DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Objections
Claim 12 is objected to because of the following informalities:
Claim 12, lines 11-12 recites “the medical condition is Alzheimer disease.” This should read “the medical condition is Alzheimer’s disease.”
Claim 12, lines 6-7 recites “the medical condition is Hungtington disease.” This should read “the medical condition is Hungtington Huntington’s disease.”
Claim 12, lines 11-12 recites “the medical condition is Parkinson disease.” This should read “the medical condition is Parkinson’s disease.”
Appropriate correction is required.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-6, 8-9, and 11-12 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Chandio et al. (“Advancing white matter tractometry of the brain using diffusion MRI and machine learning” 2022), hereinafter “Chandio,” as evidenced by Garyfallidis et al. (“Recognition of white matter bundles using local and global streamline-based registration and clustering” 2018), hereinafter “Garyfallidis ’18,” and as evidenced by Garyfallidis et al. (“QuickBundles, a method for tractography simplification” 2012), hereinafter “Garyfallidis ’12.”
Regarding claim 1, Chandio discloses a computer-implemented method (algorithms run using computer code on a computer, P.133-141, P.166) for segmenting a human patient tractogram into one or more white matter streamline bundles (RecoBundles algorithm segments a human patient tractogram into one or more white matter streamline bundles, Chandio, P.30), comprising:
obtaining a tractogram of a human patient (obtain a tractogram of the human’s brain, P.25-27, P.30), the tractogram including tractogram streamlines (tractogram includes tractogram streamlines, P.27, P.30) and a white matter atlas (obtain a white matter model/atlas, P.26, P.30) including one or more bundles each including respective atlas streamlines (white matter model/atlas includes bundles each including respective atlas streamlines, Chandio, P.26, P.30); and
for at least one bundle of the atlas and its respective atlas streamlines, attributing, to the at least one bundle, respective tractogram streamlines (RecoBundles performs far and local pruning to attribute to the bundles respective streamlines that correspond to respective model/atlas streamlines of each of the bundles, P.30; attributing vertical and horizontal tractogram segment streamlines corresponding to a respective vertical and horizontal segment of the model/atlas streamlines of each of the bundles, Chandio, P.119-121), the respective tractogram streamlines including one or more first sets each of at least one tractogram streamline, where each first set corresponds to a respective set of at least one atlas streamline of the at least one bundle (RecoBundles performs far and local pruning to attribute to the bundles respective streamlines that correspond to respective model/atlas streamlines of each of the bundles, Chandio, P.30), and the respective tractogram streamlines further including one or more second sets each of at least one tractogram streamline, where each second set corresponds to a respective sectional portion of a respective set of at least one atlas streamline of the at least one bundle (attributing vertical and horizontal tractogram segment streamlines corresponding to a respective vertical and horizontal segment of the model/atlas streamlines of each of the bundles, Chandio, P.119-121).
Regarding claim 2, Chandio discloses wherein the attributing further comprises:
using a predetermined clustering algorithm to obtain a plurality of tractogram streamline clusters (RecoBundles takes as input the whole brain tractogram, Chandio, P.30; RecoBundles takes as input the whole brain tractogram and clusters the whole brain tractogram using the QuickBundles algorithm to obtain a plurality of streamline clusters, Garyfallidis ‘18, P.284, ¶7 – P.285, ¶5);
using the predetermined clustering algorithm to obtain a plurality of atlas streamline clusters (RecoBundles takes as input the whole brain model tractogram, Chandio, P.30; RecoBundles takes as input the whole brain model tractogram and clusters the whole brain model tractogram using the QuickBundles algorithm to obtain a plurality of model streamline clusters, Garyfallidis ‘18, P.284, ¶7 – P.285, ¶5);
selecting the one or more first sets from the plurality of tractogram streamline clusters, a respective tractogram streamline cluster being selected as a first set when the respective tractogram streamline cluster fulfills a proximity criterion with the plurality of atlas streamline clusters (RecoBundles selects tractogram streamline clusters if they fulfill a minimum average direct-flip distance (MDF) threshold with the model streamline clusters, Chandio, P.30, Garyfallidis ‘18, P.285, ¶5-6); and
selecting the one or more second sets from the plurality of tractogram streamline clusters, a respective tractogram streamline cluster being selected as a second set when the respective tractogram streamline cluster fulfills the proximity criterion with a respective plurality of sectional portions of the atlas streamline clusters (selecting vertical and horizontal tractogram segment streamlines corresponding to a respective vertical and horizontal segment of the model/atlas cluster streamlines of each of the bundles, Chandio, P.119-121).
