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 .
Status of the Claims
Claims 1-4, 8, 9, 13-16, 19-21, 23, 24 and 44-48, as amended, are currently pending and have been considered below.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim 46 is rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) does/do not fall within at least one of the four categories of patent eligible subject matter because claim 46 recites “computer program instructions” which could be interpreted as software per se and software per se does not encompass one of the four categories of patent eligible subject matter. The Examiner suggests Applicant amend claim 46 to recite “A non-transitory computer readable storage medium ...” in order to overcome the rejection.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-4, 8, 9, 13-16, 19-21, 23, 24 and 44-48 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al., U.S. Publication No. 2019/0122364, hereinafter, “Zhang”, and further in view of Kullberg et al., U.S. Publication No. 2018/01444725, hereinafter, “Kullberg”.
As per claim 1, Zhang discloses a method for preparing a tool for automated image inference (Zhang, ¶0023, Referring initially to FIG. 1, there is illustrated an example system 100 for facilitating image analysis ... The system 100 can be employed by various systems, such as, but not limited to ... artificial intelligence systems, machine learning systems, neural network systems, modeling systems ... In one example, the system 100 can be associated with a classification system to facilitate visualization and/or interpretation of medical imaging data. Moreover, the system 100 and/or the components of the system 100 can be employed to use hardware and/or software to solve problems that are highly technical in nature (e.g., related to processing digital data, related to processing medical imaging data, related to medical modeling, related to medical imaging, related to artificial intelligence, etc.); Zhang, ¶0029, Zhang, ¶0030; Zhang, ¶0048; Zhang, ¶0052; Zhang, Figure 1; Zhang, Figure 8), comprising the steps of:
providing a neural network to be trained (Zhang, ¶0029, The neural network component 108 can train a neural network based on the deviation map data to determine one or more clinical conditions included in medical imaging data. For example, the deviation map data can be provided as input to a neural network. Furthermore, the neural network can perform a machine learning training process (e.g., an artificial intelligence training process for machine learning) based on the deviation map data);
obtaining multiple training subject data sets, each comprising at least one respective medical image of an associated subject and an assigned image inference of said associated subject (Zhang, ¶0025, The machine learning component 102 (e.g., the atlas map component 104) can receive medical imaging data (e.g., MEDICAL IMAGING DATA shown in FIG. 1); Zhang, ¶0026, The atlas map component 104 can generate atlas map data indicative of an atlas map that includes a first portion of the medical imaging data that satisfies a first defined criterion. In an aspect, the first portion of the medical imaging data can be from a plurality of reference patients. For instance, the first portion of the medical imaging data can be reference data from a plurality of patients. Furthermore, the first portion of the medical imaging data can be matched to a corresponding age group for a set of patient identities associated with the first portion of the medical imaging data);
wherein said method further comprises at least one of:
i) said associated subject being a training subject in a respective set common image space of a common image (Zhang, ¶0026, The atlas map component 104 can generate atlas map data indicative of an atlas map that includes a first portion of the medical imaging data that satisfies a first defined criterion. In an aspect, the first portion of the medical imaging data can be from a plurality of reference patients. For instance, the first portion of the medical imaging data can be reference data from a plurality of patients. Furthermore, the first portion of the medical imaging data can be matched to a corresponding age group for a set of patient identities associated with the first portion of the medical imaging data),
wherein each of said multiple training subject data sets further comprises at least one image of voxel-wise state of health, associated with said associated training subject, registered to said set common image space (Zhang, ¶0028, The deviation map component 106 can generate deviation map data that represents an amount of deviation for the second portion of the medical imaging data compared to the first portion of medical imaging data. In an aspect, the deviation map component 106 can modify the atlas map data to generate deviation map data ... a first color (e.g., a color blue) in the deviation map data can correspond to a first value (e.g., a normal medical condition) for the atlas map data, a second color (e.g., a color green) in the deviation map data can correspond to a second value (e.g., a possible abnormal medical condition) for the atlas map data, a third color (e.g., a color red) in the deviation map data can correspond to a third value (e.g., an abnormal medical condition) for the atlas map data, etc. ... As such, a set of deviation maps corresponding to each image for each of a plurality of clinical conditions can be generated);
wherein said at least one image of voxel-wise state of health comprises a divergence image being based on a comparison between said medical image of said respective associated training subject and collective image information of a group of subjects (Zhang, ¶0026, The atlas map component 104 can generate atlas map data indicative of an atlas map that includes a first portion of the medical imaging data that satisfies a first defined criterion. In an aspect, the first portion of the medical imaging data can be from a plurality of reference patients ... the first portion of the medical imaging data can be age-matched normal medical imaging data from a plurality of pediatric patients that belong to a plurality of pediatric age groups. Additionally, the atlas map data generated by the atlas map component 104 can include a second portion of the medical imaging data that satisfies a second defined criterion. For example, the second portion of the medical imaging data can be abnormal medical imaging data associated with one or more abnormal medical conditions. In an aspect, the second portion of the medical imaging data can be from a plurality of target patients; Zhang, ¶0028, The deviation map component 106 can generate deviation map data that represents an amount of deviation for the second portion of the medical imaging data compared to the first portion of medical imaging data. In an aspect, the deviation map component 106 can modify the atlas map data to generate deviation map data … a set of deviation maps corresponding to each image for each of a plurality of clinical conditions can be generated);
wherein said step of obtaining multiple training subject data sets comprises obtaining at least one of voxel-wise state of health registered to said set common image space (Zhang, ¶0022, age-matched normal patient image data from a plurality of pediatric patients that belong to a plurality of pediatric age groups can be accessed. Normal patient data of a given age group can be registered to an atlas to form a standardized age matched normal patient grouping for the age group. Furthermore, abnormal patient image data for a set of plurality of clinical conditions can be accessed. The abnormal patient image data can be registered to the atlas to form a standardized abnormal patient grouping. A deviation map associated with the abnormal patient image data can be determined in the standardized abnormal patient grouping based on the standardized age-matched normal patient grouping to form a deviation image data collection. Moreover, a neural network can be trained based on the deviation image data collection to determine one or more clinical conditions in patient image data), in turn comprising:
obtaining medical images for said group of subjects (Zhang, ¶0022);
registering medical images of said medical images for said group of subjects to said set common image space by a common image registering routine (Zhang, ¶0022, age-matched normal patient image data from a plurality of pediatric patients that belong to a plurality of pediatric age groups can be accessed. Normal patient data of a given age group can be registered to an atlas to form a standardized age matched normal patient grouping for the age group. Furthermore, abnormal patient image data for a set of plurality of clinical conditions can be accessed. The abnormal patient image data can be registered to the atlas to form a standardized abnormal patient grouping. A deviation map associated with the abnormal patient image data can be determined in the standardized abnormal patient grouping based on the standardized age-matched normal patient grouping to form a deviation image data collection. Moreover, a neural network can be trained based on the deviation image data collection to determine one or more clinical conditions in patient image data); and
