only assess whether the tumor is malignant or not, but also spatially understand the manner in which the malignant tumor metastasizes.);
Tsukagoshi teaches:
extracting the one or more respective regions of interest of each of the obtained at least two sets of medical images (Tsukagoshi [0113] It is possible to extract a region of interest by using a PET image in the manner described above, not only when three-dimensional CT images corresponding to mutually-different time phases are superimposed together, but also when three-dimensional fused images corresponding to mutually-different time phases are superimposed together. When the fused images corresponding to the mutually-different time phases are superimposed together, the viewer is able to not only assess whether the tumor is malignant or not, but also spatially understand the manner in which the malignant tumor metastasizes.);
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to combine the teachings of Zhang {Xuming} with ref1. Extracting regions in images and then fusing, as in Tsukagoshi, would benefit the Zhang {Xuming} teachings by allowing for the ability to fuse a certain region of interest. Additionally, this is the application of a known technique, extracting regions in images and then fusing, to yield predictable results.
Claim(s) 2, 13, and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang {Xuming} et al. (US 20230196528) in view of Tsukagoshi et al. (US 20140132597), Zhang {Xiao-dong} et al. (CN 108038862) and Wang et al. (CN 113344940).
Regarding claim 2.
Zhang {Xuming} and Tsukagoshi teach:
The method of claim 1,
Zhang {Xuming} and Tsukagoshi fail to teach:
wherein the extracting comprises: segmenting the obtained at least two sets of medical images, thereby generating a respective preliminary binary segmentation mask for each set of medical images (Zhang {Xiao-dong} [Pg 5 Par 7] The invention claims an interactive medical image intelligent segmentation modeling method, compared with the existing technology, the invention by simply drawing the outline of the target area on the minority tangent plane, which can quickly obtain the target area of the 3 D surface network and binary segmentation MASK, simple operation and high efficiency.);
computing an intersection between all the generated preliminary binary segmentation masks, thereby obtaining a common mask of one or more common regions of the obtained at least two sets of medical images (Zhang {Xiao-dong} [Pg 5 Par 7] again, when marking the 2 D section outline of the target area, automatically calculating the coordinate and the outline intersection point, effectively avoiding the surface grid defect caused by the binary outline point.);
and for each set of medical images, subtracting the obtained common mask from the respective preliminary binary segmentation mask generated for the set of medical images, thereby obtaining a respective final binary segmentation mask of the one or more respective regions of interest for the set of medical images (Wang [Pg 5 Par 3] In this embodiment, the mask image of the mask image and the mis-divided region mask image is by manual marking the drain division region and the error division region, the specific drain division region and the error division region obtaining method can be: calculating the liver blood vessel segmentation mask and the common area mask of the blood vessel mask in the step one; in step one, the blood vessel mask subtracts the common area mask to obtain the mask image of the drain division area; calculating to obtain the liver blood vessel division mask minus the blood vessel mask in the step one to obtain the mask image in the wrong division area.).
Zhang {Xiao-dong} teaches:
wherein the extracting comprises: segmenting the obtained at least two sets of medical images, thereby generating a respective preliminary binary segmentation mask for each set of medical images (Zhang {Xiao-dong} [Pg 5 Par 7] The invention claims an interactive medical image intelligent segmentation modeling method, compared with the existing technology, the invention by simply drawing the outline of the target area on the minority tangent plane, which can quickly obtain the target area of the 3 D surface network and binary segmentation MASK, simple operation and high efficiency.);
computing an intersection between all the generated preliminary binary segmentation masks, thereby obtaining a common mask of one or more common regions of the obtained at least two sets of medical images (Zhang {Xiao-dong} [Pg 5 Par 7] again, when marking the 2 D section outline of the target area, automatically calculating the coordinate and the outline intersection point, effectively avoiding the surface grid defect caused by the binary outline point.);
Wang teaches:
and for each set of medical images, subtracting the obtained common mask from the respective preliminary binary segmentation mask generated for the set of medical images, thereby obtaining a respective final binary segmentation mask of the one or more respective regions of interest for the set of medical images (Wang [Pg 5 Par 3] In this embodiment, the mask image of the mask image and the mis-divided region mask image is by manual marking the drain division region and the error division region, the specific drain division region and the error division region obtaining method can be: calculating the liver blood vessel segmentation mask and the common area mask of the blood vessel mask in the step one; in step one, the blood vessel mask subtracts the common area mask to obtain the mask image of the drain division area; calculating to obtain the liver blood vessel division mask minus the blood vessel mask in the step one to obtain the mask image in the wrong division area.).