Regarding claim 3, Chandio discloses wherein:
selecting the one or more first sets further comprises:
computing a tractogram centroid for each respective tractogram streamline cluster using a predetermined centroid computation algorithm (RecoBundles selects tractogram streamline clusters if they fulfill a minimum average direct-flip distance (MDF) threshold with the model streamline clusters, Chandio, P.30; RecoBundles selects tractogram streamline clusters if the centroid of the tractogram streamline cluster fulfill a minimum average direct-flip distance (MDF) threshold with the centroid of the model streamline cluster, Garyfallidis ‘18, P.285, ¶3-8; RecoBundles computes the centroids of the tractogram streamline clusters, Garyfallidis ’18. P.285, ¶2-4);
computing a first atlas centroid for each respective atlas streamline cluster using the predetermined centroid computation algorithm (RecoBundles selects tractogram streamline clusters if they fulfill a minimum average direct-flip distance (MDF) threshold with the model streamline clusters, Chandio, P.30; RecoBundles selects tractogram streamline clusters if the centroid of the tractogram streamline cluster fulfill a minimum average direct-flip distance (MDF) threshold with the centroid of the model streamline clusters, Garyfallidis ‘18, P.285, ¶3-8; RecoBundles computes the centroid of the model streamline clusters, Garyfallidis ’18, P.285, ¶2-4)
identifying each tractogram streamline cluster for which a value of a predetermined distance between its tractogram centroid and each first atlas centroid is not above a predetermined threshold (RecoBundles selects tractogram streamline clusters if they fulfill a minimum average direct-flip distance (MDF) threshold with the model streamline clusters, Chandio, P.30; RecoBundles selects tractogram streamline clusters if the centroid of the tractogram streamline cluster fulfill a minimum average direct-flip distance (MDF) threshold with the centroid of the model streamline cluster, Garyfallidis ‘18, P.285, ¶3-8); and
selecting the one or more second sets further comprises, for each remaining tractogram streamline cluster:
determining a plurality of second atlas centroids each for a respective sectional portion of the respective plurality of sectional portions of the atlas streamline clusters (model bundles are subclustered and the centroids thereof are determined, Chandio, P.119-121);
identifying each tractogram streamline cluster for which the value of the predetermined distance between its tractogram centroid and each second atlas centroid is not above a predetermined threshold (selecting vertical and horizontal tractogram segment cluster streamlines corresponding to a respective vertical and horizontal segment of the model/atlas cluster streamlines of each of the bundles where the selection is made using a calculation of the closest centroid point between the centroids of the tractogram segment cluster streamlines and model/atlas cluster streamlines using the minimum direct-flip distance (MDF), Chandio, P.119-121).
Regarding claim 4, Chandio discloses wherein determining the plurality of second atlas centroids further comprises:
determining the value of a length of the tractogram centroid (length of the tractogram bundle/cluster, Chandio, P.119-121); and
for each first atlas centroid having a value of the length higher than the tractogram centroid, extracting one or more sectional portions of the first atlas centroid having a same value of the length as the tractogram centroid (vertical and horizontal tractogram segments are created as segments of the first model centroid, centroids of subsegments/subclusters of the model bundles, Chandio, P.119-121).