creating said divergence image by comparing said medical image of said respective associated training subject with registered said medical images for said group of subjects (Zhang, ¶0026, The atlas map component 104 can generate atlas map data indicative of an atlas map that includes a first portion of the medical imaging data that satisfies a first defined criterion. In an aspect, the first portion of the medical imaging data can be from a plurality of reference patients ... the first portion of the medical imaging data can be age-matched normal medical imaging data from a plurality of pediatric patients that belong to a plurality of pediatric age groups. Additionally, the atlas map data generated by the atlas map component 104 can include a second portion of the medical imaging data that satisfies a second defined criterion. For example, the second portion of the medical imaging data can be abnormal medical imaging data associated with one or more abnormal medical conditions. In an aspect, the second portion of the medical imaging data can be from a plurality of target patients; Zhang, ¶0028, The deviation map component 106 can generate deviation map data that represents an amount of deviation for the second portion of the medical imaging data compared to the first portion of medical imaging data. In an aspect, the deviation map component 106 can modify the atlas map data to generate deviation map data … a set of deviation maps corresponding to each image for each of a plurality of clinical conditions can be generated); and
ii) said at least one respective medical image being medical images of at least two instances (Zhang, ¶0022);
wherein said assigned image inference is an assigned image inference for at least one of said at least two instances (Zhang, ¶0022); and the further step of:
registering medical images of said at least two instances and said assigned image inference for each subject to a set common image space of a set common image by use of a common image registering routine (Zhang, ¶0022, age-matched normal patient image data from a plurality of pediatric patients that belong to a plurality of pediatric age groups can be accessed. Normal patient data of a given age group can be registered to an atlas to form a standardized age matched normal patient grouping for the age group. Furthermore, abnormal patient image data for a set of plurality of clinical conditions can be accessed. The abnormal patient image data can be registered to the atlas to form a standardized abnormal patient grouping. A deviation map associated with the abnormal patient image data can be determined in the standardized abnormal patient grouping based on the standardized age-matched normal patient grouping to form a deviation image data collection. Moreover, a neural network can be trained based on the deviation image data collection to determine one or more clinical conditions in patient image data); and
training said neural network with said training subject data sets into a trained neural network (Zhang, ¶0029, The neural network component 108 can train a neural network based on the deviation map data to determine one or more clinical conditions included in medical imaging data. For example, the deviation map data can be provided as input to a neural network. Furthermore, the neural network can perform a machine learning training process (e.g., an artificial intelligence training process for machine learning) based on the deviation map data).
Zhang does not explicitly disclose the following limitations as further recited however Kullberg discloses
obtaining subject data sets, each comprising at least one respective whole-body medical image of an associated subject (Kullberg, ¶0001, Kullberg, ¶0016, provide a robust whole body image registration method enabling analyzing of whole body images; Kullberg, ¶0017, a method for registration of whole body volume images comprises obtaining a first image and a second image. The first image is a whole body volume image comprising water and fat magnetic resonance image data and the second image is a whole body volume image comprising water and fat magnetic resonance image data; Kullberg, ¶0115, The first image may be a member of a first set of volume images to be registered, which set comprises one or more volume images. The first set of volume images may be volume images of one and the same whole body. The second image may be a volume image composed from one or more whole bodies. The second image may comprise intensity average and shape information average volume images based on volume images of multiple bodies);
wherein said common image registering routine comprises at least two part registering steps (Kullberg, ¶0094-0097, The image registration method as presented in this particular embodiment comprises: Articulated, piece-wise affine, registration of bone sections; Registration of water images with constraints on bone; and Registration of fat images with constraints on bone and water), in at least one of which:
images of different respective tissues in said whole-body medical images are obtained, a part registering to said set common image space is performed by optimizing a weighted cost function comprising a correlation of said images of respective tissues of said whole-body medical images to images of respective tissues of said set common image as well as a correlation of said whole-body medical image to a whole-body medical image of said set common image, thereby obtaining deformation parameters defining said part registration for said whole-body medical image (Kullberg, ¶0017, a method for registration of whole body volume images comprises obtaining a first image and a second image. The first image is a whole body volume image comprising water and fat magnetic resonance image data and the second image is a whole body volume image comprising water and fat magnetic resonance image data. Bone tissue is identified from the first image creating a first bone image, and bone tissue is identified from the second image creating a second bone image. Water components are separated from the first image, generating a first water image based on absolute water content, and water components are separated from the second image, generating a second water image based on absolute water content. Fat components are separated from the first image, generating a first fat image based on absolute fat content, and fat components are separated from the second image, generating a second fat image based on absolute fat content. The first image is registered to the second image by deforming the first bone image according to a bone tissue deformation rule, deforming the first water image according to a water tissue deformation rule under constraints of the deformation of the first bone image and deforming the first fat image according to a fat tissue deformation rule under constraints of the deformation of the first bone image and the deformation of the first water image; Kullberg, ¶0018, a method for analysis of whole body volume images comprises analysing image features of whole body volume images obtainable by a registering method according to the first aspect in a holistic manner; Kullberg, ¶0098, a variational approach to image registration may be used. This means that the deformation field may be achieved by energy minimization of a metric, i.e., weighted terms of energy functions and regularization terms. Essential steps in a variational approach to image registration are choice of metric, parameterization of the deformation field, optimization method to find the optimal parameters and interpolation methods; Kullberg, ¶0099, In a deformable registration, the deformation fields may be parameterized; Kullberg, ¶0100, A stochastic gradient descent optimization method may be used; Kullberg, ¶0101-0104, Cost functions S used in this embodiment comprise: Sum of squared differences (SDD) Landmark term: Anatomical landmarks can be used to guide the registration process. Here, the mean Euclidean distance error between landmarks in the fixed and moving images may be used. Multi-band cost function: To allow multiple image input, a cost function that can handle multiple images may be needed; Kullberg, ¶0105—0108; Kullberg, ¶0115, The first image may be a member of a first set of volume images to be registered, which set comprises one or more volume images. The first set of volume images may be volume images of one and the same whole body. The second image may be a volume image composed from one or more whole bodies. The second image may comprise intensity average and shape information average volume images based on volume images of multiple bodies; Kullberg, ¶0117, The cost functions used in the individual steps of the registration procedure may be weighted sums of cost functions);
wherein said deformation parameters of one part registration step, except for a last part registration step, is used in a subsequent part registration step and wherein said deformation parameters of said last part registration step is used for creating final registered whole-body medical images (Kullberg, ¶0094-0097, The image registration method as presented in this particular embodiment comprises: Articulated, piece-wise affine, registration of bone sections; Registration of water images with constraints on bone; and Registration of fat images with constraints on bone and water; Kullberg, ¶0090, in order to improve efficiency and robustness and to avoid local minima, an image registration is usually carried out in different scales, starting from a coarse scale where the overall shape is first aligned. In the final step, fine-scale structures are aligned; Kullberg, ¶0141, To achieve a final global registration, the mean square error of body masks and fat images may be minimized by LMWATER and LMBONE as landmarks. In this step, the cost function is a linear combination of the mean square distance between the fixed and the moving fat images, the mean square distance between the fixed and the moving body mask images and the mean Euclidean distance between the landmarks LMWB in the fixed and moving image).
