DETAILED ACTION
This office action is in response to the communication received on 11/27/2025 concerning application no. 18/565,917 filed on 11/30/2023.
Claims 1-81 are pending (Claims 28-81 are withdrawn from consideration).
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 .
Election/Restrictions
Applicant's election with traverse of Group I (Claims 1-27) in the reply filed on 11/27/2025 is acknowledged. The traversal is on the ground(s) that the prior art “fails to teach the deterministic operations for alignment and isotropication.” Applicant argues that the “The claimed feature requires ‘performing deterministic operations to transform the independent MRI segments of complementary planes into a common reference frame, which includes a voxel isotropication process to generate enhanced representations of the MRI segments with isotropic voxels, and an image alignment process that allows the anatomical superposition of different image plane views’.” Applicant argues that Lang1 and Wang2 references do not address this. Similarly, Applicant argues that the “The claimed feature further requires ‘using a multi-planar combination model that comprises the application of a U-shaped CNN to the set of previously processed MRI segments in order to produce a unique high-resolution and quasi-isotropic volumetric representation’” and Lang3 and Wang4 fail to provide this. Furthermore, Applicant argues that there is a technical contribution and unity across the claims.
This is not found persuasive because allegation that the “The claimed feature requires ‘performing deterministic operations to transform the independent MRI segments of complementary planes into a common reference frame, which includes a voxel isotropication process to generate enhanced representations of the MRI segments with isotropic voxels, and an image alignment process that allows the anatomical superposition of different image plane views’” and “The claimed feature further requires ‘using a multi-planar combination model that comprises the application of a U-shaped CNN to the set of previously processed MRI segments in order to produce a unique high-resolution and quasi-isotropic volumetric representation’” is incorrect. Nothing in the independent claims establish a common technical feature that involves complementary anisotropic planes, specific alignment/normalization, anisotropy correction, image alignment/istropication, neural network use, or a particular algorithm or architecture. Rather, as noted in the restriction requirement, filed 09/11/2025, the common technical feature is receiving magnetic resonance imaging (MRI) data for a selected joint; generating MRI segments based at least in part on the MRI data, wherein the MRI segments are two-dimensional probability maps; generating three-dimensional models based at least in part on the MRI segments; autonomously determining one or more regions of interest (ROls) based at least in part on the three-dimensional models; generating three-dimensional diagnostic images illustrating selected tissue degeneration areas based at least in part on the three-dimensional models and the one or more ROIs; and displaying the three-dimensional diagnostic image. That is, the common technical feature is according to what is actually claimed and is common amongst the independent claims. Nowhere in the common technical features of the independent are the elements that Applicant contests are claimed. The common technical feature is more broadly recited than what Applicant alleges. MPEP 716.01(c) establishes “Arguments presented by the applicant cannot take the place of evidence in the record. In re Schulze, 346 F.2d 600, 602, 145 USPQ 716, 718 (CCPA 1965) and In re De Blauwe, 736 F.2d 699, 705, 222 USPQ 191, 196 (Fed. Cir. 1984).” With respect to the argument of the technical contribution, that is not the consideration in a unity of invention analysis. MPEP 823 establishes “The analysis used to determine whether the Office may require restriction differs in national stage applications submitted under 35 U.S.C. 371 (unity of invention analysis) as compared to national applications filed under 35 U.S.C. 111(a) (independent and distinct analysis). See MPEP Chapter 1800, in particular MPEP § 1850, § 1875, and § 1893.03(d), for a detailed discussion of unity of invention under the Patent Cooperation Treaty (PCT). However, the guidance set forth in this chapter with regard to other substantive and procedural matters (e.g., double patenting rejections (MPEP § 804), election and reply by applicant (MPEP § 818), and rejoinder of nonelected inventions (MPEP § 821.04) generally applies to national stage applications submitted under 35 U.S.C. 371.” The Unity of Invention analysis does not require a technical contribution consideration. Unity of invention is based on the determination of a common technical feature and assessment of whether the common technical feature makes a contribution over the prior art as a whole. This analysis was correctly performed in the Requirement for Restriction, filed 09/11/2025. While there is unity across the independent claims, the teachings of the prior art, in the form of Lang and Wang, show that the common technical feature that provides that unity is not novel and therefore does not provide a contribution over the art.
The requirement is still deemed proper and is therefore made FINAL.
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 3-4 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.
Claim 3 is indefinite for the following reasons:
Recites “a neural network”. This claim element is indefinite. It would be unclear to one with ordinary skill in the art if the “neural network” is the same as the “neural network” established claim 2 or is a separate and distinct feature.
