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 .
Response to Amendment
Applicant’s amendments and remarks, filed 11/19/2025, are acknowledged. Rejections and/or objections not reiterated from previous office actions are hereby withdrawn. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
Status of Claims
Claims 1-20 are currently under examination.
Priority
No priority claim has been filed. The effective filing date of the instant application of 04/30/2020 is acknowledged.
Response to Arguments
Applicant’s responses and arguments filed 11/19/2025 regarding claim rejections under 35 USC 103 have been fully considered.
Regarding the claim rejections under 35 USC 103, Applicant has amended the independent claims for clarifying the scope of the invention changing the scope of the claims and therefore necessitating new grounds of rejections.
Applicant argues that the references of record do not teach specifically the amended limitation therefore teaching the classification of the positive tracts followed subsequently by the identification of the negative tracks from the positive tracts using a filtering process based on distance and shape between tracts.
In response, the examiner is recognizing that the identification of the positive tracts as performed by De Piccoli is done with combining clustering with distance and shape analysis therefore performing the identification of the positive and negative tracts during the analysis process and one of ordinary skill in the art would understand as obvious that the identification of the positive tract is performed initially in order to identify the remaining tracts as negative tracts when using the clustering analysis with the similarity technique as developed by De Piccoli as in Chapts.4 and 5 when using growing regions for identifying the clustered tracts as belonging to a searched tract as positive tract based on known reference tracts as preliminary processed for bundle segmentation (see p.12 summary of the thesis chapter) and since in order to identify the negative tracts relative to the positive tracts based on their distances and shape differences from the positive tracts as identified using the reference tracts, one person of ordinary skills in the art would recognize that identification of the positive tracts has to be initially performed as the initial step as classification step. Therefore, the examiner takes the position that De Piccoli teaches the amended limitation as written and therefore find the Applicant’s argument as not persuasive.
. 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.
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.
For the purpose of clarity of the rejection, the text provided within brackets as followed represents limitation(s) or part(s) thereof that is/are not taught by the respective reference, which are addressed later in the rejection, e.g., [...Limitation not taught...].
The following rejections are modified in view of amendment.
Claims 1-5, 11-13, 15, 17 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (2019 MICCAI 2019 LNCS 11766:599-608; Pub.Date ePub 10/10/2019) in view of Butz-Ostendorf (USPN 20220230752 A1; Pub.Date 07/21/2022; Fil.Date 06/03/2019) with evidentiary reference Alexander et al. (2007 J Am Soc Exp NeuroTherapeutics 4:316-329; Pub.Date 2007) in view of De Piccoli (2018 PhD Thesis University of Verona Italy 133 pages; Pub.Date 2018).
Regarding independent claim 1, Zhang teaches a method of using a processor to automatically segment a preselected fiber neuronal tract in a selected data (Title, abstract and Fig. 1 (d) performing a patient specific segmentation of predicting the CST tract using specific extraction method such as FiberMap as exemplified in Fig. 3 on different patients presenting different pathologies), comprising:
[…recalling an input of the preselected fiber neuronal tract to be classified in the selected data, wherein the preselected fiber neuronal tract is operable to be selected by a user…];
Zhang does not specifically teach recalling an input of the preselected fiber neuronal tract to be classified in the selected data, wherein the preselected fiber neuronal tract is operable to be selected by a user but Butz-Ostendorf teaches within the same field of endeavor of providing a computer-implemented method for imaging and analyzing the patient brain for tractography (Title, abstract and [0212]) the use of a processor with a user interface module ([0181] and [0027]-[0029]) enabling the user selection of specific regions of brain atlas ([0181]) in order to parcellate the patient’s brain into disjunct areas and structures ([0143]-[0147]) with the selection directed to single fiber tracts ([0212], [0294]-[0295] for selecting specific tracts of the brain atlas) from tract data of specific atlas such as topographic data ([0221]-[0222]) such as using a healthy connectome database to assess the negative deviation of the patient connections relative to the healthy connection of the “human” healthy connectome ([0328]-[029]) therefore teaching recalling an input of the preselected fiber neuronal tract to be classified in the selected data, wherein the preselected fiber neuronal tract is operable to be selected by a user.
Therefore it would have been obvious for a person of ordinary skill in the art before the effective filling date of the invention to have modified the method of Zhang such that the method further comprises: recalling an input of the preselected fiber neuronal tract to be classified in the selected data, wherein the preselected fiber neuronal tract is operable to be selected by a user, since one of ordinary skill in the art would recognize that preselecting a fiber neuronal tract within an atlas built with healthy subject for comparison with that corresponding tract from the patient for assessing the status of the tract was known in the art, as taught by Butz-Ostendorf. One of ordinary skill in the art would have expected that this modification could have been made with predictable results since both Butz-Ostendorf and Zhang teach analyzing tractography mapping of a subject. The motivation would have been to provide a method for a better indication of the pathological condition of the subject, as suggested by Butz-Ostendorf ([0241]-[0243]).
Zhang further teaches accessing the selected data of a subject with accessing subject specific dMRI data such as DTI data (Supplemental Data p. S2 Fig.S2 with DTI data and p.600 last ¶-p.601 first ¶ “Third, we demonstrate successful tract segmentation on a large test dataset (374 subjects). We believe the proposed method is the first fiber-based deep learning tract segmentation method that can generalize to dMRI data with different acquisition parameters and from different populations, including brain tumor patients” for the generation of global subject specific tractography image in Fig. 1d as obtaining subject specific tractograms from diffusion MRI (dMRI) data as selected data of a subject to provide and image “subject-specific unlabeled tractography data” Fig.1d bottom left image) with the evidentiary reference Alexander reviewing the DTI processed data to obtain the subject specific tractography image (Fig. 6);
evaluating the selected data based on a first criteria to determine an image tractography including a plurality of tracts (Supplemental data p.S2 and Fig.S2 with analysis of DTI imaging data and Fig. 1d analysis of the dMRI data for providing a global subject specific tractography image with p.600 last ¶-p.601 first ¶ “Third, we demonstrate successful tract segmentation on a large test dataset (374 subjects). We believe the proposed method is the first fiber-based deep learning tract segmentation method that can generalize to dMRI data with different acquisition parameters and from different populations, including brain tumor patients” wherein evidential reference Alexander describes the evaluation of the DTI data from the DWI image with production of the subject specific tractography and Zhang teaching the condition of wherein having or not having a tumor);
recalling a trained classification algorithm regarding at least the preselected fiber neuronal tract (Fig. 1 showing the method for creating the trained classification system being based at least with some selected or preselected neuronal tracts such as AF and CST with the Fig. 1a 1c and 1d and p.602-603 ¶ 2.2 CNN tract Segmentation Model Training, with a trained CNN model for tract segmentation using 100 subject dMRI tractography data for labelling 55 anatomical fiber tracts including “other fibers” class for fibers not being labelled within the 54 known tracts (p.601-602 ¶ 2.1 Datasets and p.S1 with listing of the 54 fiber tracts as given known fiber tracts)) and recalling the trained CNN classification system for labelling the subject specific tracts in Fig. 1d);
wherein the trained classification algorithm is configured to identify tracts based on:
diffusion weight information collected in the selected data as discussed above for accessing selected data as the data specific from the subject to be tested (Fig. 1d as obtaining subject specific tractograms from diffusion MRI (dMRI) data as selected data of a subject to provide and image “subject-specific unlabeled tractography data” Fig.1d bottom left image) the subject specific are tested to identify tracts using the algorithm (Fig.1d)
and a training set of image data different from the selected data (the training data for the classification algorithm for identifying tracts have been from selected HCP data as referred as dMRI data (see J 2.1 Datasets) where dMRI is known in the art to be diffusion weighted magnetic resonance imaging, the trained classification algorithm is based on dMRI/diffusion weight information ) wherein Zhang teaches the training set being different from the subject specific imaging data (Fig.1a training set versus Fig.1d subject specific data to be tested for tract identification) therefore reading on the amended limitation as claimed.