It would have been obvious to one skilled in the art before the effective filing date of the claimed invention to combine the teachings of Kullberg and Zhang because they are in the same field of endeavor. One skilled in the art would have been motivated to include the whole-body images as taught by Kullberg in the system of Zhang in order to enable the detection of where and how image features from a whole body deviate from image features from multiple whole bodies of an atlas of volume images (Kullberg, ¶0201).
As per claim 2, Zhang and Kullberg disclose the method according to claim 1, wherein
said associated subject being a training subject in a respective set common image space of a common image (Zhang, ¶0026, The atlas map component 104 can generate atlas map data indicative of an atlas map that includes a first portion of the medical imaging data that satisfies a first defined criterion. In an aspect, the first portion of the medical imaging data can be from a plurality of reference patients. For instance, the first portion of the medical imaging data can be reference data from a plurality of patients. Furthermore, the first portion of the medical imaging data can be matched to a corresponding age group for a set of patient identities associated with the first portion of the medical imaging data),
wherein each of said multiple training subject data sets further comprises at least one whole-body image of voxel-wise state of health, associated with said associated training subject, registered to said set common image space (Zhang, ¶0028, The deviation map component 106 can generate deviation map data that represents an amount of deviation for the second portion of the medical imaging data compared to the first portion of medical imaging data. In an aspect, the deviation map component 106 can modify the atlas map data to generate deviation map data ... a first color (e.g., a color blue) in the deviation map data can correspond to a first value (e.g., a normal medical condition) for the atlas map data, a second color (e.g., a color green) in the deviation map data can correspond to a second value (e.g., a possible abnormal medical condition) for the atlas map data, a third color (e.g., a color red) in the deviation map data can correspond to a third value (e.g., an abnormal medical condition) for the atlas map data, etc. ... As such, a set of deviation maps corresponding to each image for each of a plurality of clinical conditions can be generated; Kullberg, ¶0201, In 53, the method alternatively comprises performing a comparison of image features, or image features derived from a deformation field, of the method for registration of volume images from a set of registered volume images of a whole body and a volume image atlas of registered volume images of multiple whole bodies enabling detecting where and how image features from a whole body deviate from image features from multiple whole bodies of the atlas of volume images);
wherein said at least one whole-body image of voxel-wise state of health comprises a whole-body divergence image being based on a comparison between said whole-body medical image of said respective associated training subject and collective image information of a group of subjects (Kullberg, ¶0157, Cross-sectional studies may be studied using whole-body “correlation-maps”, and groups of subjects, for instance normal versus pre-diabetic, can be compared using whole-body “difference-maps”; Kullberg, ¶0201, In 53, the method alternatively comprises performing a comparison of image features, or image features derived from a deformation field, of the method for registration of volume images from a set of registered volume images of a whole body and a volume image atlas of registered volume images of multiple whole bodies enabling detecting where and how image features from a whole body deviate from image features from multiple whole bodies of the atlas of volume images);
wherein said step of obtaining multiple training subject data sets comprises obtaining at least one whole-body image of voxel-wise state of health registered to said set common image space, in turn comprising: obtaining whole-body medical images for said group of subjects (Zhang, ¶0022; Kullberg, ¶0157);
registering whole-body medical images of said whole-body medical images for said group of subjects to said set common image space by a common image registering routine (Zhang, ¶0022; Kullberg, ¶0157); and
creating said whole-body divergence image by comparing said whole-body medical image of said respective associated training subject with registered said whole-body medical images for said group of subjects (Zhang, ¶0026; Zhang, ¶0028; Kullberg, ¶0160, FIG. 10 illustrates the results from atlas creation and anomaly detection; Kullberg, ¶0201, In 53, the method alternatively comprises performing a comparison of image features, or image features derived from a deformation field, of the method for registration of volume images from a set of registered volume images of a whole body and a volume image atlas of registered volume images of multiple whole bodies enabling detecting where and how image features from a whole body deviate from image features from multiple whole bodies of the atlas of volume images).
As per claim 3, Zhang and Kullberg disclose the method according to claim 1, wherein said set common image space is equal to a respective training subject image space (Zhang, ¶0025, The machine learning component 102 (e.g., the atlas map component 104) can receive medical imaging data (e.g., MEDICAL IMAGING DATA shown in FIG. 1); Zhang, ¶0026, The atlas map component 104 can generate atlas map data indicative of an atlas map that includes a first portion of the medical imaging data that satisfies a first defined criterion. In an aspect, the first portion of the medical imaging data can be from a plurality of reference patients. For instance, the first portion of the medical imaging data can be reference data from a plurality of patients. Furthermore, the first portion of the medical imaging data can be matched to a corresponding age group for a set of patient identities associated with the first portion of the medical imaging data).