Applicant is encouraged to provide consistent and clear language.
The term “high resolution” is a relative term which renders the claim indefinite. The term “high resolution” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. The determination of the resolution being “high” is subjective as the claim presently does not provide a threshold or a form of reference to benchmark the resolution. Resolution being considered “high” is not a definite value in the art and would be unclear to one with ordinary skill in the art.
Claims that are not discussed above but are cited to be rejected under 35 U.S.C. 112(b) are also rejected because they inherit the indefiniteness of the claims they respectively depend upon.
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, 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.
Claims 1-2, 5-12, and 23-26 are rejected under 35 U.S.C. 103 as being unpatentable over Lang et al. (PGPUB No. US 2016/0270696) in view of Wang et al. (PGPUB No. US 2014/0161334).
Regarding claim 1, Lang teaches a method of determining joint tissue degeneration, the method comprising:
receiving magnetic resonance imaging (MRI) data for a selected joint (Abstract teaches assessing the condition of a cartilage in a joint and assessing cartilage loss. Paragraph 0142 teaches obtaining the patient's magnetic resonance imaging (MRI) data of the knee showing at least the bones on either side of the joint);
generating MRI segments based at least in part on the MRI data (Paragraphs 0161 and 0256 teach cartilage and/or said bone is segmented; the cartilage is segmented slice by slice from MR images);
generating three-dimensional models based at least in part on the MRI segments (Paragraphs 0238 and 278 teach the set of segmented two-dimensional MR images can be transformed to a voxel representation using a computer program. Paragraphs 0232, 0268, and 0276 teach the size of the targeted volumes of interest can be selected to exceed that of the cartilage defect in anteroposterior and mediolateral direction, e.g. by 0.5 to 1 cm);
autonomously determining one or more regions of interest (ROls) based at least in part on the three-dimensional models (Paragraphs 0232, 0268, and 0276 teach the size of the targeted volumes of interest can be selected to exceed that of the cartilage defect in anteroposterior and mediolateral direction, e.g. by 0.5 to 1 cm. If the defect is located high on the femoral condyle or in the trochlear region, the targeted VOI can be chosen so that its size exceeds that of the cartilage defect in super-inferior and mediolateral direction; the 3D coordinates of the targeted VOI relative to the 3D contour of the joint and object coordinate system; a volume of interest in the cartilage, i.e., a region of the cartilage that includes a cartilage defect. Such a defect may be the result of a disease of the cartilage (e.g., osteoarthritis) or the result of degeneration due to overuse or age; defining a volume of interest around the region of the cartilage defect whereby the volume of interest is larger than the region of cartilage defect, but does not encompass the entire articular cartilage);
generating three-dimensional diagnostic images illustrating selected tissue degeneration areas based at least in part on the three-dimensional models and the one or more ROIs (Paragraphs 0250-52 and 0261 teach with a full 3D image captured, various "maps" or displays of the cartilage can be constructed to give a cartilage degeneration pattern. This is represented by step 16); and
displaying the three-dimensional diagnostic images (Paragraphs 0250-52 and 0261 teach with a full 3D image captured, various "maps" or displays of the cartilage can be constructed to give a cartilage degeneration pattern. This is represented by step 16. One such display can, for example, be a color-coding of a displayed image to reflect the thickness for the cartilage. This will allow easy visual identification of actual or potential defects in the cartilage; x, y, and z position of each pixel located along the bone-cartilage interface can be registered on a 3D map and thickness values are translated into color values; the anatomic location of each pixel at the bone cartilage interface can be displayed simultaneous with the thickness of the cartilage in this location; the cartilage thickness maps obtained using the algorithm described above display only a visual assessment of cartilage thickness along the articular surface).
However, Lang is silent regarding a method, wherein the MRI segments are two-dimensional probability maps.
In an analogous imaging field of endeavor, regarding MRI image analysis and modeling, Wang teaches a method, wherein the MRI segments are two-dimensional probability maps (Paragraphs 0005, 0055, 0074-78 teach magnetic resonance (MR) image testing model and determining a testing volume of the testing model that includes areas of the testing model to be classified as bone or cartilage; classification process, by the data processing system, using first pass random forest classifiers to produce a first pass probability map that classifies, each voxel of the testing model as one of femoral cartilage, tibial cartilage, patellar cartilage, or background; The "areas" or "portions" of the MR testing models described herein are intended to refer to 2D areas).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Lang with Wang’s teaching of MRI segments being 2D probability maps. This modified method would allow the user to improve boundary refinement and segmentation accuracy (Paragraph 0065 of Wang). Furthermore, the modification improves classification performance according to the probability mapping (Paragraph 0078 of Wang).