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to combine the teachings of Zhang {Xuming} and Tsukagoshi with Zhang {Xiao-dong} and Wang. Generating binary segmentation masks, intersection points, and subtracting the mask, as in Zhang {Xiao-dong} and Wang, would benefit the Zhang {Xuming} and Tsukagoshi teachings by allowing for further processing on the mask. Additionally, this is the application of a known technique, generating binary segmentation masks, intersection points, and subtracting the mask, to yield predictable results.
Regarding claim 13
Zhang {Xuming} and Tsukagoshi teach:
The non-transitory computer readable storage medium of claim 12,
Zhang {Xuming} and Tsukagoshi fail to teach:
wherein the extracting includes: segmenting the obtained at least two sets of medical images, thereby generating a respective preliminary binary segmentation mask for each set of medical images (Zhang {Xiao-dong} [Pg 5 Par 7] The invention claims an interactive medical image intelligent segmentation modeling method, compared with the existing technology, the invention by simply drawing the outline of the target area on the minority tangent plane, which can quickly obtain the target area of the 3 D surface network and binary segmentation MASK, simple operation and high efficiency.);
computing an intersection between all the generated preliminary binary segmentation masks, thereby obtaining a common mask of one or more common regions of the obtained at least two sets of medical images (Zhang {Xiao-dong} [Pg 5 Par 7] again, when marking the 2 D section outline of the target area, automatically calculating the coordinate and the outline intersection point, effectively avoiding the surface grid defect caused by the binary outline point.);
and for each set of medical images, subtracting the obtained common mask from the respective preliminary binary segmentation mask generated for the set of medical images, thereby obtaining a respective final binary segmentation mask of the one or more respective regions of interest for the set of medical images (Wang [Pg 5 Par 3] In this embodiment, the mask image of the mask image and the mis-divided region mask image is by manual marking the drain division region and the error division region, the specific drain division region and the error division region obtaining method can be: calculating the liver blood vessel segmentation mask and the common area mask of the blood vessel mask in the step one; in step one, the blood vessel mask subtracts the common area mask to obtain the mask image of the drain division area; calculating to obtain the liver blood vessel division mask minus the blood vessel mask in the step one to obtain the mask image in the wrong division area.).
Zhang {Xiao-dong} teaches:
wherein the extracting comprises: segmenting the obtained at least two sets of medical images, thereby generating a respective preliminary binary segmentation mask for each set of medical images (Zhang {Xiao-dong} [Pg 5 Par 7] The invention claims an interactive medical image intelligent segmentation modeling method, compared with the existing technology, the invention by simply drawing the outline of the target area on the minority tangent plane, which can quickly obtain the target area of the 3 D surface network and binary segmentation MASK, simple operation and high efficiency.);
computing an intersection between all the generated preliminary binary segmentation masks, thereby obtaining a common mask of one or more common regions of the obtained at least two sets of medical images (Zhang {Xiao-dong} [Pg 5 Par 7] again, when marking the 2 D section outline of the target area, automatically calculating the coordinate and the outline intersection point, effectively avoiding the surface grid defect caused by the binary outline point.);
Wang teaches:
and for each set of medical images, subtracting the obtained common mask from the respective preliminary binary segmentation mask generated for the set of medical images, thereby obtaining a respective final binary segmentation mask of the one or more respective regions of interest for the set of medical images (Wang [Pg 5 Par 3] In this embodiment, the mask image of the mask image and the mis-divided region mask image is by manual marking the drain division region and the error division region, the specific drain division region and the error division region obtaining method can be: calculating the liver blood vessel segmentation mask and the common area mask of the blood vessel mask in the step one; in step one, the blood vessel mask subtracts the common area mask to obtain the mask image of the drain division area; calculating to obtain the liver blood vessel division mask minus the blood vessel mask in the step one to obtain the mask image in the wrong division area.).