As per claim 4, Zhang and Kullberg disclose the method according to claim 1, wherein said step of obtaining multiple training subject data sets comprises the steps of:
obtaining at least one respective whole-body medical image of an associated training subject in a respective subject image space (Kullberg, ¶0017; Zhang, ¶0025; Zhang, ¶0026);
registering whole-body medical images of said at least one whole-body medical image of said training subject data sets, being in an image space different from said set common image space, to said set common image space by use of said common image registering routine (Kullberg, ¶0017, a method for registration of whole body volume images comprises obtaining a first image and a second image. The first image is a whole body volume image comprising water and fat magnetic resonance image data and the second image is a whole body volume image comprising water and fat magnetic resonance image data. Bone tissue is identified from the first image creating a first bone image, and bone tissue is identified from the second image creating a second bone image. Water components are separated from the first image, generating a first water image based on absolute water content, and water components are separated from the second image, generating a second water image based on absolute water content. Fat components are separated from the first image, generating a first fat image based on absolute fat content, and fat components are separated from the second image, generating a second fat image based on absolute fat content. The first image is registered to the second image by deforming the first bone image according to a bone tissue deformation rule, deforming the first water image according to a water tissue deformation rule under constraints of the deformation of the first bone image and deforming the first fat image according to a fat tissue deformation rule under constraints of the deformation of the first bone image and the deformation of the first water image).
As per claim 8, Zhang and Kullberg disclose the method according to claim 1, wherein said at least one respective whole-body medical image being whole-body medical images of at least two instances (Zhang, ¶0022; Kullberg, ¶0150);
wherein said assigned image inference is an assigned image inference for at least one of said at least two instances (Zhang, ¶0022; Kullberg, ¶0149); and
comprising the further step of: registering whole-body medical images of said at least two instances and said assigned image inference for each subject to a set common image space of a set common image by use of a common image registering routine (Zhang, ¶0022; Kullberg, ¶0151; Kullberg, ¶0201).
As per claim 9, Zhang and Kullberg disclose the method according to claim 1, wherein the method comprises at least one of: said assigned image inference is obtained by human intervention or in statistical ways based on said whole-body medical image of said at least one of said at least two instances (Kullberg, ¶0146, The invention thus enables, among other aspects, the creation of a statistical atlas being a statistical representation of image features such as tissue morphology, and characteristics as function and metabolism in all voxels of a studied whole body); and
each of said multiple training subject data sets comprises an assigned image inference of said associated subject for at least another one of said at least two instances being based on an assigned automatic image inference deduced from whole-body medical images of said respective subject ((Zhang, ¶0023, Zhang, ¶0029, Zhang, ¶0030; Zhang, ¶0048; Zhang, ¶0052; Zhang, Figure 1; Zhang, Figure 8)
As per claim 13, Zhang discloses a method for automated image inference (Zhang, ¶0023, Zhang, ¶0029, Zhang, ¶0030; Zhang, ¶0048; Zhang, ¶0052; Zhang, Figure 1; Zhang, Figure 8), comprising the steps of:
providing a trained neural network (Zhang, ¶0029);
wherein said trained neural network being trained with training subject data sets of at least one respective medical image, and an assigned image inference of an associated subject (Zhang, ¶0025; Zhang, ¶0026, atlas map);
obtaining a subject data set of at least one medical image of an associated subject (Zhang, ¶0026); and
operating said trained neural network with said subject data set as input data, resulting in an image inference (Zhang, ¶0029);
wherein said method further comprises at least one of:
i) said training subject data sets further comprises at least one training image of voxel-wise state of health, all registered to a set common image space of a set common image (Zhang, ¶0028) and
wherein said at least one training image of voxel-wise state of health comprises a divergence image based on a comparison between said medical image of said respective associated training subject and collective image information of a group of subjects (Zhang, ¶0026; Zhang, ¶0028, deviation map);
wherein said subject data set is a subject data set of at least one medical image of an associated subject in a common image space of a common image, and at least one image of voxel-wise state of health registered to said common image space (Zhang, ¶0022);
wherein said at least one image of voxel-wise state of health comprises a divergence image being based on a comparison between said medical image of said associated subject and collective image information of a group of subjects (Zhang, ¶0022);
wherein said step of obtaining said subject data set comprises obtaining at least one image of voxel-wise state of health registered to said common image space, in turn comprising: obtaining medical images for said group of subjects (Zhang, ¶0022);
registering medical images of said medical images for said group of subjects to said common image space by a common image registering routine (Zhang, ¶0022); and
creating said divergence image by comparing said medical image of said associated subject with registered said medical images for said group of subjects (Zhang, ¶0026; Zhang, ¶0028); and
ii) said training subject data sets are training subject data sets (129A, 129B) of at least one respective medical image of at least two, non-simultaneous instances (Zhang, ¶0022, age-matched normal patient image data from a plurality of pediatric patients that belong to a plurality of pediatric age groups can be accessed. Normal patient data of a given age group can be registered to an atlas to form a standardized age matched normal patient grouping for the age group. Furthermore, abnormal patient image data for a set of plurality of clinical conditions can be accessed);
wherein said assigned image inference is an assigned image inference of an associated subject for at least one of said at least two instances for each training data set, registered to a respective set common image space (Zhang, ¶0022); and
further comprising: registering medical images of said at least two instances to a common image space of a common image by use of a common image registering routine (Zhang, ¶0022).
Zhang does not explicitly disclose the following limitations as further recited however Kullberg discloses
wherein said subject data set is a subject data set of at least one whole-body medical image of at least two, non-simultaneous, instances of an associated subject (Kullberg, ¶0150, The analysis of images is typically based on multispectral image data collected from different subjects (whole bodies) or at different points in time. This approach may be used to combine whole-body image data from, for instance, healthy subjects to create a statistical atlas that contains detailed statistics on tissue morphology, function, and metabolism in all voxels in the entire body);
wherein said common image registering routine comprises at least two part registering steps (Kullberg, ¶0094-0097, The image registration method as presented in this particular embodiment comprises: Articulated, piece-wise affine, registration of bone sections; Registration of water images with constraints on bone; and Registration of fat images with constraints on bone and water), in at least one of which:
images of different respective tissues in said whole-body medical images are obtained, a part registering to said common space is performed by optimizing a weighted cost function comprising a correlation of said images of respective tissues of said whole-body medical image to images of respective tissues of said common image as well as a correlation of said whole-body medical images to a whole-body medical image of said common image, thereby obtaining deformation parameters defining said part registration for said whole-body medical image (Kullberg, ¶0017; Kullberg, ¶0018; Kullberg, ¶0098, a variational approach to image registration may be used; Kullberg, ¶0099, In a deformable registration, the deformation fields may be parameterized; Kullberg, ¶0100; Kullberg, ¶0101-0104, Cost functions S used in this embodiment comprise: Sum of squared differences (SDD) Landmark term: Anatomical landmarks can be used to guide the registration process; Kullberg, ¶0105—0108; Kullberg, ¶0115; Kullberg, ¶0117, The cost functions used in the individual steps of the registration procedure may be weighted sums of cost functions);
wherein said deformation parameters of one part registration step, except for a last part registration step, is used in a subsequent part registration step and wherein said deformation parameters of said last part registration step is used for creating final registered whole-body medical images (Kullberg, ¶0094-0097, The image registration method as presented in this particular embodiment comprises: Articulated, piece-wise affine, registration of bone sections; Registration of water images with constraints on bone; and Registration of fat images with constraints on bone and water; Kullberg, ¶0090; Kullberg, ¶0141).