Regarding claim 2, modified Lang teaches the method in claim 1, as discussed above.
While Lang teaches the determination of boundaries of joint tissues and generating segmented images for the discrimination the joint tissues (Paragraphs 0232, 0238, 0250-52, 0261, 0268, and 0276. Fig. 12), Lang is silent regarding a method, processing MRI images with a neural network.
In an analogous imaging field of endeavor, regarding MRI image analysis and modeling, Wang teaches a method, wherein the step of generating MRI segments includes processing MRI images with a neural network to discriminate between different joint tissues, determine boundaries of each of the joint tissues and generating segmented images (Paragraph 0037 teaches a fully automatic learning-based voxel classification method for cartilage segmentation. This include pre-segmentation of corresponding bones in the knee joint. Paragraph 0018 teaches the use of an iterative multi-class learning method to segment the femoral, tibial, and patellar cartilage simultaneously, and can effectively exploit the spatial contextual constraints between bone and cartilage and also between different cartilages. Paragraph 0002 teaches operability with MRI).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Lang with Wang’s teaching of use of a neural network. This modified method would allow the user to improve boundary refinement and segmentation accuracy (Paragraph 0065 of Wang). Furthermore, the modification improves classification performance according to the probability mapping (Paragraph 0078 of Wang).
Regarding claim 5, modified Lang teaches the method in claim 1, as discussed above.
Lang further teaches a method, wherein the one or more ROIs are based at least in part on topological gradients of the three-dimensional models (Paragraph 0231 teaches one can use a 2D or a 3D surface detection technique to extract the surface of the joint, e.g. the femoral condyles. For detection of the surface of the femoral condyles, a step-by-step problem solving procedure, i.e., an algorithm, can convolve a data set with a 3D kernel to locate the maximum gradient location. The maximum gradient location corresponds to the zero crossing of a spatial location. When the kernel is designed properly, then there will be only one zero crossing in the mask. Thus, that zero crossing is the surface. This operation is preferably three-dimensional rather than two-dimensional. The surface of the joint, e.g. the femoral condyles, on the baseline scan can be registered in an object coordinate system A. The surface of the joint, e.g. the femoral condyles, on the follow-up scan can be registered in an object coordinate system B. Once these surfaces have been defined, a transformation B to B′ can be performed that best matches B′ with A. Such transformations can, for example, be performed using a Levenberg Marquardt technique. Alternatively, the transformations and matching can be applied to the cartilage only. The same transformation can be applied to the cartilage sensitive images on the follow-up scan in order to match the cartilage surfaces).
Regarding claim 6, modified Lang teaches the method in claim 5, as discussed above.
Lang further teaches a method, wherein the topological gradients are identified based on computer aided analysis of the three-dimensional models (Paragraph 0232 teaches that the 3D surface registration can be done via computer control. Paragraphs 0218-20 teach 3D modeling and imaging).
Regarding claim 7, modified Lang teaches the method in claim 1, as discussed above.
Lang further teaches a method, wherein the one or more ROIs include three-dimensional bone regions near the selected joint (Paragraph 0159 teaches volume of interest smaller than the articular cartilage surface is electronically placed in or around an area of diseased or damaged cartilage. Paragraph 0278-79 teaches that the bone is assessed and modeled. See Fig. 10).
Regarding claim 8, modified Lang teaches the method in claim 7, as discussed above.
Lang further teaches a method, wherein the three-dimensional bone regions include a femur, a tibia, or a combination thereof (Paragraph 0155 teaches that the tibia and femur can be modeled. See Fig. 12. Paragraph 0259 teaches area of articular cartilage defects in different locations of the femur, tibia, and patella).
Regarding claim 9, modified Lang teaches the method in claim 1, as discussed above.
Lang further teaches a method, wherein the one or more ROIs include three-dimensional cartilage regions near the selected joint (Paragraph 0159 teaches volume of interest smaller than the articular cartilage surface is electronically placed in or around an area of diseased or damaged cartilage. Paragraph 0278-79 teaches that the bone is assessed and modeled. See Fig. 10. Paragraph 0259 teaches area of articular cartilage defects in different locations of the femur, tibia, and patella).
Regarding claim 10, modified Lang teaches the method in claim 9, as discussed above.
Lang further teaches a method, wherein the three-dimensional cartilage regions include a femoral cartilage region, a tibial cartilage region, a tibial cartilage loading region, or a combination thereof (Paragraphs 0239-40 teaches the consideration and modeling of femoral cartilage. Paragraph 0259 teaches area of articular cartilage defects in different locations of the femur, tibia, and patella).