evaluating at least a sub-plurality of tracts of the plurality of tracts (p. 603 ¶ 2.4 Tract Segmentation of Unlabeled Tractography Data with registration of the subject specific tractography data with an atlas and Fig. 1b and 1d global subject specific segmentation of unlabeled tractography data as image of fibers in tractography image of the subject wherein each of the fibers are evaluated using FiberMap) with FiberMap feature descriptor is performing for each fiber of a tract the “encoding of the spatial coordinates of points along the fiber” wherein the encoding is considered as reading on a feature of the fiber at the determined point (p.602 ¶ 2.2) which reads on including determining points along each tract of the sub-plurality of tracts and evaluating a selected feature of at least a selected number of determined points of the determined points;
classifying each of the evaluated at least sub-plurality of tracts (Fig. 1d with prediction of the labelling of the subject specific fibers using the trained CNN such as the determination of labelled CST fibers and “other fibers” within the set of 54 labelled set of fibers (p.601-602 ¶ 2.1 Datasets and p.S1 with listing of the 54 fiber tracts as given known fiber tracts)) [...as a positive tract or negative tract based on the recalled trained classification and the preselected fiber neuronal tract, wherein each positive tract is at least a portion of the preselected fiber neuronal tract and each negative tract is are not at least a portion of the preselected fiber neuronal tract, wherein each negative tract is identified subsequent to classification of positive tracts by filtering tracts farthest in distance and most different in shape from positive tracts...];
determining whether at least one classified positive tract of the evaluated sub-plurality of tracts is a positive tract that is the preselected fiber neuronal tract (Fig. 1d with prediction of the labelling of the subject specific fibers using the trained CNN such as the determination of labelled CST fiber as the preselected fiber neuronal tract and “other fibers” within the set of 54 labelled set of fibers as other given fiber tracts(p.601-602 ¶ 2.1 Datasets, with the preselected fiber neuronal tract CST is displayed in Fig. 3 as extracted for each of the patient of reported pathological case and therefore is determined as a positive tract being the preselected neuronal tract);
outputting a representation of the preselected fiber neuronal tract that is at least one tract of the evaluated plurality of tracts is determined to be the preselected fiber neuronal tract (Fig. 1d final image of the subject specific tractography image with color labelled fiber tracts and Fig.3 for outputting a specific preselected fiber tract such as AF or/and CST fiber tract).
Zhang, Butz-Ostendorf and Alexander do not specifically teach classifying each tract of the evaluated at least sub-plurality of tracts as positive tracts or negative tracts, based on the recalled trained classification and the preselected fiber neuronal tract, wherein each positive tract is at least a portion of the preselected fiber neuronal tract and each negative tract is are not at least a portion of the preselected fiber neuronal tract, wherein each negative tract is identified subsequent to classification of positive tracts by filtering tracts farthest in distance and most different in shape from positive tracts as in claim 1.
However, De Piccoli teaches within the same field of endeavor of classification of brain fibers (Title and abstract) the review of the state in the art for segmentation of brain fibers from dMRI imaging techniques via reconstruction of fiber tracts from white matter of the brain (abstract, p13-31) with the generic and common consideration of the similarity concept used for supervised and unsupervised classification of the fiber tracts after selecting a specific fiber tract to be segmented (p.13-31 with the common practice to “focus on selected white matter fiber bundles” p.9 3rd ¶ with supervised/unsupervised training for fiber clustering p.20-24) based on a clustering/distance classification (Fig.2.4). De Piccoli teaches the development of a new similarity (or di-similarity) approach for classifying the fiber tracts combining a similarity distance point-to-point and similarity in shape with the “NewSimilarity metric” (Fig.2.1 and chap.4 and Fig.4.1 with distance similarity (point-to-point) and shape (similarity shape)) as used for performing classification of the fibers and their validation (Fig. 2.4) with presenting the importance of combining the location or distance between fiber as first parameter and shape of the fibers for classification (p.31-32 ¶ 2.4 Conclusions). Additionally De Piccoli teaches the use of the clustering process with the NewSimilarity metric for identifying the considered tracts of interest as considered as positive wherein therefore performing the identification of the positive and negative tracts during the analysis process and one of ordinary skill in the art would understand as obvious that the identification of the positive tract is performed initially in order to identify the remaining tracts as negative tracts when using the clustering analysis with the similarity technique as developed by De Piccoli as in Chapts.4 and 5 when using growing regions for identifying the clustered tracts as belonging to a searched tract as positive tract based on known reference tracts as preliminary processed for bundle segmentation (see p.12 summary of the thesis chapters) and since in order to identify the negative tracts relative to the positive tracts based on their distances and shape differences from the positive tracts as identified using the reference tracts, one person of ordinary skills in the art would recognize that identification of the positive tracts has to be initially performed as the initial step as classification step, therefore De Piccoli teachings are reading on classifying each tract of the evaluated at least sub-plurality of tracts as positive tracts or negative tracts, based on the recalled trained classification and the preselected fiber neuronal tract, wherein each positive tract is at least a portion of the preselected fiber neuronal tract and each negative tract is are not at least a portion of the preselected fiber neuronal tract, wherein each negative tract is identified subsequent to classification of positive tracts by filtering tracts farthest in distance and most different in shape from positive tracts as claimed.