It would have been obvious to one skilled in the art before the effective filing date of the claimed invention to combine the teachings of Kullberg and Zhang because they are in the same field of endeavor. One skilled in the art would have been motivated to include the whole-body images as taught by Kullberg in the system of Zhang in order to enable the detection of where and how image features from a whole body deviate from image features from multiple whole bodies of an atlas of volume images (Kullberg, ¶0201).
As per claim 14, Zhang and Kullberg disclose the method according to claim 13, wherein said training subject data sets further comprises at least one training whole-body image of voxel-wise state of health, all registered to a set common image space of a set common image and wherein said at least one training whole-body image of voxel-wise state of health comprises a whole-body divergence image based on a comparison between said whole-body medical image of said respective associated training subject and collective image information of a group of subjects (Zhang, ¶0022; Kullberg, ¶0201);
wherein said subject data set is a subject data set of at least one whole-body medical image of an associated subject in a common image space of a common image, and at least one whole-body image of voxel-wise state of health registered to said common image space (Zhang, ¶0026; Zhang, ¶0028);
wherein said at least one whole-body image of voxel-wise state of health comprises a whole-body divergence image being based on a comparison between said whole-body medical image of said associated subject and collective image information of a group of subjects (Zhang, ¶0022; Kullberg, ¶0201);
wherein said step of obtaining said subject data set comprises obtaining at least one whole-body image of voxel-wise state of health registered to said common image space, in turn comprising: obtaining whole-body medical images for said group of subjects (Zhang, ¶0022);
registering whole-body medical images of said whole-body medical images for said group of subjects to said common image space by a common image registering routine (Zhang, ¶0022); and
creating said whole-body divergence image by comparing said whole-body medical image of said associated subject with registered said whole-body medical images for said group of subjects (Zhang, ¶0026; Zhang, ¶0028).
As per claim 15, Zhang and Kullberg disclose the method according to claim 13, wherein said common image space is equal to said subject image space (Zhang, ¶0025, The machine learning component 102 (e.g., the atlas map component 104) can receive medical imaging data (e.g., MEDICAL IMAGING DATA shown in FIG. 1); Zhang, ¶0026, The atlas map component 104 can generate atlas map data indicative of an atlas map that includes a first portion of the medical imaging data that satisfies a first defined criterion. In an aspect, the first portion of the medical imaging data can be from a plurality of reference patients. For instance, the first portion of the medical imaging data can be reference data from a plurality of patients. Furthermore, the first portion of the medical imaging data can be matched to a corresponding age group for a set of patient identities associated with the first portion of the medical imaging data).
As per claim 16, Zhang and Kullberg disclose the method according to claim 13, wherein step of obtaining a subject data set comprises the steps of:
obtaining at least one respective whole-body medical image of said associated subject in a subject image space (Kullberg, ¶0017, a method for registration of whole body volume images comprises obtaining a first image and a second image. The first image is a whole body volume image comprising water and fat magnetic resonance image data and the second image is a whole body volume image comprising water and fat magnetic resonance image data);
registering whole-body medical images of said at least one whole-body medical image of said subject data set, being in an image space different from said common image space, to said common image space by use of said common image registering routine (Kullberg, ¶0017, a method for registration of whole body volume images comprises obtaining a first image and a second image. The first image is a whole body volume image comprising water and fat magnetic resonance image data and the second image is a whole body volume image comprising water and fat magnetic resonance image data. Bone tissue is identified from the first image creating a first bone image, and bone tissue is identified from the second image creating a second bone image. Water components are separated from the first image, generating a first water image based on absolute water content, and water components are separated from the second image, generating a second water image based on absolute water content. Fat components are separated from the first image, generating a first fat image based on absolute fat content, and fat components are separated from the second image, generating a second fat image based on absolute fat content. The first image is registered to the second image by deforming the first bone image according to a bone tissue deformation rule, deforming the first water image according to a water tissue deformation rule under constraints of the deformation of the first bone image and deforming the first fat image according to a fat tissue deformation rule under constraints of the deformation of the first bone image and the deformation of the first water image).
As per claim 19, Zhang and Kullberg disclose the method according to claim 13, wherein said training subject data sets are training subject data sets of at least one respective whole-body medical image of at least two, non-simultaneous instances (Zhang, ¶0022; Kullberg, ¶0150, The analysis of images is typically based on multispectral image data collected from different subjects (whole bodies) or at different points in time. This approach may be used to combine whole-body image data from, for instance, healthy subjects to create a statistical atlas that contains detailed statistics on tissue morphology, function, and metabolism in all voxels in the entire body);
wherein said assigned image inference is an assigned image inference of an associated subject for at least one of said at least two instances for each training data set, registered to a respective set common image space (Zhang, ¶0022; Kullberg, ¶0149, By applying an image registration process, image data from a large number of healthy subjects (whole bodies) can be deformed to a common coordinate system to create a mean shape or reference person in which each voxel may be considered to contain a distribution of all imaging parameters 720-722 measured in an entire cohort of individuals;
wherein said subject data set is a subject data set of at least one whole-body medical image of at least two, non-simultaneous, instances of an associated subject (Zhang, ¶0022; Kullberg, ¶0151, By using the atlas, image data from each individual dataset may then be compared to this statistical atlas, in order to calculate deviations in each pixel from all image parameters collected, such as fat and water content, FDG-uptake, etc. in the entire body, as illustrated by the diagrams in part C of FIG. 7); and further comprising:
registering whole-body medical images of said at least two instances to a common image space of a common image by use of a common image registering routine (Kullberg, ¶0201).