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to combine the teachings of Zhang {Xuming} and Tsukagoshi with Zhang {Xiao-dong} and Wang. Generating binary segmentation masks, intersection points, and subtracting the mask, as in Zhang {Xiao-dong} and Wang, would benefit the Zhang {Xuming} and Tsukagoshi teachings by allowing for further processing on the mask. Additionally, this is the application of a known technique, generating binary segmentation masks, intersection points, and subtracting the mask, to yield predictable results.
Regarding claim 17
Zhang {Xuming} and Tsukagoshi teach:
The computer system of claim 16,
Zhang {Xuming} and Tsukagoshi fail to teach:
wherein the processor is further configured to extract the one or more respective regions of interest by being configured to: segmenting the obtained at least two sets of medical images, thereby generating a respective preliminary binary segmentation mask for each set of medical images (Zhang {Xiao-dong} [Pg 5 Par 7] The invention claims an interactive medical image intelligent segmentation modeling method, compared with the existing technology, the invention by simply drawing the outline of the target area on the minority tangent plane, which can quickly obtain the target area of the 3 D surface network and binary segmentation MASK, simple operation and high efficiency.);
computing an intersection between all the generated preliminary binary segmentation masks, thereby obtaining a common mask of one or more common regions of the obtained at least two sets of medical images (Zhang {Xiao-dong} [Pg 5 Par 7] again, when marking the 2 D section outline of the target area, automatically calculating the coordinate and the outline intersection point, effectively avoiding the surface grid defect caused by the binary outline point.);
and for each set of medical images, subtracting the obtained common mask from the respective preliminary binary segmentation mask generated for the set of medical images, thereby obtaining a respective final binary segmentation mask of the one or more respective regions of interest for the set of medical images (Wang [Pg 5 Par 3] In this embodiment, the mask image of the mask image and the mis-divided region mask image is by manual marking the drain division region and the error division region, the specific drain division region and the error division region obtaining method can be: calculating the liver blood vessel segmentation mask and the common area mask of the blood vessel mask in the step one; in step one, the blood vessel mask subtracts the common area mask to obtain the mask image of the drain division area; calculating to obtain the liver blood vessel division mask minus the blood vessel mask in the step one to obtain the mask image in the wrong division area.).
Zhang {Xiao-dong} teaches:
wherein the extracting comprises: segmenting the obtained at least two sets of medical images, thereby generating a respective preliminary binary segmentation mask for each set of medical images (Zhang {Xiao-dong} [Pg 5 Par 7] The invention claims an interactive medical image intelligent segmentation modeling method, compared with the existing technology, the invention by simply drawing the outline of the target area on the minority tangent plane, which can quickly obtain the target area of the 3 D surface network and binary segmentation MASK, simple operation and high efficiency.);
computing an intersection between all the generated preliminary binary segmentation masks, thereby obtaining a common mask of one or more common regions of the obtained at least two sets of medical images (Zhang {Xiao-dong} [Pg 5 Par 7] again, when marking the 2 D section outline of the target area, automatically calculating the coordinate and the outline intersection point, effectively avoiding the surface grid defect caused by the binary outline point.);
Wang teaches:
and for each set of medical images, subtracting the obtained common mask from the respective preliminary binary segmentation mask generated for the set of medical images, thereby obtaining a respective final binary segmentation mask of the one or more respective regions of interest for the set of medical images (Wang [Pg 5 Par 3] In this embodiment, the mask image of the mask image and the mis-divided region mask image is by manual marking the drain division region and the error division region, the specific drain division region and the error division region obtaining method can be: calculating the liver blood vessel segmentation mask and the common area mask of the blood vessel mask in the step one; in step one, the blood vessel mask subtracts the common area mask to obtain the mask image of the drain division area; calculating to obtain the liver blood vessel division mask minus the blood vessel mask in the step one to obtain the mask image in the wrong division area.).