Therefore it would have been obvious for a person of ordinary skill in the art before the effective filling date of the invention to have modified the method of Zhang and Alexander such that the method further comprises: classifying each tract of the evaluated at least sub-plurality of tracts as positive tracts or negative tracts, based on the recalled trained classification and the preselected fiber neuronal tract, wherein each positive tract is at least a portion of the preselected fiber neuronal tract and each negative tract is are not at least a portion of the preselected fiber neuronal tract, wherein each negative tract is identified subsequent to classification of positive tracts by filtering tracts farthest in distance and most different in shape from positive tracts, since one of ordinary skill in the art would recognize that preselecting a fiber neuronal tract for identifying and segmenting it for reconstruction within a patient image using a distance measure and a shape index was known in the art with supervised or unsupervised classification, as taught by De Piccoli. One of ordinary skill in the art would have expected that this modification could have been made with predictable results since both De Piccoli and Zhang teach providing a tractography mapping of a subject. The motivation would have been to provide a method for better classifying fiber neuronal tract with a better similarity index including distance and shape, as suggested by De Piccoli (p.55 ¶ 3.4 Conclusions).
Regarding the dependent claims 2-5, 11-13, 20, all the elements of these claims are disclosed by the teaching of Zhang, Butz-Ostendorf, with evidential reference Alexander and De Piccoli.
Regarding claim 2, Zhang teaches the accessed selected data includes diffusion weighted gradient images of the subject since Zhang teaches the subject specific tractography images acquired with DTI conventionally known in the art to be obtained with diffusion weighted images (DWI as in Fig.1d) as Alexander is describing the DTI data (p.316 col.1 2nd ¶ to col.2 1st ¶ “The diffusion of water within tissues will be altered by changes in the tissue microstructure and organization; consequently, diffusion-weighted (DW) MRI methods, including DTI, are potentially powerful probes for characterizing the effects of disease and aging on microstructure” and p.319 col.2 last ¶ “Maps of DTI measures are estimated from the raw DW images”).
Regarding claim 3, Zhang teaches with the use of DTI imaging data for the determination of the global subject specific tractography images (Fig. 1d) implicitly determining an anisotropy of water within an image of the selected data; and determining tracts through the image based on the determined anisotropy, since evidential reference Alexander reviewed the DTI imaging data analysis as measuring the signal attenuation from water diffusion for characterizing the three-dimensional diffusion of water (p.316 Introduction) with its anisotropy as function of the spatial location (abstract) for the determination of white matter connectivity (p.316 Introduction) leading to the identification of the subject specific tracts (p.321 col.2 last ¶ to p.322 col.1 1st with Fig.6 representing some color coded tracts).
Regarding claim 4, as discussed above for claim 1 and Dyer teachings, Dyer teaches comparing the determined image tractography including the plurality of tracts to an atlas of fiber neuronal tracts as claimed with using database for defining the extrinsic data/tracts ([0057]) and analyzing the patient tracts as intrinsic data/tract ([0057]), wherein the analysis is starting with the selection of a predetermined/preselected tract/fiber bundle from the extrinsic data/tracts and performing a comparison of the image data/tract data from the patient with the preselected tract with identifying the overlap between the preselected tract and the intrinsic or patient image tracts ([0061]).
Regarding claim 5, Zhang teaches wherein evaluating all of the sub-plurality of tracts includes at least one of: (i) evaluating a fractional anisotropy at each point of the determined points, (ii) evaluating a diffusion-encoded-color at each point of the determined points or (iii) determining a distance from a starting region of each tract to an ending region of each tract or (iv) determining a curvature of the tract at each point of the determined points (p.604 ¶ 2.5 Experimental Evaluation – Comparison of Fiber Feature Descriptors “a CurTor descriptor that concatenated curvature and torsion at each point along a fiber (size: n×2) [8], a 2D-RAS+CurTor descriptor that concatenated the CurTor and Orig-RAS descriptors (size: n×5) [18], and the proposed FiberMap descriptor (size: 2n×2n×3). n = 15 points per fiber was used across all descriptors” therefore a curvature at each point of the determined points). Similarly, De Piccoli teaches the shape similarity with the determination/evaluation of the change of angle of the fibers at each of the determined points of the fibers in order to quantify the shape or change of shape along the fiber for quantifying the shape of the fiber (p.65 ¶ 4.3.1 Similarity of fibers in 5th ¶).
Regarding claim 11, Zhang teaches classify the evaluated at least the sub-plurality of tracts (Fig.1d classifying the unlabeled tracts of the subject specific tractography within the 55 classes including 54 known given tract classes and an “other tract” class, as discussed in claim 1) and determining whether at least one of the evaluated sub-plurality of tracts is the given fiber neuronal tract (Fig.1d identifying CST or Fig.3 identifying AF and CST) which implicitly teach the use of a processor or computer to perform the training of the CNN and the application of the trained neural network to the processed subject specific tractography tracts since the development of a CNN and its application is at least requiring the use of a processor due to the complexity of the intrinsic non-linearity of the calculations.
Regarding claim 12, Zhang teaches the acquisition of subject specific dMRI data (Title, p.600 last ¶ to p.601 1st ¶ “Third, we demonstrate successful tract segmentation on a large test dataset (374 subjects). We believe the proposed method is the first fiber-based deep learning tract segmentation method that can generalize to dMRI data with different acquisition parameters and from different populations, including brain tumor patients”, including DTI diffusion tensor imaging data for obtaining the subject specific tractography image (p.S2 Fig.S2 and Fig.1d) wherein, as discussed in claim 2, evidential reference Alexander is describing the DTI data (p.316 col.1 2nd ¶ to col.2 1st ¶ “The diffusion of water within tissues will be altered by changes in the tissue microstructure and organization; consequently, diffusion-weighted (DW) MRI methods, including DTI, are potentially powerful probes for characterizing the effects of disease and aging on microstructure” and p.319 col.2 last ¶ “Maps of DTI measures are estimated from the raw DW images”) therefore Zhang teaches acquiring diffusion weighted gradient images of the subject as claimed.
Regarding claim 13, Zhang teaches wherein the recalled preselected fiber neuronal tract is at least one of a cortico-spinal tract, an optical tract, a frontal aslant tract, a dentato rubro thalamic tract, a fornix tract, or combinations thereof (labelling of the subject CST as given tract in Fig.1d).
Regarding claim 20, Zhang teaches the classification algorithm as a learned CNN (abstract, Fig. 1 CNN tract classification model) therefore teaching the trained classification algorithm is associated with an artificial neural network or a convolution neural network as claimed.