As per claim 20, Zhang and Kullberg disclose he method according to claim 13, wherein at least one of said assigned image inference and an assigned automatic image inference, if any, comprises lesion segmentation, whereby said trained neural network being trained with at least one of said assigned image inference and an assigned automatic image inference, if any, comprising lesion segmentation (Zhang, ¶0033, The system 200 includes the machine learning component 102 and a medical imaging diagnosis process 202. The machine learning component 102 can include the atlas map component 104, the deviation map component 106, the neural network component 108, the processor 110 and/or the memory 112 ... the medical imaging diagnosis process 202 can perform deep learning to facilitate classification and/or localization of one or more diseases ... A disease classified and/or localized by the medical imaging diagnosis process 202 can include, for example, a lung disease, a heart disease, a tissue disease, a bone disease, a tumor, a cancer, tuberculosis, cardiomegaly, hypoinflation of a lung, opacity of a lung, hyperdistension, a spine degenerative disease, calcinosis, or another type of disease associated with an anatomical region of a patient body; Kullberg, ¶0080, embodiments of the present disclosure allow not only signal intensity from MRI or PET images to be compared. Also, fusion of image data will also cause different regions of a subject (whole body) to expand/contract and this can be used to estimate deviations in local volumes, of for example abdominal fat, muscles or liver, and also local deformations. Multiple local feature/texture measures, such as intensity heterogeneity may also be measured, which can be used to determine deviations of tissue heterogeneity, for example due to pathologies such as tumors or fibrosis; Kullberg, ¶0194, image features, wherever mentioned may comprise one or more of signal intensities, features derived from a deformation field, typically regional volumes, and filtered measures, such as texture, segmented tissue).
As per claim 21, Zhang and Kullberg disclose the method according to claim 13, wherein said common image space is selected to be an image space of said whole-body medical image (201A, 201B, 202A, 202B) one of said at least two instances (Kullberg, ¶0094-0097, The image registration method as presented in this particular embodiment comprises: Articulated, piece-wise affine, registration of bone sections; Registration of water images with constraints on bone; and Registration of fat images with constraints on bone and water).
As per claim 23, Zhang and Kullberg disclose the method according to claim 13, comprising the further step of creating said whole-body divergence image (Kullberg, ¶0201, In 53, the method alternatively comprises performing a comparison of image features, or image features derived from a deformation field, of the method for registration of volume images from a set of registered volume images of a whole body and a volume image atlas of registered volume images of multiple whole bodies enabling detecting where and how image features from a whole body deviate from image features from multiple whole bodies of the atlas of volume images).
As per claim 24, Zhang and Kullberg disclose the method according to claim 23, wherein said step of creating said whole-body divergence image in turn comprises the steps of:
creating a whole-body health statistical atlas (Kullberg, ¶0146, The invention thus enables, among other aspects, the creation of a statistical atlas being a statistical representation of image features such as tissue morphology, and characteristics as function and metabolism in all voxels of a studied whole body);
obtaining a whole-body medical image of an investigated subject (Kullberg, ¶0151, By using the atlas, image data from each individual dataset may then be compared to this statistical atlas, in order to calculate deviations in each pixel from all image parameters collected);
registering at least one of said whole-body health statistical atlas and said whole-body medical image to a common image space, using said image registering routine (Kullberg, ¶0201); and
deriving a whole-body divergence image as a comparison between said whole-body medical image of said investigated subject and said whole-body health statistical atlas (Kullberg, ¶0201, In 53, the method alternatively comprises performing a comparison of image features, or image features derived from a deformation field, of the method for registration of volume images from a set of registered volume images of a whole body and a volume image atlas of registered volume images of multiple whole bodies enabling detecting where and how image features from a whole body deviate from image features from multiple whole bodies of the atlas of volume images).
As per claim 44, Zhang and Kullberg disclose the method according to claim 1, wherein said image inference comprises at least one of: segmentation; classification; regression; and image registration in combination with image segmentation (Kullberg, ¶0046, in cases in which studied bodies or objects are pre-segmented an improved registration may be of benefit; Kullberg, ¶0107, the method for registration of whole body volume images comprises the further step of segmenting the first image and the second image into segments, wherein the step of registering is performed for each segment. In other words, the registering thus comprises matching of said segments between said first image and said second image. In a further embodiment, the step of segmenting the first image and said second image is performed in the first water image and the second water image, identifying organs).
As per claim 45, Zhang discloses a tool for automated image inference (Zhang, ¶0023, Zhang, ¶0029, Zhang, ¶0030; Zhang, ¶0048; Zhang, ¶0052; Zhang, Figure 1; Zhang, Figure 8), comprising:
a processor; an input for subject data sets; an output for subject image inference; and computer program instructions; whereby said computer program instructions, when being executed by said processor cause said processor (Zhang, ¶0006, using a processor operatively coupled to memory to execute computer executable components to perform acts such as generating atlas map data) to
form a registered subject data set from a subject data set of at least one medical image (Zhang, ¶0028);
whereby said computer program instructions, when being executed by said processor further cause said processor to operate a trained neural network with said registered subject data set as input data, resulting in an image inference being provided to said output (Zhang, ¶0023, Zhang, ¶0029, Zhang, ¶0030; Zhang, ¶0048; Zhang, ¶0052; Zhang, Figure 1; Zhang, Figure 8);
wherein said trained neural network being trained with registered training subject data sets of at least one respective medical image, an associated assigned image inference of an associated subject (Zhang, ¶0025; Zhang, ¶0026, atlas map);