Regarding claim 11, modified Lang teaches the method in claim 1, as discussed above.
Lang further teaches a method, wherein the three-dimension diagnostic images include a three- dimensional thickness map of a joint space associated with the selected joint (Paragraphs 0236-37 teach the determination and generation of thickness maps. Paragraphs 0242-44 teaches the thickness calculation. Paragraph 0251 teaches the algorithmic determination of the thickness maps. See Fig. 22).
Regarding claim 12, modified Lang teaches the method in claim 11, as discussed above.
Lang further teaches a method, wherein determining the three-dimensional thickness map comprises:
estimating an edge of one or more cartilage regions within an MRI segment associated with the selected joint (Paragraph 0242 teaches the anatomic location of each pixel at the bone cartilage interface can be displayed simultaneously with the thickness of the cartilage in this location. Abstract teaches operability in the MRI context);
determining a skeleton associated with the selected joint; determining a volume based on the estimated edge and skeleton (Paragraphs 0242-45 teach edge detector can produce accurate surface points and their corresponding surface normal. The detector can be applied to the baseline and the follow-up data set. For the baseline data set, both the surface points and surface normal can be used to form locally supporting planes (for each voxel). These planes can form an approximated surface for the baseline skeletal site. After thresholding, the voxels on the edge of the cartilage structure can be extracted using a slice by slice 8-neighbor search, resulting in a binary volume with the voxels on the cartilage surface having a value of 1 and all others being 0. To classify these surface points as part of the ICS or OCS, a semi-automatic approach. Abstract teaches operability in the MRI context); and
determining the thickness associated with the joint based on the volume, summed over the MRI segment (Paragraphs 0242-45 teach edge detector can produce accurate surface points and their corresponding surface normal. The detector can be applied to the baseline and the follow-up data set. For the baseline data set, both the surface points and surface normal can be used to form locally supporting planes (for each voxel). These planes can form an approximated surface for the baseline skeletal site. After thresholding, the voxels on the edge of the cartilage structure can be extracted using a slice by slice 8-neighbor search, resulting in a binary volume with the voxels on the cartilage surface having a value of 1 and all others being 0. To classify these surface points as part of the ICS or OCS, a semi-automatic approach. Abstract teaches operability in the MRI context. Abstract teaches operability in the MRI context).
Regarding claim 23, modified Lang teaches the method in claim 1, as discussed above.
Lang further teaches a method, further comprising: determining quantitative joint information based at least in part on the three- dimensional models; and displaying the quantitative joint information (Paragraph 0160 teaches the acquisition of the 3D dataset of the anatomy. Quantitative measurement is performed of volume, thickness, biochemical contents and/or relaxation time of the cartilage in the subregion. The representation is used to devise a treatment for damaged or diseased cartilage or bone. Paragraph 0199 teaches various “maps” or displays of the cartilage can be constructed to give a cartilage degeneration pattern. One such display can, for example, be a color-coding of a displayed image to reflect the thickness for the cartilage. This will allow easy visual identification of actual or potential defects in the cartilage).
Regarding claim 24, modified Lang teaches the method in claim 1, as discussed above.
Lang further teaches a method, further comprising: predicting joint-related conditions based at least in part on the three-dimensional diagnostic images; and displaying an image showing, at least in part, the predicted joint-related conditions (Paragraph 0242 teaches the determination of the cartilage thickness and that the edge associated with them can be registered on a 3D or multiple 2D maps and thickness values are translated to color values. In this fashion, the anatomic location of each pixel at the bone cartilage interface can be displayed simultaneously with the thickness of the cartilage in this location. Paragraph 0199 teaches various “maps” or displays of the cartilage can be constructed to give a cartilage degeneration pattern. One such display can, for example, be a color-coding of a displayed image to reflect the thickness for the cartilage. This will allow easy visual identification of actual or potential defects in the cartilage).
Regarding claim 25, modified Lang teaches the method in claim 24, as discussed above.
Lang further teaches a method, wherein the predicting includes determining a classification of the predicted joint-related conditions (Paragraph 0143 teaches that the rate of degeneration can be assessed. And that can be normal degeneration or greater than normal degeneration. Paragraph 0207 teaches that the joints are classified into three general morphological types: fibrous, cartilaginous, and synovial. Paragraph 0199 teaches various “maps” or displays of the cartilage can be constructed to give a cartilage degeneration pattern. One such display can, for example, be a color-coding of a displayed image to reflect the thickness for the cartilage. This will allow easy visual identification of actual or potential defects in the cartilage).