Regarding independent claim 15, Zhang implicitly teaches the use of an imaging device for the acquisition of dMRI of the subjects for providing consistent tractography segmentation (Title, abstract and use of DTI imaging data in p.S2 and Fig.S3 to obtain a global subject specific tractography image as in Fig.1d with unlabeled tracts with performing a patient specific segmentation of predicting the CST tract using specific extraction method such as FiberMap as exemplified in Fig. 3 on different patients presenting different pathologies) with an implicit processor for processing the imaging signal and data) therefore teaching a system configured automatically segment a preselected fiber neuronal tract in an image of a subject, comprising: a processor system configured to execute instructions to automatically:
[…access an input of the preselected fiber neuronal tract to be classified in the selected data…]
Zhang further teaches access the selected data, wherein the preselected fiber neuronal tract accessed is at least one of a relevant fiber neuronal tract that is a limited number of neuronal tracks to be segmented from the selected data (Fig. 1 showing the method for creating the trained classification system being based at least with some selected or preselected neuronal tracts such as AF and CST with the Fig. 1a 1c and 1d and p.602-603 ¶ 2.2 CNN tract Segmentation Model Training, with a trained CNN model for tract segmentation using 100 subject dMRI tractography data for labelling 55 anatomical fiber tracts including “other fibers” class for fibers not being labelled within the 54 known tracts (p.601-602 ¶ 2.1 Datasets and p.S1 with listing of the 54 fiber tracts as given known fiber tracts)) and recalling the trained CNN classification system for labelling the subject specific tracts in Fig. 1d with accessing subject specific dMRI data such as DTI data (Supplemental Data p. S2 Fig.S2 with DTI data and p.600 last ¶-p.601 first ¶ “Third, we demonstrate successful tract segmentation on a large test dataset (374 subjects). We believe the proposed method is the first fiber-based deep learning tract segmentation method that can generalize to dMRI data with different acquisition parameters and from different populations, including brain tumor patients” for the generation of global subject specific tractography image in Fig. 1d as obtaining subject specific tractograms from diffusion MRI (dMRI) data as selected data of a subject to obtain “subject-specific unlabeled tractography data” Fig.1d bottom left image) with the evidentiary reference Alexander reviewing the DTI process to image the subject specific tractography image (Fig. 6);
evaluate the accessed selected data based on a first criteria to determine an image tractography including a plurality of tracts (Supplemental data p.S2 and Fig.S2 with analysis of DTI imaging data and Fig. 1d analysis of the dMRI data for providing a global subject specific tractography image with p.600 last ¶-p.601 first ¶ “Third, we demonstrate successful tract segmentation on a large test dataset (374 subjects). We believe the proposed method is the first fiber-based deep learning tract segmentation method that can generalize to dMRI data with different acquisition parameters and from different populations, including brain tumor patients” wherein evidential reference Alexander describes the evaluation of the DTI data from the DWI image with production of the subject specific tractography and Zhang teaching the condition of wherein having or not having a tumor is used to testing the accuracy of the method);
recall a trained classification algorithm regarding at least on the preselected fiber neuronal tract (Fig. 1 showing the method for creating the trained classification system being based at least with some selected or preselected neuronal tracts such as AF and CST with the Fig. 1a 1c and 1d and p.602-603 ¶ 2.2 CNN tract Segmentation Model Training, with a trained CNN model for tract segmentation using 100 subject dMRI tractography data for labelling 55 anatomical fiber tracts including “other fibers” class for fibers not being labelled within the 54 known tracts (p.601-602 ¶ 2.1 Datasets)) and recalling the trained CNN classification system for labelling the subject specific tracts in Fig. 1d);
wherein the trained classification algorithm is configured to identify tracts based on:
diffusion weight information collected in the selected data as discussed above for accessing selected data as the data specific from the subject to be tested (Fig. 1d as obtaining subject specific tractograms from diffusion MRI (dMRI) data as selected data of a subject to provide and image “subject-specific unlabeled tractography data” Fig.1d bottom left image) the subject specific are tested to identify tracts using the algorithm (Fig.1d)
and a training set of image data different from the selected data (the training data for the classification algorithm for identifying tracts have been from selected HCP data as referred as dMRI data (see J 2.1 Datasets) where dMRI is known in the art to be diffusion weighted magnetic resonance imaging, the trained classification algorithm is based on dMRI/diffusion weight information ) wherein Zhang teaches the training set being different from the subject specific imaging data (Fig.1a training set versus Fig.1d subject specific data to be tested for tract identification) therefore reading on the amended limitation as claimed.
evaluate at least a sub-plurality of tracts of the plurality of tracts (p. 603 ¶ 2.4 Tract Segmentation of Unlabeled Tractography Data with registration of the subject specific tractography data with an atlas and Fig. 1b and 1d global subject specific segmentation of unlabeled tractography data as image of fibers in tractography image of the subject wherein each of the fibers are evaluated using FiberMap) with FiberMap feature descriptor is performing for each fiber of a tract the “encoding of the spatial coordinates of points along the fiber” wherein the encoding is considered as reading on a feature of the fiber at the determined point (p.602 ¶ 2.2) which reads on including determining points along each tract of the sub-plurality of tracts and evaluating a selected feature of at least a selected number of determined points of the determined points;
classify each of the evaluated at least the sub-plurality of tracts (Fig. 1d with prediction of the labelling of the subject specific fibers using the trained CNN such as the determination of labelled CST fibers and “other fibers” within the set of 54 labelled set of fibers (p.601-602 ¶ 2.1 Datasets and p.S1 with listing of the 54 fiber tracts as given known fiber tracts)) [...as positive tracts or negative tracts based on the recalled trained classification algorithm and the preselected fiber neuronal tract, where positive tracts are at least one of the preselected the fiber neuronal tracts and negative tracts are not at least one of the preselected the fiber neuronal tracts, wherein negative tracts are identified subsequent to classification of positive tracts by filtering tracts farthest in distance and most different in shape from positive tracts...];
determine whether at least one of the evaluated sub-plurality of tracts is a positive tract that is the preselected fiber neuronal tract (Fig. 1d with prediction of the labelling of the subject specific fibers using the trained CNN such as the determination of labelled CST fiber as the preselected fiber neuronal tract and “other fibers” within the set of 54 labelled set of fibers as other given fiber tracts(p.601-602 ¶ 2.1 Datasets, with the preselected fiber neuronal tract CST is displayed in Fig. 3 as extracted for each of the patient of reported pathological case); and
output a representation of the preselected fiber neuronal tract that is at least one of the evaluated plurality of tracts is determined to be the preselected fiber neuronal tract (Fig. 1d final image of the subject specific tractography image with color labelled fiber tracts and Fig.3 for outputting a specific preselected fiber tract such as AF or/and CST fiber tract).