Regarding claim 5, Chandio discloses wherein extracting the one or more sectional portions of the first atlas centroid further comprises cutting iteratively the first atlas centroid using a predetermined offset (vertical and horizontal tractogram segments are created as segments of the first model centroid, centroids of subsegments/subclusters of the model bundles, wherein the segments are iteratively offset from one another, Chandio, P.119-121, Fig. 6.3)
Regarding claim 6, Chandio discloses wherein the predetermined clustering algorithm (RecoBundles takes as input the whole brain tractogram and whole brain model tractogram, Chandio, P.30; RecoBundles takes as input the whole brain tractogram and whole brain model tractogram, and clusters the whole brain tractogram and whole brain model tractogram using the QuickBundles algorithm to obtain a plurality of streamline clusters for the whole brain tractogram and whole brain model tractogram, Garyfallidis ‘18, P.284, ¶7 – P.285, ¶5; QuickBundles algorithm, Garyfallidis ’12, P.4, ¶2 – P.5, ¶3) includes for a respective plurality of streamlines:
assigning an initial streamline to an initial streamline cluster (QuickBundles algorithm assigns a first streamline to a first streamline cluster, Garyfallidis ’12, P.5, ¶1);
iteratively visiting subsequent streamlines of the respective plurality of streamlines (QuickBundles algorithm visits each remaining streamline of the respective plurality of streamlines in turn, Garyfallidis ’12, P.5, ¶1); and
for each respective subsequent streamline (QuickBundles algorithm visits each remaining streamline of the respective plurality of streamlines in turn, Garyfallidis ’12, P.5, ¶1) and with respect to a predetermined distance (minimum average direct flip distance (MDF), Garyfallidis ’12, P.3, ¶4, Garyfallidis ’12, P.5, ¶1):
computing a respective distance value between the subsequent streamline and a centroid of each already-existing streamline cluster (QuickBundles algorithm computes the minimum average direct flip distance (MDF) between the remaining streamline and a centroid of each centroid streamline of all the current clusters, Garyfallidis ’12, P.5, ¶1); and
determining a respective streamline cluster having a smallest distance value (determine a current streamline cluster having a smallest MDF value, Garyfallidis ’12, P.5, ¶1):
if the respective distance value is below a predetermined threshold, assigning the respective subsequent streamline to the respective streamline cluster (if the MDF value is below a clustering threshold, add the remaining streamline to the respective current streamline cluster, Garyfallidis ’12, P.5, ¶1),
else, creating a subsequent streamline cluster and assigning the respective subsequent streamline to said subsequent streamline cluster (otherwise create a new cluster, Garyfallidis ’12, P.5, ¶1).
Regarding claim 8, Chandio discloses wherein the predetermined distance is a minimum direct-flip distance (RecoBundles computes the minimum direct flip distance (MDF), Chandio, P.30; see also Chandio, P.32, 47, 91, 120, 167).
Regarding claim 9, Chandio discloses
wherein the attributing further comprises:
using a predetermined clustering algorithm to obtain a plurality of tractogram streamline clusters (RecoBundles takes as input the whole brain tractogram and whole brain model tractogram, Chandio, P.30; RecoBundles takes as input the whole brain tractogram and whole brain model tractogram, and clusters the whole brain tractogram and whole brain model tractogram using the QuickBundles algorithm to obtain a plurality of streamline clusters for the whole brain tractogram and whole brain model tractogram, Garyfallidis ‘18, P.284, ¶7 – P.285, ¶5; QuickBundles algorithm, Garyfallidis ’12, P.4, ¶2 – P.5, ¶3; RecoBundles performs far and local pruning after finding the corresponding streamlines of the whole brain tractogram using the whole brain model tractogram, Chandio, P.30; RecoBundles performs far and local pruning after clustering using the QuickBundles algorithm, Garyfallidis ’18, P.285, ¶2-5); RecoBundles uses the QuickBundles algorithm to recompute the streamline clusters after the initial finding of the corresponding streamlines, Garyfallidis ’18, P.285, ¶4-5);
using the predetermined clustering algorithm to obtain a plurality of atlas streamline clusters (RecoBundles takes as input the whole brain tractogram and whole brain model tractogram, Chandio, P.30; RecoBundles takes as input the whole brain tractogram and whole brain model tractogram, and clusters the whole brain tractogram and whole brain model tractogram using the QuickBundles algorithm to obtain a plurality of streamline clusters for the whole brain tractogram and whole brain model tractogram, Garyfallidis ‘18, P.284, ¶7 – P.285, ¶5; QuickBundles algorithm, Garyfallidis ’12, P.4, ¶2 – P.5, ¶3; RecoBundles performs far and local pruning after finding the corresponding streamlines of the whole brain tractogram using the whole brain model tractogram, Chandio, P.30; RecoBundles performs far and local pruning after clustering using the QuickBundles algorithm, Garyfallidis ’18, P.285, ¶2-5); RecoBundles uses the QuickBundles algorithm to recompute the model streamline clusters after the initial finding of the corresponding streamlines, Garyfallidis ’18, P.285, ¶4-5);