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to combine the teachings of Zhang {Xuming} and Tsukagoshi with Zhang {Xiao-dong} and Wang. Generating binary segmentation masks, intersection points, and subtracting the mask, as in Zhang {Xiao-dong} and Wang, would benefit the Zhang {Xuming} and Tsukagoshi teachings by allowing for further processing on the mask. Additionally, this is the application of a known technique, generating binary segmentation masks, intersection points, and subtracting the mask, to yield predictable results.
Regarding claim 20
Zhang {Xuming} and Tsukagoshi teach:
The computer system of claim 16,
Zhang {Xuming} and Tsukagoshi fail to teach:
further comprising a viewer, the viewer comprising a graphical user interface configured for displaying the single set of images (Zhang {Xiao-dong} [Pg 2 Par 4] An interactive medical image intelligent segmentation modeling method, comprising the following steps: step S1, obtaining medical image data; step S2, introducing the medical image data into the image processing system, and displaying the image in the multi-display window;).
Zhang {Xiao-dong} and Wang teach:
further comprising a viewer, the viewer comprising a graphical user interface configured for displaying the single set of images (Zhang {Xiao-dong} [Pg 2 Par 4] An interactive medical image intelligent segmentation modeling method, comprising the following steps: step S1, obtaining medical image data; step S2, introducing the medical image data into the image processing system, and displaying the image in the multi-display window;).
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to combine the teachings of Zhang {Xuming} with Zhang {Xiao-dong} and Wang. Generating binary segmentation masks, intersection points, and subtracting the mask, as in Zhang {Xiao-dong} and Wang, would benefit the Zhang {Xuming} teachings by allowing for further processing on the mask. Additionally, this is the application of a known technique, generating binary segmentation masks, intersection points, and subtracting the mask, to yield predictable results.
Claim(s) 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang {Xuming} et al. (US 20230196528) in view of Tsukagoshi et al. (US 20140132597) and Carbonera et al. (US 20130169638).
Regarding claim 5.
Zhang {Xuming} and Tsukagoshi teach:
The method of claim 1,
Zhang {Xiao-dong} and Tsukagoshi fail to teach:
wherein the single set of images defines a voxel grid, the assembling including assigning a respective value to each voxel of the voxel grid by performing, for each voxel (Carbonera [0085] As briefly described above, once the voxel grid 54 is constructed, the processing apparatus 16 is configured to determine which voxels 56 of the grid 54 are to be used in the generation of the surface model of the region of interest (Step 108).):
determining whether the voxel belongs to one of the respective regions of interest of one of the at least two sets of medical images (Carbonera [0085] As briefly described above, once the voxel grid 54 is constructed, the processing apparatus 16 is configured to determine which voxels 56 of the grid 54 are to be used in the generation of the surface model of the region of interest (Step 108).);
and if the voxel belongs to one of the respective regions of interest, assigning a respective value to the voxel according to the set of medical images from which a respective mask having the respective regions of interest to which the voxel belongs is obtained (Carbonera [0118] In general terms, the processing apparatus 16 is configured to compute/calculate the Boolean Union approximation in much the same manner as that of the generation of the individual surface models 58 described above. More particularly, in an exemplary embodiment, the processing apparatus 16 is configured to first calculate or construct a grid of voxels from the multi-faceted surfaces corresponding to the individual regions of interest. In other words, two or more multi-faceted surfaces of two or more individual surface models are combined into one common voxel grid. For purposes of illustration, FIG. 16 depicts a voxel grid 66 calculated for a pair of simplified, oval-shaped surface models corresponding to different regions of a structure of interest that are to be joined to create a composite surface model. Once the voxel grid 66 is calculated or constructed, the processing apparatus 16 is configured to extract a single, composite multi-faceted surface model from the voxel grid 66 using, for example, a Marching Cubes algorithm. In an exemplary embodiment, the processing apparatus 16 is then configured to decimate and/or smooth the resulting multi-faceted surface in the same or similar manner as was described above with respect to the generation of the individual surface models 58.).