While Zhang teaches the classification of the preselected fiber neuronal tract with “recalling a trained classification algorithm regarding at least the preselected fiber neuronal tract” as discussed above”, Zhang does not specifically teach access an input of the preselected fiber neuronal tract to be classified in the selected data and the preselected fiber neuronal tract selected by a user to be classified but Butz-Ostendorf teaches within the same field of endeavor of providing a computer-implemented method for imaging and analyzing the patient brain for tractography (Title, abstract and [0212]) the use of a processor with a user interface module ([0181] and [0027]-[0029]) enabling the user selection of specific regions of brain atlas ([0181]) in order to parcellate the patient’s brain into disjunct areas and structures ([0143]-[0147]) with the selection directed to single fiber tracts ([0212], [0294]-[0295] for selecting specific tracts of the brain atlas) from tract data of specific atlas such as topographic data ([0221]-[0222]) such as using a healthy connectome database to assess the negative deviation of the patient connections relative to the healthy connection of the “human” healthy connectome ([0328]-[029]) therefore teaching access an input of the preselected fiber neuronal tract to be classified in the selected data and the preselected fiber neuronal tract selected by a user to be classified.
Therefore it would have been obvious for a person of ordinary skill in the art before the effective filling date of the invention to have modified the system of Zhang as evidenced by Alexander such that the system further comprises: access an input of the preselected fiber neuronal tract to be classified in the selected data and the preselected fiber neuronal tract selected by a user to be classified, since one of ordinary skill in the art would recognize that preselecting a fiber neuronal tract within an atlas built with healthy subject for comparison with that corresponding tract from the patient for assessing the status of the tract was known in the art, as taught by Butz-Ostendorf. One of ordinary skill in the art would have expected that this modification could have been made with predictable results since both Butz-Ostendorf and Zhang teach analyzing tractography mapping of a subject. The motivation would have been to provide a method for a better indication of the pathological condition of the subject, as suggested by Butz-Ostendorf ([0241]-[0243]).
Zhang, Butz-Ostendorf and Alexander do not specifically teach classify each of the evaluated at least sub-plurality of tracts as positive tracts or negative tracts based on the recalled trained classification algorithm and the preselected fiber neuronal tract, where positive tracts are at least one of the preselected the fiber neuronal tracts and negative tracts are not at least one of the preselected the fiber neuronal tracts, wherein negative tracts are identified subsequent to classification of positive tracts by filtering tracts farthest in distance and most different in shape from positive tracts as in claim 15.
However, De Piccoli teaches within the same field of endeavor of classification of brain fibers (Title and abstract) the review of the state in the art for segmentation of brain fibers from dMRI imaging techniques via reconstruction of fiber tracts from white matter of the brain (abstract, p13-31) with the generic and common consideration of the similarity concept used for supervised and unsupervised classification of the fiber tracts after selecting a specific fiber tract to be segmented (p.13-31 with the common practice to “focus on selected white matter fiber bundles” p.9 3rd ¶ with supervised/unsupervised training for fiber clustering p.20-24) based on a clustering/distance classification (Fig.2.4). De Piccoli teaches the development of a new similarity (or di-similarity) approach for classifying the fiber tracts combining a similarity distance point-to-point and similarity in shape with the “NewSimilarity metric” (Fig.2.1 and chap.4 and Fig.4.1 with distance similarity (point-to-point) and shape (similarity shape)) as used for performing classification of the fibers and their validation (Fig. 2.4) with presenting the importance of combining the location or distance between fiber as first parameter and shape of the fibers for classification (p.31-32 ¶ 2.4 Conclusions). Additionally De Piccoli teaches the use of the clustering process with the NewSimilarity metric for identifying the considered tracts of interest as considered as positive wherein therefore performing the identification of the positive and negative tracts during the analysis process and one of ordinary skill in the art would understand as obvious that the identification of the positive tract is performed initially in order to identify the remaining tracts as negative tracts when using the clustering analysis with the similarity technique as developed by De Piccoli as in Chapts.4 and 5 when using growing regions for identifying the clustered tracts as belonging to a searched tract as positive tract based on known reference tracts as preliminary processed for bundle segmentation (see p.12 summary of the thesis chapters) and since in order to identify the negative tracts relative to the positive tracts based on their distances and shape differences from the positive tracts as identified using the reference tracts, one person of ordinary skills in the art would recognize that identification of the positive tracts has to be initially performed as the initial step as classification step, therefore De Piccoli teachings are reading on classify each of the evaluated at least sub-plurality of tracts as positive tracts or negative tracts based on the recalled trained classification algorithm and the preselected fiber neuronal tract, where positive tracts are at least one of the preselected the fiber neuronal tracts and negative tracts are not at least one of the preselected the fiber neuronal tracts, where negative tracts are identified subsequent to classification of positive tracts by filtering tracts farthest in distance and most different in shape from positive tracts as claimed.
Therefore it would have been obvious for a person of ordinary skill in the art before the effective filling date of the invention to have modified the system of Zhang, Butz-Ostendorf and Alexander such that the method further comprises: classifying each of the evaluated at least sub-plurality of tracts as positive tracts or negative tracts based on the recalled trained classification algorithm and the preselected fiber neuronal tract, where positive tracts are at least one of the preselected the fiber neuronal tracts and negative tracts are not at least one of the preselected the fiber neuronal tracts, wherein negative tracts are identified subsequent to classification of positive tracts by filtering tracts farthest in distance and most different in shape from positive tracts, since one of ordinary skill in the art would recognize that preselecting a fiber neuronal tract for identifying and segmenting it for reconstruction within a patient image using a distance measure and a shape index was known in the art with supervised or unsupervised classification, as taught by De Piccoli. One of ordinary skill in the art would have expected that this modification could have been made with predictable results since both De Piccoli and Zhang teach providing a tractography mapping of a subject. The motivation would have been to provide a method for better classifying fiber neuronal tract with a better similarity index including distance and shape, as suggested by De Piccoli (p.55 ¶ 3.4 Conclusions).
Regarding the dependent claim 17, all the elements of these claims are disclosed by the teaching of Zhang, Butz-Ostendorf, with evidential reference Alexander and De Piccoli.
Regarding claim 17, Zhang teaches implicitly a display for visualization and visual comparison of labelled tracts as in Fig.3, wherein the display is providing an image of the subject with the brain and the location of the given tract (Fig.3) therefore the display configured to display an image of the subject and the outputted given neuronal tract.