whereby said computer program instructions, when being executed by said processor further cause said processor to operate a trained neural network with said registered subject data set as input data, resulting in an image inference being provided to said output (Zhang, ¶0023, Zhang, ¶0029, Zhang, ¶0030; Zhang, ¶0048; Zhang, ¶0052; Zhang, Figure 1; Zhang, Figure 8);
wherein said computer program instructions, when being executed by said processor, further cause at least one of: i) said subject data set is a subject data set in a common space of a common image (Zhang, ¶0028);
said subject data set comprising at least one image of voxel-wise state of health obtained by said input, in a common space of a common image (Zhang, ¶0026; Zhang, ¶0028);
said training subject data sets further comprises at least one training image of voxel-wise state of health, all registered to a set common image space of a set common image, where said at least one training image of voxel-wise state of health comprises a divergence image based on a comparison between said medical image of said respective associated training subject and collective image information of a group of subjects (Zhang, ¶0026; Zhang, ¶0028, deviation map);
wherein said at least one image of voxel-wise state of health comprises a divergence image being based on a comparison between said medical image of said associated subject and collective image information of a group of subjects (Zhang, ¶0022);
whereby said computer program instructions, when being executed by said processor cause said processor to: obtain medical images for said group of subjects (Zhang, ¶0022);
register medical images of said medical images for said group of subjects to said common image space by a common image registering routine (Zhang, ¶0022); and
create said divergence image by comparing said medical image of said associated subject with registered said medical images for said group of subjects (Zhang, ¶0026; Zhang, ¶0028); and
ii) said subject data set is a subject data set in a common space of a common image (Zhang, ¶0022);
whereby said computer program instructions, when being executed by said processor cause said processor to form a registered subject data set from at least one medical image (221A, 221B, 222A, 222B), obtained by said input (13), of at least two, non-simultaneous, instances of an associated subject (Zhang, ¶0022);
whereby said computer program instructions, when being executed by said processor cause said processor to perform a registering of medical images of said at least two instances to a common image space of a common image by use of a common image registering routine (Zhang, ¶0022);
wherein said trained neural network being trained with training subject data sets of at least one respective medical image of at least two, non-simultaneous, instances, and an assigned image inference of an associated subject for at least one of said at least two instances for each subject data set, registered to a respective set common image space (Zhang, ¶0022; Zhang, ¶0023, Zhang, ¶0029, Zhang, ¶0030; Zhang, ¶0048; Zhang, ¶0052; Zhang, Figure 1; Zhang, Figure 8);
whereby said computer program instructions, when being executed by said processor further cause said processor to operate a trained neural network with said registered subject data set as input data, resulting in an image inference being provided to said output (Zhang, ¶0023, Zhang, ¶0029, Zhang, ¶0030; Zhang, ¶0048; Zhang, ¶0052; Zhang, Figure 1; Zhang, Figure 8);
wherein said trained neural network being trained with registered training subject data sets of at least one respective medical image, an associated assigned image inference of an associated subject and at least one training image of voxel-wise state of health, all registered to a set common image space of a set common image, where said at least one training image of voxel-wise state of health comprises a divergence image based on a comparison between said medical image of said respective associated training subject and collective image information of a group of subjects (Zhang, ¶0026; Zhang, ¶0028).
Zhang does not explicitly disclose the following limitations as further recited however Kullberg discloses
wherein said common image registering routine comprises at least two part registering steps (Kullberg, ¶0094-0097, The image registration method as presented in this particular embodiment comprises: Articulated, piece-wise affine, registration of bone sections; Registration of water images with constraints on bone; and Registration of fat images with constraints on bone and water), in at least one of which:
images of different respective tissues in said whole-body medical images are obtained, a part registering to said common space is performed by optimizing a weighted cost function comprising a correlation of said images of respective tissues of said whole-body medical image to images of respective tissues of said common image as well as a correlation of said whole-body medical images to a whole-body medical image of said common image, thereby obtaining deformation parameters defining said part registration for said whole-body medical image (Kullberg, ¶0017; Kullberg, ¶0018; Kullberg, ¶0098, a variational approach to image registration may be used; Kullberg, ¶0099, In a deformable registration, the deformation fields may be parameterized; Kullberg, ¶0100; Kullberg, ¶0101-0104, Cost functions S used in this embodiment comprise: Sum of squared differences (SDD) Landmark term: Anatomical landmarks can be used to guide the registration process; Kullberg, ¶0105—0108; Kullberg, ¶0115; Kullberg, ¶0117, The cost functions used in the individual steps of the registration procedure may be weighted sums of cost functions);
wherein said deformation parameters of one part registration step, except for a last part registration step, is used in a subsequent part registration step and wherein said deformation parameters of said last part registration step is used for creating final registered whole-body medical images (Kullberg, ¶0094-0097, The image registration method as presented in this particular embodiment comprises: Articulated, piece-wise affine, registration of bone sections; Registration of water images with constraints on bone; and Registration of fat images with constraints on bone and water; Kullberg, ¶0090; Kullberg, ¶0141).
It would have been obvious to one skilled in the art before the effective filing date of the claimed invention to combine the teachings of Kullberg and Zhang because they are in the same field of endeavor. One skilled in the art would have been motivated to include the whole-body images as taught by Kullberg in the system of Zhang in order to enable the detection of where and how image features from a whole body deviate from image features from multiple whole bodies of an atlas of volume images (Kullberg, ¶0201).