Carbonera teaches:
wherein the single set of images defines a voxel grid, the assembling including assigning a respective value to each voxel of the voxel grid by performing, for each voxel (Carbonera [0085] As briefly described above, once the voxel grid 54 is constructed, the processing apparatus 16 is configured to determine which voxels 56 of the grid 54 are to be used in the generation of the surface model of the region of interest (Step 108).):
determining whether the voxel belongs to one of the respective regions of interest of one of the at least two sets of medical images (Carbonera [0085] As briefly described above, once the voxel grid 54 is constructed, the processing apparatus 16 is configured to determine which voxels 56 of the grid 54 are to be used in the generation of the surface model of the region of interest (Step 108).);
and if the voxel belongs to one of the respective regions of interest, assigning a respective value to the voxel according to the set of medical images from which a respective mask having the respective regions of interest to which the voxel belongs is obtained (Carbonera [0118] In general terms, the processing apparatus 16 is configured to compute/calculate the Boolean Union approximation in much the same manner as that of the generation of the individual surface models 58 described above. More particularly, in an exemplary embodiment, the processing apparatus 16 is configured to first calculate or construct a grid of voxels from the multi-faceted surfaces corresponding to the individual regions of interest. In other words, two or more multi-faceted surfaces of two or more individual surface models are combined into one common voxel grid. For purposes of illustration, FIG. 16 depicts a voxel grid 66 calculated for a pair of simplified, oval-shaped surface models corresponding to different regions of a structure of interest that are to be joined to create a composite surface model. Once the voxel grid 66 is calculated or constructed, the processing apparatus 16 is configured to extract a single, composite multi-faceted surface model from the voxel grid 66 using, for example, a Marching Cubes algorithm. In an exemplary embodiment, the processing apparatus 16 is then configured to decimate and/or smooth the resulting multi-faceted surface in the same or similar manner as was described above with respect to the generation of the individual surface models 58.).
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to combine the teachings of Zhang {Xuming} and Tsukagoshi with Carbonera. Being able to determine a voxel grid and being able to process those voxels by having them be part of a specific region, as in Carbonera, would benefit the Zhang {Xuming} and Tsukagoshi teachings by allowing for more precise processing of the image. Additionally, this is the application of a known technique, being able to determine a voxel grid and being able to process those voxels by having them be part of a specific region, to yield predictable results.
Claim(s) 6-7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang {Xuming} et al. (US 20230196528) in view of Tsukagoshi et al. (US 20140132597), Carbonera et al. (US 20130169638) and Lee et al. (WO 2023017919).
Regarding claim 6.
Zhang {Xuming}, Tsukagoshi, and Carbonera teach:
The method of claim 5,
Zhang {Xuming}, Tsukagoshi, and Carbonera fail to teach:
wherein the obtaining of the at least two sets of medical images includes obtaining a set of labels each corresponding to a respective set of medical images, and wherein the assigning of the respective value includes assigning the respective label associated to the set of medical images having the respective region of interest to which the voxel belongs (Lee [Pg 6 Par 4] Meanwhile, although not shown in FIG. 1 , the medical image analysis apparatus 1000 may include any suitable input unit and/or output unit. In detail, the medical image analysis apparatus 1000 may receive a user's input necessary for analyzing a medical image through an input unit. For example, the medical image analysis apparatus 1000 may obtain a user's input for allocating label information to each of a plurality of areas included in a medical image through an input unit. As another example, the medical image analysis apparatus 1000 may obtain a user's input for setting a region of interest of a joint interval region for acquiring a joint interval value through an input unit.).