Claims 6-8 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (2019 MICCAI 2019 LNCS 11766:599-608; Pub.Date ePub 10/10/2019) in view of Butz-Ostendorf (USPN 20220230752 A1; Pub.Date 07/21/2022; Fil.Date 06/03/2019) with evidentiary reference Alexander et al. (2007 J Am Soc Exp NeuroTherapeutics 4:316-329; Pub.Date 2007) in view of De Piccoli (2018 PhD Thesis University of Verona Italy 133 pages; Pub.Date 2018) as applied to claim 1 and further in view of Pisner (USPN 20200167694 A1; Pub.Date 05/28/2020; Fil.Date 04/01/2019).
Zhang, Butz-Ostendorf, with evidential reference Alexander and De Piccoli teach a method as set forth above.
Zhang, Butz-Ostendorf, with evidential reference Alexander and De Piccoli do not specifically teach classifying the sub-plurality of tracts per a random forest classification system trained with classification criteria for the given fiber neuronal tract as in claim 6.
However, Pisner teaches within the same field of endeavor of analyzing tracts within brain connectomes (Title, abstract and [0012] “This can be accomplished using either deterministic or probabilistic tractography... This tracking process intimately depends both on the type of diffusion model fit to the data, as well as the method of tractography used once the model is fit... Various methods of deterministic and probabilistic tractography also exist, the majority of which share a common set of tracking hyperparameters including step size, curvature threshold, tissue classification approach, number of samples, length threshold, and others not stated herein”) the use of specific ensemble machine learning algorithms for performing classification accommodated for ensemble connectomes such as Random Forests since “they often produce more accurate solutions than a single model would” ([0031]).
Therefore it would have been obvious for a person of ordinary skill in the art before the effective filling date of the invention to have modified the method of Zhang and Alexander as modified by Butz-Ostendorf, Alexander and De Piccoli such that the method further comprises: classifying the sub-plurality of tracts per a random forest classification system trained with classification criteria for the given fiber neuronal tract, since one of ordinary skill in the art would recognize that classification of brain tracts using Random Forests algorithm was known in the art as taught by Pisner and since Zhang already teaches the trained classification system with a machine learning system as discussed in claim 1. One of ordinary skill in the art would have expected that this modification could have been made with predictable results since both Zhang l and Pisner both teach using either deterministic or probabilistic tractography and performing machine learning techniques applied to tractography and connectomes. The motivation would have been to use specific algorithms such as Random Forests known to provide more accurate solutions, as suggested by Pisner ([0031]).
Regarding the dependent claims 7-8, all the elements of these claims are anticipated by the teaching of Zhang, Butz-Ostendorf, with evidential reference Alexander, De Piccoli and Pisner.
Regarding claim 7, Zhang teaches the given fiber neuronal tract includes at least one brain fiber neuronal tract (Fig. 1 and Fig. 3 showing image and segmentation of AF and CST tracts as arcuate fasciculus and corticospinal tracts, p.601 2nd ¶ as neuronal tracts).
Regarding claim 8, Zhang teaches evaluating at least a sub-plurality of tracts of the plurality of tracts includes evaluating all of the plurality of tracts with labelling all the tracts as within the 54 known tracts and the remaining tracts as “other fibers/tracts” (Fig. 1 and p.601 2nd ¶ “In the present study, we used training fiber samples from a total of 54 tracts of interest, such as arcuate fasciculus (AF) and corticospinal tract (CST), for a total of 273379 fibers. We grouped the fibers from all other clusters and the rejected false positive fibers into the category of “other fibers” (a total of 726621 fibers). In total, we had 55 tract classes in the training dataset.”).
Claims 9-10 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (2019 MICCAI 2019 LNCS 11766:599-608; Pub.Date ePub 10/10/2019) in view of Butz-Ostendorf (USPN 20220230752 A1; Pub.Date 07/21/2022; Fil.Date 06/03/2019) with evidentiary reference Alexander et al. (2007 J Am Soc Exp NeuroTherapeutics 4:316-329; Pub.Date 2007) in view of De Piccoli (2018 PhD Thesis University of Verona Italy 133 pages; Pub.Date 2018) as applied to claim 1 and further in view of Kumar et al. (2017 in Proc. of GRAIL/MFCA/MICGen 2017, LNCS 10551:92–100; Pub.Date 2017) and Hwang (2012 PhD Thesis Biomedical Engineering USC 161 pages).
Zhang, Butz-Ostendorf, with evidential reference Alexander and De Piccoli teach a method as set forth above.
Regarding claim 9, as discussed for claim 5 above, Zhang teaches determining points along each tract of the sub-plurality of tracts and Zhang teaches outputting the given fiber neuronal tract when at least one of the evaluated plurality of tracts is determined to be a given fiber neuronal tract includes displaying the given fiber neuronal tract with a display device with an implicit display device for visualization of the given fiber neuronal tract and visual comparison as in Fig. 3. As discussed above, De Piccoli teaches a similar description than the anisotropy fraction by analyzing the change in angle at determined point along the fiber for characterizing the shape of the fiber.
Zhang does not specifically teach outputting representation of the preselected fiber neuronal tract includes displaying a graphical representation of the fiber neuronal tract superimposed on an image of the subject and evaluating a fractional anisotropy at each point of the determined points as in claim 9.
However, Kumar teaches similarly to De Piccoli the necessity of including a quantitative index reflecting the relationship between the microstructure and the geometry along the fibers (Title and abstract) with the evaluation of a general fraction anisotropy at each chosen points along the fiber (Fig.1 top left graph/image for comparing two associated fibers with GFA color-coded fibers and p.96 1st ¶) therefore teaching evaluating a fractional anisotropy at each point of the determined points as claimed.
Therefore it would have been obvious for a person of ordinary skill in the art before the effective filling date of the invention to have modified the method of Zhang as modified by Alexander and De Piccoli such that the method further comprises: evaluating a fractional anisotropy at each point of the determined points, since one of ordinary skill in the art would recognize that characterizing the shape and microstructure along the fiber with the determination of general fractional anisotropy at each chosen point along the fiber was known in the art, as taught by Kumar. One of ordinary skill in the art would have expected that this modification could have been made with predictable results since both De Piccoli and Kumar teach providing a tractography mapping of a subject using an additional shape descriptor along the fiber. The motivation would have been to provide a method for better classifying fiber neuronal tract with a better similarity index including distance and shape, as suggested by De Piccoli (p.55 ¶ 3.4 Conclusions) especially for characterizing brain diseases, as suggested by Kumar (abstract).
Additionally, Hwang teaches within the same field of endeavor of analyzing diffusion magnetic resonance (Title and abstract) the comparison between tracts from healthy control subjects and tract from a patient in order to observe the changes with outputting a representation of the control neuronal tract from healthy subjects as preselected fiber neuronal tract on a TBI image from the patient while displaying a representation of the TBI patient tract on the same TBI image from the patient (Fig. 10.6 and p.88 captions) in order to visualize the change in location of the tract to diagnosis a disease. One of ordinary skill in the art would have found obvious to provide the superimposition of the control tract data and of the patient tract data since both are already reported on the same reference image of the TBI patient (Figs. 10.6 – 10.10) and since providing a superimposition would have been a mere design consideration for displaying the results, therefore teaching or at least suggesting outputting representation of the preselected fiber neuronal tract includes displaying a graphical representation of the fiber neuronal tract superimposed on an image of the subject as claimed.