Regarding claim 26, modified Lang teaches the method in claim 24, as discussed above.
Lang further teaches a method, wherein the classifications include pain progression, joint space width progression, pain and joint space width progression, neither pain nor joint space width progression, or a combination thereof (Paragraph 0205 teaches the mathematical quantification of the that allows the tracking of the progression of a defect, or conversely, continued tracking of healthy cartilage. This aids a health worker in providing therapy for the patients. Paragraph 0230 teaches that this allows a health practitioner to determine cartilage loss in a reproducible fashion and thus follow the progression of a cartilage defect over time. Paragraph 0259 teaches this allows the user to monitor the progression of osteoarthritis. Paragraph 0199 teaches various “maps” or displays of the cartilage can be constructed to give a cartilage degeneration pattern. One such display can, for example, be a color-coding of a displayed image to reflect the thickness for the cartilage. This will allow easy visual identification of actual or potential defects in the cartilage).
Claims 3-4 are rejected under 35 U.S.C. 103 as being unpatentable over Lang et al. (PGPUB No. US 2016/0270696) in view of Wang et al. (PGPUB No. US 2014/0161334) further in view of Jafari-Khouzani et al. ("MRI Upsampling Using Feature-Based Nonlocal Means Approach", 2014).
Regarding claim 3, modified Lang teaches the method in claim 2, as discussed above.
However, the combination of Lang and Wang is silent regarding a method, wherein after processing MRI images with a neural network an upsampling algorithm is used, which includes voxel isotropication, image alignment and a multi-planar combination model; the upsampling algorithm allows to combine complementary information from different anatomical views to provide high resolution 3D representations of the joint.
In an analogous imaging field of endeavor, regarding MRI image processing, Jafari-Khouzani teaches a method, wherein after processing MRI images with a neural network an upsampling algorithm is used, which includes voxel isotropication, image alignment and a multi-planar combination model; the upsampling algorithm allows to combine complementary information from different anatomical views to provide high resolution 3D representations of the joint (Pages 2-3 teach that the method is related to another category of methods, in which a high-resolution (HR) image with a different contrast is used to upsample the LR image. The proposed algorithm may be used to upsample regions of interest (ROIs) manually drawn on LR images. Page 14 teaches that upsampling was done using a HR T2W image (1 mm isotropic). The DSC images, and in particular GE DSC, had susceptibility arti fact appearing as signal drop and geometric distortion. Standard interpolation techniques are not accurate and result in distorted edges in the planes perpendicular to the acquisition plane. Abstract teaches that the technique is applied to LR images with both anisotropic and isotropic voxel size).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the combination of Lang and Wang with Jafari-Khouzani’s teaching of the upsampling technique. This modified method would allow the user to perofrm imaging with greater accuracy, faster processing, and fewer computations (Abstract of Jafari-Khouzani). Furthermore, the modification allows for dynamic MRI scanning with accurate correction of motion artifacts (Discussion of Jafari-Khouzani).
Regarding claim 4, modified Lang teaches the method in claim 3, as discussed above.
Lang further teaches a method, wherein after applying the upsampling algorithm a statistical shape modeling is used to automatically select the side of the input knee sequence (Paragraph 0159 teaches volumetric representation includes information on volume, thickness, curvature, shape and/or relaxation time of both normal and damaged cartilage of said joint. A volume of interest smaller than the articular cartilage surface is electronically placed in or around an area of diseased or damaged cartilage. See Figs. 10, 12, and 22. Paragraph 0222 teaches difference in CNR between DEFT and SPGR was statistically significant (p<0.001). Cartilage morphology, i.e. cartilage layers, were consistently best delineated with the DEFT sequence).
Claims 13-14 and 18-22 are rejected under 35 U.S.C. 103 as being unpatentable over Lang et al. (PGPUB No. US 2016/0270696) in view of Wang et al. (PGPUB No. US 2014/0161334) further in view of Wang et al. (PGPUB No. US 20180321347; hereinafter referred to as “Wang ‘347”).
Regarding claim 13, modified Lang teaches the method in claim 1, as discussed above.3
Lang further teaches a method, wherein the three-dimensional diagnostic images include a bone edema and inflammation image (Paragraph 0195 teaches that the image analysis allows for the assessment of degeneration pattern and assessment of the inflammation for consideration for therapy).
However, the combination of Lang and Wang is silent regarding a method, wherein the three-dimensional diagnostic images include a bone edema.