Lee teaches:
wherein the obtaining of the at least two sets of medical images includes obtaining a set of labels each corresponding to a respective set of medical images, and wherein the assigning of the respective value includes assigning the respective label associated to the set of medical images having the respective region of interest to which the voxel belongs (Lee [Pg 6 Par 4] Meanwhile, although not shown in FIG. 1 , the medical image analysis apparatus 1000 may include any suitable input unit and/or output unit. In detail, the medical image analysis apparatus 1000 may receive a user's input necessary for analyzing a medical image through an input unit. For example, the medical image analysis apparatus 1000 may obtain a user's input for allocating label information to each of a plurality of areas included in a medical image through an input unit. As another example, the medical image analysis apparatus 1000 may obtain a user's input for setting a region of interest of a joint interval region for acquiring a joint interval value through an input unit.).
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to combine the teachings of Zhang {Xuming}, Tsukagoshi, and Carbonera with Lee. Having a certain value assigned to each location, as in Lee, would benefit the Zhang {Xuming}, Tsukagoshi, and Carbonera teachings by allowing for each voxel to be a part of a certain type. Additionally, this is the application of a known technique, having certain parts of an image being labeled is common in the art to yield predictable results.
Regarding claim 7.
Zhang {Xuming}, Tsukagoshi, and Carbonera teach:
The method of claim 5,
Zhang {Xuming}, Tsukagoshi, and Carbonera fail to teach:
wherein the assigning of the respective value includes assigning the respective value equal to a value in a corresponding location of the set of medical images having the respective regions of interest to which the voxel belongs (Lee [Pg 6 Par 4] Meanwhile, although not shown in FIG. 1 , the medical image analysis apparatus 1000 may include any suitable input unit and/or output unit. In detail, the medical image analysis apparatus 1000 may receive a user's input necessary for analyzing a medical image through an input unit. For example, the medical image analysis apparatus 1000 may obtain a user's input for allocating label information to each of a plurality of areas included in a medical image through an input unit. As another example, the medical image analysis apparatus 1000 may obtain a user's input for setting a region of interest of a joint interval region for acquiring a joint interval value through an input unit.).
Lee teaches:
wherein the assigning of the respective value includes assigning the respective value equal to a value in a corresponding location of the set of medical images having the respective regions of interest to which the voxel belongs (Lee [Pg 6 Par 4] Meanwhile, although not shown in FIG. 1 , the medical image analysis apparatus 1000 may include any suitable input unit and/or output unit. In detail, the medical image analysis apparatus 1000 may receive a user's input necessary for analyzing a medical image through an input unit. For example, the medical image analysis apparatus 1000 may obtain a user's input for allocating label information to each of a plurality of areas included in a medical image through an input unit. As another example, the medical image analysis apparatus 1000 may obtain a user's input for setting a region of interest of a joint interval region for acquiring a joint interval value through an input unit.).
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to combine the teachings of Zhang {Xuming}, Tsukagoshi, and Carbonera with Lee. Having a certain value assigned to each location, as in Lee, would benefit the Zhang {Xuming}, Tsukagoshi, and Carbonera teachings by allowing for each voxel to be a part of a certain type. Additionally, this is the application of a known technique, having certain parts of an image being labeled is common in the art to yield predictable results.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang {Xuming} et al. (US 20230196528) in view of Tsukagoshi et al. (US 20140132597), Carbonera et al. (US 20130169638), Sjostrand et al. (US 20190209116), and Georgescu et al. (US 20200193594).
Regarding claim 8.