selecting the one or more first sets from the plurality of tractogram streamline clusters, a respective tractogram streamline cluster being selected as a first set when the respective tractogram streamline cluster fulfills a proximity criterion with the plurality of atlas streamline clusters (RecoBundles performs far pruning by computing the minimum average direct flip distance (MDF) between the streamline and the centroid of each streamline cluster, wherein streamlines are removed/excluded from the respective streamline cluster if the MDF value is above a threshold, Chandio, P.30, Garfallidis ’18, P.285, ¶5-6); and
selecting the one or more second sets from the plurality of tractogram streamline clusters, a respective tractogram streamline cluster being selected as a second set when the respective tractogram streamline cluster fulfills the proximity criterion with a respective plurality of sectional portions of the atlas streamline clusters (selecting vertical and horizontal tractogram segment streamlines corresponding to a respective vertical and horizontal segment of the model/atlas cluster streamlines of each of the bundles, Chandio, P.119-121);
wherein the predetermined clustering algorithm takes as input a threshold value (RecoBundles takes as input a distance threshold for the QuickBundles algorithm, Chandio, P.30, Garyfallidis ’18, P.285, ¶2-6, Garyfallidis ’12, P.5, ¶1-7; RecoBundles takes as input a distance threshold for far pruning and near pruning, Chandio, P.30, Garyfallidis ’18, P.285, ¶2-6), and prior to the using of the predetermined clustering algorithm and the selecting of the one or more first sets and the one or more second sets (RecoBundles performs far and local pruning after finding the corresponding streamlines of the whole brain tractogram using the whole brain model tractogram, Chandio, P.30; RecoBundles performs far and local pruning after clustering using the QuickBundles algorithm, Garyfallidis ’18, P.285, ¶2-5; ), the method further comprises:
retrieving all the tractogram streamlines from the tractogram (RecoBundles takes as input the whole brain tractogram, Chandio, P.30, Garyfallidis ‘18, P.284, ¶7 – P.285, ¶5) and all atlas streamlines from the white matter atlas (RecoBundles takes as input the whole brain model tractogram, Chandio, P.30, Garyfallidis ‘18, P.284, ¶7 – P.285, ¶5);
applying the predetermined clustering algorithm to said all the tractogram streamlines to obtain an initial plurality of tractogram streamline clusters (RecoBundles takes as input the whole brain tractogram, Chandio, P.30; RecoBundles takes as input the whole brain tractogram and clusters the whole brain tractogram using the QuickBundles algorithm to obtain a plurality of streamline clusters, Garyfallidis ‘18, P.284, ¶7 – P.285, ¶5);
applying the predetermined clustering algorithm to said all the atlas streamlines (RecoBundles takes as input the whole brain model tractogram, Chandio, P.30; RecoBundles takes as input the whole brain model tractogram and clusters the whole brain model tractogram using the QuickBundles algorithm to obtain a plurality of model streamline clusters, Garyfallidis ‘18, P.284, ¶7 – P.285, ¶5); and
selecting one or more initial sets of tractogram streamlines from the plurality of initial tractogram streamline clusters, a respective initial tractogram streamline cluster being selected as an initial set when the respective initial tractogram streamline cluster fulfills a coarser proximity criterion with a plurality of initial atlas streamline clusters (RecoBundles selects tractogram streamline clusters if they fulfill a minimum average direct-flip distance (MDF) threshold with the model streamline clusters with a coarser distance, Chandio, P.30, Garyfallidis ‘18, P.285, ¶5-6),
wherein the using of the predetermined clustering algorithm to obtain the plurality of tractogram streamline clusters is applied to the streamlines of at least part of the one or more initial sets of tractogram streamlines (RecoBundles performs far and local pruning after finding the corresponding streamlines of the whole brain tractogram using the whole brain model tractogram, Chandio, P.30; RecoBundles performs far and local pruning after clustering using the QuickBundles algorithm, Garyfallidis ’18, P.285, ¶2-5).