In an analogous imaging field of endeavor, regarding MRI image processing, Wang ‘347 teaches a method, wherein the three-dimensional diagnostic images include a bone edema (Paragraph 0243 teaches the mapping and assessment of edema and other cellularity pathologies).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the combination of Lang and Wang with Wang ‘347’s teaching of the assessment of the edema. This modified method would allow the user to improve their understanding of a subject's structure and/or composition and/or function, and can be used to improve the accuracy of any resulting medical diagnoses or experimental analyses (Paragraph 0005 of Wang ‘347). Furthermore, the modification have robust and accurate analysis of the patient anatomy (Paragraph 0062 of Wang ‘347).
Regarding claim 14, modified Lang teaches the method in claim 13, as discussed above.
Lang further teaches a method, wherein the three-dimensional diagnostic images include a bone edema and inflammation image (Paragraph 0195 teaches that the image analysis allows for the assessment of degeneration pattern and assessment of the inflammation for consideration for therapy).
However, the combination of Lang and Wang is silent regarding a method, wherein the bone edema and inflammation image is based at least in part on determining a water concentration in one or more tissues associated with the selected joint.
In an analogous imaging field of endeavor, regarding MRI image processing, Wang ‘347 teaches a method, wherein the bone edema and inflammation image is based at least in part on determining a water concentration in one or more tissues associated with the selected joint (Paragraph 0285 teaches water, fat and inhomogeneity components were then obtained using IDEAL-based techniques. Paragraph 0243 teaches the mapping and assessment of edema and other cellularity pathologies).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the combination of Lang and Wang with Wang ‘347’s teaching of image analysis according to water contribution. This modified method would allow the user to improve their understanding of a subject's structure and/or composition and/or function, and can be used to improve the accuracy of any resulting medical diagnoses or experimental analyses (Paragraph 0005 of Wang ‘347). Furthermore, the modification have robust and accurate analysis of the patient anatomy (Paragraph 0062 of Wang ‘347).
Regarding claim 18, modified Lang teaches the method in claim 1, as discussed above.
However, the combination of Lang and Wang is silent regarding a method, further comprising determining a water concentration of bones and cartilage associated with the select joint based at least in part on determining a uniformity of voxel intensity.
In an analogous imaging field of endeavor, regarding MRI image processing, Wang ‘347 teaches a method, further comprising determining a water concentration of bones and cartilage associated with the select joint based at least in part on determining a uniformity of voxel intensity (Paragraph 0285 teaches water, fat and inhomogeneity components were then obtained using IDEAL-based techniques. Paragraph 0243 teaches the mapping and assessment of edema and other cellularity pathologies. Paragraph 0045 teaches T2 weighted image according to a water map. Paragraph 0224 teaches generation of an estimate for fat and water fractions and the magnetic field. Paragraph 0266 teaches iteration tends to enforce both uniformity and underestimation of high susceptibility structures. Paragraph 0216 teaches automatically identification using the characteristic feature of uniform intensity and can be detected using a regional variance calculation).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the combination of Lang and Wang with Wang ‘347’s teaching of the automatic computation of the water concentration of bones and cartilage. This modified method would allow the user to improve their understanding of a subject's structure and/or composition and/or function, and can be used to improve the accuracy of any resulting medical diagnoses or experimental analyses (Paragraph 0005 of Wang ‘347). Furthermore, the modification have robust and accurate analysis of the patient anatomy (Paragraph 0062 of Wang ‘347).
Regarding claim 19, modified Lang teaches the method in claim 18, as discussed above.
However, the combination of Lang and Wang is silent regarding a method, wherein determining the uniformity includes determining an entropy associated with one or more three-dimensional models.
In an analogous imaging field of endeavor, regarding MRI image processing, Wang ‘347 teaches a method, wherein determining the uniformity includes determining an entropy associated with one or more three-dimensional models (Paragraph 0065 teaches the consideration of shadow artifacts and isolating the tissue. One specific tissue structure is that CSF in the ventricles of the brain is almost pure water with very little cellular contents. Therefore, ventricular susceptibility map should be nearly uniform, and any deviation from uniformity should be regarded as shadow artifacts to be penalized during numerical optimization by incorporating a regularization term. Shadow artifacts are penalized and minimized. Paragraph 0190 teaches imaging using multi-echo GRE at 3T with acquisition matrix=416×256×68. Paragraph 0266 teaches consideration of bone magnetic susceptibility that can be estimated by a highly regularized piece-wise inversion of the local magnetic field).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the combination of Lang and Wang with Wang ‘347’s teaching of determination of entropy with 3D models. This modified method would allow the user to improve their understanding of a subject's structure and/or composition and/or function, and can be used to improve the accuracy of any resulting medical diagnoses or experimental analyses (Paragraph 0005 of Wang ‘347). Furthermore, the modification have robust and accurate analysis of the patient anatomy (Paragraph 0062 of Wang ‘347).