Zhang {Xuming}, Tsukagoshi, and Carbonera teach:
The method of claim 5,
Zhang {Xuming}, Tsukagoshi, and Carbonera fail to teach:
wherein the respective value assigned to the voxel is equal to a result of an addition of:
a value in a corresponding location of the set of medical images having the respective regions of interest to which the voxel belongs (Sjostrand [0034] In certain embodiments, the method comprises: identifying, by the processor, (e.g., using the second module) a bladder volume within the 3D anatomical image (e.g., within the initial VOI) corresponding to a bladder of the subject; determining, by the processor, a dilated bladder volume by applying a morphological dilation operation to the identified bladder volume; and at step (e), determining the one or more uptake metrics using intensity values of voxels of the 3D functional image that (i) correspond to the prostate volume identified within the VOI of the 3D anatomical image, but (ii) do not correspond to regions of the 3D anatomical image within the dilated bladder volume (e.g., thereby omitting from the computation of the one or more uptake metrics those voxels of the 3D functional image that correspond to locations in the 3D anatomical image within a predefined distance from the identified bladder volume; e.g., and, accordingly, are excessively close to the identified bladder volume)),
and an offset which depends on the set of medical images having the respective regions of interest to which the voxel belongs (Georgescu [0028] The lymph nodes are identified in the medical image data by determining the location of the lymph nodes from probability map 304 through further processing. In one embodiment, locations of lymph nodes are extracted from probability map 304 via non-maximum suppression and scale support filtering. A lymph node location candidate is extracted from probability map 304 if the output at that voxel is a local maxima (non-maxima suppression) and if there is enough support around it to match a Gaussian shape (scale support filtering). As a result, a detected lymph node will have a location (the voxel with a local max probability), a probability value, and a scale estimate (the scale of the best local fitting Gaussian to the probability map).).
Sjostrand teaches:
wherein the respective value assigned to the voxel is equal to a result of an addition of:
a value in a corresponding location of the set of medical images having the respective regions of interest to which the voxel belongs (Sjostrand [0034] In certain embodiments, the method comprises: identifying, by the processor, (e.g., using the second module) a bladder volume within the 3D anatomical image (e.g., within the initial VOI) corresponding to a bladder of the subject; determining, by the processor, a dilated bladder volume by applying a morphological dilation operation to the identified bladder volume; and at step (e), determining the one or more uptake metrics using intensity values of voxels of the 3D functional image that (i) correspond to the prostate volume identified within the VOI of the 3D anatomical image, but (ii) do not correspond to regions of the 3D anatomical image within the dilated bladder volume (e.g., thereby omitting from the computation of the one or more uptake metrics those voxels of the 3D functional image that correspond to locations in the 3D anatomical image within a predefined distance from the identified bladder volume; e.g., and, accordingly, are excessively close to the identified bladder volume)),
Georgescu teaches:
and an offset which depends on the set of medical images having the respective regions of interest to which the voxel belongs (Georgescu [0028] The lymph nodes are identified in the medical image data by determining the location of the lymph nodes from probability map 304 through further processing. In one embodiment, locations of lymph nodes are extracted from probability map 304 via non-maximum suppression and scale support filtering. A lymph node location candidate is extracted from probability map 304 if the output at that voxel is a local maxima (non-maxima suppression) and if there is enough support around it to match a Gaussian shape (scale support filtering). As a result, a detected lymph node will have a location (the voxel with a local max probability), a probability value, and a scale estimate (the scale of the best local fitting Gaussian to the probability map).).
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to combine the teachings of Zhang {Xuming}, Tsukagoshi, and Carbonera with Sjostrand and Georgescu. Having a certain value assigned to each location and being able to move the offset by allowing for a region to be bigger, as in Sjostrand and Georgescu, would benefit the Zhang {Xuming}, Tsukagoshi, and Carbonera teachings by allowing for each voxel to be a part of a certain type. Additionally, this is the application of a known technique, having certain parts of an image being labeled is common in the art to yield predictable results.
Allowable Subject Matter
Claims 3, 4, 9, 11, 14, 15, 18, and 19 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 DENIS VASILIY MINKO whose telephone number is (571)270-5226. The examiner can normally be reached Monday-Thursday 8:30-6:00 EST.
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, Said Broome can be reached at 571-272-2931. 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.
/DENIS VASILIY MINKO/Examiner, Art Unit 2612
/Said Broome/Supervisory Patent Examiner, Art Unit 2612
Prosecution Insights