As per claim 46, Zhang discloses computer program instructions, which computer program instruction, when being executed by a processor cause said processor to
form a registered subject data set from an obtained subject data set of at least one medical image (Zhang, ¶0028);
whereby said computer program instructions, when being executed by said processor further cause said processor to operate a trained neural network with said registered subject data set as input data, resulting in an image inference being provided to said output (Zhang, ¶0023, Zhang, ¶0029, Zhang, ¶0030; Zhang, ¶0048; Zhang, ¶0052; Zhang, Figure 1; Zhang, Figure 8);
wherein said trained neural network being trained with registered training subject data sets of at least one respective medical image, an associated assigned image inference of an associated subject (Zhang, ¶0025; Zhang, ¶0026, atlas map);
whereby said computer program instructions, when being executed by said processor further cause said processor to operate a trained neural network with said registered subject data set as input data, resulting in an image inference being provided to said output (Zhang, ¶0023, Zhang, ¶0029, Zhang, ¶0030; Zhang, ¶0048; Zhang, ¶0052; Zhang, Figure 1; Zhang, Figure 8);
wherein said computer program instructions, when being executed by said processor further cause at least one of: i) said subject data set is a subject data set in a common space of a common image (Zhang, ¶0028);
said subject data set comprising at least one image of voxel-wise state of health, in a common space of a common image (Zhang, ¶0026; Zhang, ¶0028);;
said training subject data sets further comprises at least one training image of voxel-wise state of health, all registered to a set common image space of a set common image, where said at least one training image of voxel-wise state of health comprises a divergence image based on a comparison between said medical image of said respective associated training subject and collective image information of a group of subjects (Zhang, ¶0026; Zhang, ¶0028, deviation map);
wherein said at least one image of voxel-wise state of health comprises a divergence image being based on a comparison between said whole-body medical image of said respective associated training subject and collective image information of a group of subjects (Zhang, ¶0022);
whereby said computer program instructions further cause said processor to: obtain medical images for said group of subjects (Zhang, ¶0022);
register medical images of said medical images for said group of subjects to said common image space by a common image registering routine (Zhang, ¶0022); and
create said divergence image by comparing said whole-body medical image of said associated subject with registered said medical images for said group of subjects (Zhang, ¶0026; Zhang, ¶0028); and
ii) said subject data set is a subject data set in a common space of a common image (Zhang, ¶0022);
whereby said computer program instructions, when being executed by said processor cause said processor to form a registered subject data set from at least one medical image, obtained by said input, of at least two, non-simultaneous, instances of an associated subject (Zhang, ¶0022);
whereby said computer program instructions, when being executed by said processor cause said processor to perform a registering of whole-body medical images of said at least two instances to a common image space of a common image by use of a common image registering routine (Zhang, ¶0022);
wherein said trained neural network being trained with training subject data sets of at least one respective medical image of at least two, non-simultaneous, instances, and an assigned image inference of an associated subject for at least one of said at least two instances for each subject data set, registered to a respective set common image space (Zhang, ¶0022; Zhang, ¶0023, Zhang, ¶0029, Zhang, ¶0030; Zhang, ¶0048; Zhang, ¶0052; Zhang, Figure 1; Zhang, Figure 8);
and whereby said computer program instructions further cause said processor to operate a trained neural network with said registered subject data set as input data, resulting in an image inference being provided (Zhang, ¶0023, Zhang, ¶0029, Zhang, ¶0030; Zhang, ¶0048; Zhang, ¶0052; Zhang, Figure 1; Zhang, Figure 8);
wherein said trained neural network being trained with registered training subject data sets of at least one respective medical image, an associated assigned image inference of an associated subject and at least one training image of voxel-wise state of health, all registered to a set common image space of a set common image, where said at least one training image of voxel-wise state of health comprises a divergence image based on a comparison between said medical image of said respective associated training subject and collective image information of a group of subjects (Zhang, ¶0022; Zhang, ¶0023; Zhang, ¶0026; Zhang, ¶0028; Zhang, ¶0029, Zhang, ¶0030; Zhang, ¶0048; Zhang, ¶0052; Zhang, Figure 1; Zhang, Figure 8).
Zhang does not explicitly disclose the following limitations as further recited however Kullberg discloses
wherein said common image registering routine comprises at least two part registering steps (Kullberg, ¶0094-0097, The image registration method as presented in this particular embodiment comprises: Articulated, piece-wise affine, registration of bone sections; Registration of water images with constraints on bone; and Registration of fat images with constraints on bone and water),, in at least one of which:
images of different respective tissues in said whole-body medical images are obtained, a part registering to said common space is performed by optimizing a weighted cost function comprising a correlation of said images of respective tissues of said whole-body medical image to images of respective tissues of said common image as well as a correlation of said whole-body medical images to a whole-body medical image of said common image, thereby obtaining deformation parameters defining said part registration for said whole-body medical image (Kullberg, ¶0017; Kullberg, ¶0018; Kullberg, ¶0098, a variational approach to image registration may be used; Kullberg, ¶0099, In a deformable registration, the deformation fields may be parameterized; Kullberg, ¶0100; Kullberg, ¶0101-0104, Cost functions S used in this embodiment comprise: Sum of squared differences (SDD) Landmark term: Anatomical landmarks can be used to guide the registration process; Kullberg, ¶0105—0108; Kullberg, ¶0115; Kullberg, ¶0117, The cost functions used in the individual steps of the registration procedure may be weighted sums of cost functions);
wherein said deformation parameters of one part registration step, except for a last part registration step, is used in a subsequent part registration step and wherein said deformation parameters of said last part registration step is used for creating final registered whole-body medical images (Kullberg, ¶0094-0097, The image registration method as presented in this particular embodiment comprises: Articulated, piece-wise affine, registration of bone sections; Registration of water images with constraints on bone; and Registration of fat images with constraints on bone and water; Kullberg, ¶0090; Kullberg, ¶0141).
It would have been obvious to one skilled in the art before the effective filing date of the claimed invention to combine the teachings of Kullberg and Zhang because they are in the same field of endeavor. One skilled in the art would have been motivated to include the whole-body images as taught by Kullberg in the system of Zhang in order to enable the detection of where and how image features from a whole body deviate from image features from multiple whole bodies of an atlas of volume images (Kullberg, ¶0201)
As per claim 47, Zhang and Kullberg disclose the method according to claim 1, comprising the further step of creating said whole-body divergence image (Kullberg, ¶0201, In 53, the method alternatively comprises performing a comparison of image features, or image features derived from a deformation field, of the method for registration of volume images from a set of registered volume images of a whole body and a volume image atlas of registered volume images of multiple whole bodies enabling detecting where and how image features from a whole body deviate from image features from multiple whole bodies of the atlas of volume images).
As per claim 48, Zhang and Kullberg disclose the method according to claim 47, wherein said step of creating said whole-body divergence image comprises the steps of:
creating a whole-body health statistical atlas (Kullberg, ¶0146, The invention thus enables, among other aspects, the creation of a statistical atlas being a statistical representation of image features such as tissue morphology, and characteristics as function and metabolism in all voxels of a studied whole body);
obtaining a whole-body medical image of an investigated subject (Kullberg, ¶0151, By using the atlas, image data from each individual dataset may then be compared to this statistical atlas, in order to calculate deviations in each pixel from all image parameters collected);
registering at least one of said whole-body health statistical atlas and said whole-body medical image to a common image space, using said image registering routine (Kullberg, ¶0201);
deriving a whole-body divergence image as a comparison between said whole-body medical image of said investigated subject and said whole-body health statistical atlas (Kullberg, ¶0201, In 53, the method alternatively comprises performing a comparison of image features, or image features derived from a deformation field, of the method for registration of volume images from a set of registered volume images of a whole body and a volume image atlas of registered volume images of multiple whole bodies enabling detecting where and how image features from a whole body deviate from image features from multiple whole bodies of the atlas of volume images).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TRACY MANGIALASCHI whose telephone number is (571)270-5189. The examiner can normally be reached M-F, 9:30AM TO 6:00PM.
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, Vu Le can be reached at (571) 272-7332. 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.
/TRACY MANGIALASCHI/Primary Examiner, Art Unit 2668