Therefore it would have been obvious for a person of ordinary skill in the art before the effective filling date of the invention to have modified the method of Zhang as modified by Alexander, Butz-Ostendorf, De Piccoli and Kumar such that the method further comprises: outputting representation of the preselected fiber neuronal tract includes displaying a graphical representation of the fiber neuronal tract superimposed on an image of the subject, since one of ordinary skill in the art would recognize that visualizing superimposed on the patient the patient TBI tract as selected tract and the control tract from several healthy subject was known in the art, as taught by Kumar and since assembling the representation of the control data and the patient data on the same patient image would have been a mere design consideration since they are already represented on the same reference image of the patient’s head. One of ordinary skill in the art would have expected that this modification could have been made with predictable results since both Hwang and Zhang are both teach providing a tractography mapping of a subject. The motivation would have been to provide a visualization of the difference between the patient’s tract and the control to reveal differences and abnormality for the patient’s tract to support a medical diagnosis for the patient, as suggested by Hwang (p.83 ¶ 10.3.4.1 and p.97 last ¶ and Fig. 10.10).
Regarding the dependent claim 10, all the elements of these claims are anticipated by the teaching of Zhang, Butz-Ostendorf with evidential reference Alexander, De Piccoli and Kumar.
Regarding claim 10, Zhang teaches identifying the given fiber neuronal tract with the CNN labelling the unlabeled subject specific tract (Fig. 1d).
Regarding claim 18, Zhang teaches acquiring dMRI data at least from DTI data (Title, p.600 last ¶ to p.601 1st ¶ “Third, we demonstrate successful tract segmentation on a large test dataset (374 subjects). We believe the proposed method is the first fiber-based deep learning tract segmentation method that can generalize to dMRI data with different acquisition parameters and from different populations, including brain tumor patients”, including DTI diffusion tensor imaging data for obtaining the subject specific tractography image (p.S2 Fig.S2 and Fig.1d) wherein, as discussed in claim 2, evidential reference Alexander is describing the DTI data from DWI as diffusion weighted images (p.316 col.1 2nd ¶ to col.2 1st ¶ “The diffusion of water within tissues will be altered by changes in the tissue microstructure and organization; consequently, diffusion-weighted (DW) MRI methods, including DTI, are potentially powerful probes for characterizing the effects of disease and aging on microstructure” and p.319 col.2 last ¶ “Maps of DTI measures are estimated from the raw DW images” and Alexander describing imaging sequences used for MRI devices to acquire DWI images in Fig.3) therefore teaching the use of an imaging system configured to acquire diffusion weighted gradient images of the subject.
As discussed above for claim 9, Zhang teaches determining points along each tract of the sub-plurality of tracts and Zhang teaches outputting the given fiber neuronal tract when at least one of the evaluated plurality of tracts is determined to be a given fiber neuronal tract includes displaying the given fiber neuronal tract with a display device with an implicit display device for visualization of the given fiber neuronal tract and visual comparison as in Fig. 3. As discussed above, De Piccoli teaches a similar description than the anisotropy fraction by analyzing the change in angle at determined point along the fiber for characterizing the shape of the fiber.
Zhang does not specifically teach evaluating a fractional anisotropy at each point of the determined points as in claim 18.
However, Kumar teaches similarly to De Piccoli the necessity of including a quantitative index reflecting the relationship between the microstructure and the geometry along the fibers (Title and abstract) with the evaluation of a general fraction anisotropy at each chosen points along the fiber (Fig.1 top left graph/image for comparing two associated fibers with GFA color-coded fibers and p.96 1st ¶) therefore teaching evaluating a fractional anisotropy at each point of the determined points as claimed.
Therefore it would have been obvious for a person of ordinary skill in the art before the effective filling date of the invention to have modified the method of Zhang as modified by Alexander and De Piccoli such that the method further comprises: evaluating a fractional anisotropy at each point of the determined points, since one of ordinary skill in the art would recognize that characterizing the shape and microstructure along the fiber with the determination of general fractional anisotropy at each chosen point along the fiber was known in the art, as taught by Kumar. One of ordinary skill in the art would have expected that this modification could have been made with predictable results since both De Piccoli and Kumar teach providing a tractography mapping of a subject using an additional shape descriptor along the fiber. The motivation would have been to provide a method for better classifying fiber neuronal tract with a better similarity index including distance and shape, as suggested by De Piccoli (p.55 ¶ 3.4 Conclusions) especially for characterizing brain diseases, as suggested by Kumar (abstract).
Claims 14 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (2019 MICCAI 2019 LNCS 11766:599-608; Pub.Date ePub 10/10/2019) in view of Butz-Ostendorf (USPN 20220230752 A1; Pub.Date 07/21/2022; Fil.Date 06/03/2019) with evidentiary reference Alexander et al. (2007 J Am Soc Exp NeuroTherapeutics 4:316-329; Pub.Date 2007) in view of De Piccoli (2018 PhD Thesis University of Verona Italy 133 pages; Pub.Date 2018) as applied to claims 1 and 15, and further in view of Thomas et al. (WO2014/139024 A1; Pub.Date 09/18/2014; Fil.Date 03/14/2024).
Zhang, Butz-Ostendorf, Alexander and De Piccoli teach a method as set forth above.
Zhang, Butz-Ostendorf, Alexander and De Piccoli do not specifically teach navigating an instrument relative to the outputted the given fiber neuronal tract as in claim 14.
Regarding claim 14, Thomas teaches within the same field of endeavor of medical imaging with tractography of the brain (Title and abstract, Fig. 1 DTI(3) and DWI(4) for tractography and p.15 2nd ¶ “use of tractography”) a navigation system (p.27 2nd ¶ “ the processor(s) may include navigation module(s) that analyze input(s) to provide visualization and other outputs during procedures, such as tool tracking, and contextual information” tracking the medical tool relative to the tractograms, and p.51 2nd ¶ “This functionality is achieved by hiding diffusion tracts (or tractography information) in all regions of the brain except for the tracts that intersect the geometric space occupied by the target region or within the immediate vicinity (within a threshold). Alternatively, the tracts that intersect the geometric space occupied by a surgical tool that is virtually inserted in the brain may be displayed. Such tool may be a virtual representation of a biopsy needle, a port for minimally invasive surgery (e.g. an access port), a deep brain stimulation needle, or a catheter, to name a few. This approach 20 of selective display of 0TI information helps manage the large-data problem associated with visualization of an entire 0TI image. It also aids the surgeon in narrowing their focus and seeing principally the impacted tracts, as opposed to all tractography information associated with the entire brain”) therefore teaching navigating an instrument relative to the outputted the given fiber neuronal tract as claimed.