Regarding claim 20, modified Lang teaches the method in claim 18, as discussed above.
However, the combination of Lang and Wang is silent regarding a method, wherein determining the uniformity includes determining an energy associated with voxels of one or more three-dimensional models.
In an analogous imaging field of endeavor, regarding MRI image processing, Wang ‘347 teaches a method, wherein determining the uniformity includes determining an energy associated with voxels of one or more three-dimensional models (Paragraphs 0136-38 teaches the objective consists of two energy terms, data fidelity and regularization, as in the discrete formulation. The data fidelity term involves a linear operator T defined by a formulaic equation, where d and * are the unit dipole kernel and the convolution operation, respectively).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the combination of Lang and Wang with Wang ‘347’s teaching of determination of energy with 3D models. This modified method would allow the user to improve their understanding of a subject's structure and/or composition and/or function, and can be used to improve the accuracy of any resulting medical diagnoses or experimental analyses (Paragraph 0005 of Wang ‘347). Furthermore, the modification have robust and accurate analysis of the patient anatomy (Paragraph 0062 of Wang ‘347).
Regarding claim 21, modified Lang teaches the method in claim 18, as discussed above.
However, the combination of Lang and Wang is silent regarding a method, wherein determining the uniformity includes determining a gray level co-occurrence matrix of joint entropy.
In an analogous imaging field of endeavor, regarding MRI image processing, Wang ‘347 teaches a method, wherein determining the uniformity includes determining a gray level co-occurrence matrix of joint entropy (Paragraph 0138 teaches GAXPY operations used in both PD and GNCG are as few as O(N), because the matrices that are involved are very sparse. These matrices are either diagonal or gradient matrix derived from the forward/central difference scheme).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the combination of Lang and Wang with Wang ‘347’s teaching of assessment according to gray level co-occurence. This modified method would allow the user to improve their understanding of a subject's structure and/or composition and/or function, and can be used to improve the accuracy of any resulting medical diagnoses or experimental analyses (Paragraph 0005 of Wang ‘347). Furthermore, the modification have robust and accurate analysis of the patient anatomy (Paragraph 0062 of Wang ‘347).
Regarding claim 22, modified Lang teaches the method in claim 18, as discussed above.
However, the combination of Lang and Wang is silent regarding a method, wherein determining the uniformity includes determining a gray level co-occurrence matrix of inverse difference.
In an analogous imaging field of endeavor, regarding MRI image processing, Wang ‘347 teaches a method, wherein determining the uniformity includes determining a gray level co-occurrence matrix of inverse difference (Paragraph 0277 teaches the quantitative BOLD (qBOLD) method, but there is error in approximation and the inverse condition for estimating [dH] is poor. The most widely investigated approach is calibrated fMRI (cfMRI), which empirically models the gradient echo (GRE) magnitude R2* decay).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the combination of Lang and Wang with Wang ‘347’s teaching of determination according to gray level co-occurrence matrix of inverse difference. This modified method would allow the user to improve their understanding of a subject's structure and/or composition and/or function, and can be used to improve the accuracy of any resulting medical diagnoses or experimental analyses (Paragraph 0005 of Wang ‘347). Furthermore, the modification have robust and accurate analysis of the patient anatomy (Paragraph 0062 of Wang ‘347).
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Lang et al. (PGPUB No. US 2016/0270696) in view of Wang et al. (PGPUB No. US 2014/0161334) further in view of Tamez-Pena et al. (PGPUB No. US 2005/0113663).
Regarding claim 15, modified Lang teaches the method in claim 1, as discussed above.
However, the combination of Lang and Wang is silent regarding a method, wherein the three-dimensional diagnostic images include a joint space width image.
In an analogous imaging field of endeavor, regarding MRI image processing, Tamez-Pena teaches a method, wherein the three-dimensional diagnostic images include a joint space width image (Paragraph 0004 teaches knees were imaged using fast GRE sequences in a clinical scanner under unloaded (normal) conditions and with an axial load that mimics the person's standing load. The results show that changes of 50 microns in the average distance between bones can be measured and that normal axial loads reduce the joint space width significantly and can be detected. Paragraph 0036 teaches the extreme anterior points of these searches will define the most anterior location of the joint space).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the combination of Lang and Wang with Tamez-Pena’s teaching of assessment of the joint space width. This modified method would allow the user to have improved diagnostic capability over prior art which would measure biomarkers, such as cartilage volume or thickness, as a whole over the entire cartilage, thus combining information from both load bearing and non-load bearing regions of the cartilage (Paragraph 0013 of Tamez-Pena). Furthermore, the modification allows for accurate femur extraction (Paragraph 0031 of Tamez-Pena).
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Lang et al. (PGPUB No. US 2016/0270696) in view of Wang et al. (PGPUB No. US 2014/0161334) further in view of Tamez-Pena et al. (PGPUB No. US 2005/0113663further in view of Martel-Pelletier et al. (PGPUB No. US 2006/0002600).
Regarding claim 16, modified Lang teaches the method in claim 15, as discussed above.
However, the combination of Lang, Wang, and Tamez-Pena is silent regarding a method, further comprising determining a mean value from a lowest five percent distribution of joint spaces.
In an analogous imaging field of endeavor, regarding joint disorder and cartilage assessment, Martel-Pelletier teaches a method, further comprising determining a mean value from a lowest five percent distribution of joint spaces (Paragraph 0079 teaches that the population is an average map and the representatives are in percentage points. See Fig. 7).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the combination of Lang and Wang with Martel-Pelletier’s teaching of determining a mean value from a lowest five percent distribution. This modified method would allow the user to allow a user to define classes on the basis of quantitative cartilage thickness information (Paragraph 0081 of Martel-Pelletier). Furthermore, the modification providers showring diagnostic and acquisition times (Paragraph 0016 of Martel-Pelletier).
Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over Lang et al. (PGPUB No. US 2016/0270696) in view of Wang et al. (PGPUB No. US 2014/0161334) further in view of Huo et al. (PGPUB No. US 2016/0180520).
Regarding claim 17, modified Lang teaches the method in claim 1, as discussed above.
However, the combination of Lang and Wang is silent regarding a method, wherein the three-dimensional diagnostic images include a bone spur identification image.
In an analogous imaging field of endeavor, regarding MRI image analysis, Huo teaches a method, wherein the three-dimensional diagnostic images include a bone spur identification image (Paragraph 0071 teaches performance of local analysis of a particular region of the joint, such as where a fracture, bone spur, or other condition contributes to loss of cartilage).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the combination of Lang and Wang with Huo’s teaching of bone spur identification. This modified method would allow the user to allow the user to provide improved diagnosis and care in arthritic cases (Paragraph 0003 of Huo). Furthermore, the modification will allow the user to improve the methodology to more accurately characterize joint spacing using volume imaging techniques (Paragraph 0007 of Huo).
Claim 27 is rejected under 35 U.S.C. 103 as being unpatentable over Lang et al. (PGPUB No. US 2016/0270696) in view of Wang et al. (PGPUB No. US 2014/0161334) further in view of Chaoui et al. (PGPUB No. US 2021/0093395).
Regarding claim 27, modified Lang teaches the method in claim 24, as discussed above.
However, the combination of Lang and Wang is silent regarding a method, wherein the predicting is based on a deep-learning model executed by a trained convolutional neural network.
In an analogous imaging field of endeavor, regarding joint disorder assessment, Chaoui teaches a method, wherein the predicting is based on a deep-learning model executed by a trained convolutional neural network (Paragraph 0633 teaches the CNN can be trained. Paragraph 0829 teaches the classification system can be done via the neural network that allows for the assessment of arthritis).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the combination of Lang and Wang with Chaoui’s teaching of training a CNN. This modified method would allow the user to improve alignment of the 3D model with the observed anatomy of interest (Paragraph 0341 of Chaoui). Furthermore, the modification can improve surgical outcomes by customizing a surgical plan for each patient (Paragraph 0172 of Chaoui).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Rabinoff et al. (PGPUB No. US 2006/0129324): Teaches training a neural network for prediction of joint disorders.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ADIL PARTAP S VIRK whose telephone number is (571)272-8569. The examiner can normally be reached Mon-Fri 8-5.
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, Pascal Bui-Pho can be reached on 571-272-2714. 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.
/ADIL PARTAP S VIRK/Primary Examiner, Art Unit 3798
1 Applicant argues that Lang does not address the complementary anisotropic planes and specific alignment/normalization.
2 Applicant argues that Wang does not address the missing anisotropy correction and missing image alignment/istropication.
3 Applicant argues that Lang has missing neural network use.
4 Applicant argues that Wang has the wrong algorithm/architecture.
Prosecution Insights