Therefore it would have been obvious for a person of ordinary skill in the art before the effective filling date of the invention to have modified the method Zhang as modified by Butz-Ostendorf, Alexander and De Piccoli such that the method further comprises: navigating an instrument relative to the outputted the given fiber neuronal tract, since one of ordinary skill in the art would recognize that combining a tractography imaging of the patient brain within a navigation system for positioning a medical tool relative to selected cerebral tracts was known in the art as taught by Thomas. One of ordinary skill in the art would have expected that this modification could have been made with predictable results since both Zhang and Thomas both teach providing a tractography mapping with selected tracts of interest. The motivation would have been to provide visual support to the surgeon in narrowing their focus during the surgical procedure by providing visually the positioning of the medical tool relative to the tracts of interest to minimize the impact of the invasive surgery on the brain by preserving the functionality of the intact tracts, as suggested by Thomas (p.51 2nd ¶).
Zhang, Butz-Ostendorf, Alexander and De Piccoli teach a system as set forth above.
Zhang, Butz-Ostendorf, Alexander and De Piccoli do not specifically teach a navigation system including a tracking system and a tracking device; wherein an instrument is operable to be navigated relative to the output the given neuronal tract within the navigation system as in claim 19.
However, similarly to claim 14, Thomas teaches within the same field of endeavor of medical imaging with tractography of the brain (Title and abstract, Fig. 1 DTI(3) and DWI(4) for tractography and p.15 2nd ¶ “use of tractography”) a navigation system (p.27 2nd ¶ “ the processor(s) may include navigation module(s) that analyze input(s) to provide visualization and other outputs during procedures, such as tool tracking, and contextual information” tracking the medical tool relative to the tractograms, and p.51 2nd ¶ “This functionality is achieved by hiding diffusion tracts (or tractography information) in all regions of the brain except for the tracts that intersect the geometric space occupied by the target region or within the immediate vicinity (within a threshold). Alternatively, the tracts that intersect the geometric space occupied by a surgical tool that is virtually inserted in the brain may be displayed. Such tool may be a virtual representation of a biopsy needle, a port for minimally invasive surgery (e.g. an access port), a deep brain stimulation needle, or a catheter, to name a few. This approach 20 of selective display of 0TI information helps manage the large-data problem associated with visualization of an entire 0TI image. It also aids the surgeon in narrowing their focus and seeing principally the impacted tracts, as opposed to all tractography information associated with the entire brain”) therefore teaching a navigation system including a tracking system and a tracking device; wherein an instrument is operable to be navigated relative to the output the given neuronal tract within the navigation system as claimed.
Therefore it would have been obvious for a person of ordinary skill in the art before the effective filling date of the invention to have modified the apparatus of Zhang as modified by Butz-Ostendorf, Alexander and De Piccoli, such that the apparatus further comprises: a navigation system including a tracking system and a tracking device; wherein an instrument is operable to be navigated relative to the output the given neuronal tract within the navigation system, since one of ordinary skill in the art would recognize that using a system configured to combine a tractography imaging of the patient brain within a navigation system for positioning a medical tool relative to selected cerebral tracts was known in the art as taught by Thomas. One of ordinary skill in the art would have expected that this modification could have been made with predictable results since both Cetingul and Thomas both teach providing a tractography mapping with selected tracts of interest. The motivation would have been to provide visual support to the surgeon in narrowing their focus during the surgical procedure by providing visually the positioning of the medical tool relative to the tracts of interest to minimize the impact of the invasive surgery on the brain by preserving the functionality of the intact tracts, as suggested by Thomas (p.51 2nd ¶).
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (2019 MICCAI 2019 LNCS 11766:599-608; Pub.Date ePub 10/10/2019) in view of Butz-Ostendorf (USPN 20220230752 A1; Pub.Date 07/21/2022; Fil.Date 06/03/2019) with evidentiary reference Alexander et al. (2007 J Am Soc Exp NeuroTherapeutics 4:316-329; Pub.Date 2007) in view of De Piccoli (2018 PhD Thesis University of Verona Italy 133 pages; Pub.Date 2018) as applied to claim 15 and further in view of Cetingul et al. (US 2017/0052241 A1; Pub.Date 2017-02-23; Fil.Date 2016-07-28; IDS reference).
Zhang, Butz-Ostendorf, Alexander and De Piccoli teach a system as set forth above.
Zhang, Butz-Ostendorf, Alexander and De Piccoli do not specifically teach a memory system configured to store the instruction as in claim 16.
However, Cetingul teaches within the same field of endeavor of performing tractography specific to a subject (Title and abstract) the use of a memory for storing instruction to perform the tractography of the subject ([0007] “In a second aspect, a non-transitory computer readable storage medium has stored therein data representing instructions executable by a programmed processor for tractography with magnetic resonance imaging. The storage medium includes instructions for identifying brain regions of interest, tracts, and tract path spatial restrictions from atlases registered to a patient, determining a white matter mask for the patient, inputting diffusion weighted imaging data from a magnetic resonance imager, solving for fiber orientation distributions from the diffusion weighted imaging data, the brain regions of interest, the tracts, and the tract path spatial restrictions, and outputting a tractogram that is a function of the fiber orientation distributions”).
Therefore it would have been obvious for a person of ordinary skill in the art before the effective filling date of the invention to have modified the system of Zhang as modified by Butz-Ostendorf, Alexander and De Piccoli such that the system further comprises: a memory system configured to store the instruction, since one of ordinary skill in the art would recognize that using a non-transitory computer readable storage medium for storing instructions for producing the subject specific tractography was commonly and routinely performed in the art as taught by Cetingul. One of ordinary skill in the art would have expected that this modification could have been made with predictable results since both Cetingul and Zhang teach providing a tractography mapping of a subject. The motivation would have been to provide a support for storing large algorithms necessary for the analysis of large amount of imaging data such as for the subject specific brain tractography.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PATRICK M MEHL whose telephone number is (571)272-0572. The examiner can normally be reached Monday-Friday 9AM-6PM.
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, KEITH M RAYMOND can be reached at (571) 270-1790. 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.
/PATRICK M MEHL/ Examiner, Art Unit 3798
/KEITH M RAYMOND/ Supervisory Patent Examiner, Art Unit 3798
Prosecution Insights