Regarding claim 11, Chandio discloses wherein obtaining the tractogram further comprises:
obtaining a diffusion magnetic resonance image (MRI) of the brain (diffusion-weighted magnetic resonance imaging, Chandio, P.3);
determining a diffusion voxel model from the diffusion MRI (voxels modeling of the Diffusion-weighted magnetic resonance imaging images, Chandio, P.3-11); and
constructing the tractogram from the diffusion voxel model (tractogram streamlines are constructed from the diffusion voxel model, Chandio, P.3-11).
Regarding claim 12, Chandio discloses wherein a result of the attributing is applied to diagnosing and/or treating a patient with respect to a medical condition (diagnosing/treating Alzheimer’s, Multiple Sclerosis, Parkinson’s, and/or neurosurgical planning, Chandio, P.vii-viii, P.xx, P.2, P.3, P.18, P.20, P.48-49, P.50, P.54, P.60, P.59, P.73, P.84, P.98, P.103, P.105-107, P.112, P.115, P.116, P.119, P.130, P.132, P.144, P.148, Fig. 10.1), wherein the at least one bundle comprises:
a bundle corresponding to the cingulum fasciculus (cingulum bundle, Chandio, P.xvii, P.66, P.84-85, Fig. 3.4), and/or the medical condition is a condition impacting functioning of memory, such as Alzheimer disease (medical condition such as Alzheimer’s, Chandio, P.vii-viii, P.2, P.20, P.98, P.103, P.105-107, P.112, P.116, P.132, P.144, P.148),
a bundle corresponding to the corpus callosum (corpus callosum bundle, Chandio, P.50, P.94, P.99, P.145),
a bundle corresponding to optical radiations (optic radiation bundle, Chandio, P.2, P.23, P.99, P.108), and/or the medical condition is a condition impacting optical nerve fibers and/or incurring an optic neuritis, such as multiple sclerosis (medical condition such as Multiple Sclerosis, Chandio, P.2),
a bundle corresponding to corticospinal tracts (corticospinal tract bundle, Chandio, P.xx, P.18, P.48-49, P.50, P.60, P.69, P.73, P.84, P.115, P.116, P.119, P.130, Fig. 10.1) and/or the medical condition is Parkinson disease (medical condition such as Parkinson’s, Chandio, P.vii-viii, P.2, P.19, P.22, P.25, P.38, P.49, P.57, P.103, P.141, P.142-142, P.148), and/or
one or more bundles usable for neurosurgical planning (bundles used for neurosurgical planning, Chandio, P.3, P.54).
Claims 13-17 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Chandio as evidenced by Garyfallidis ’18, and as evidenced by Garyfallidis ’12.
Regarding claim 13, Chandio discloses a non-transitory computer readable storage medium having recorded thereon a computer program comprising instructions for performing a computer-implemented method (algorithms run using computer code stored and executed on a computer, P.133-141, P.166) for segmenting a human patient tractogram into one or more white matter streamline bundles (RecoBundles algorithm segments a human patient tractogram into one or more white matter streamline bundles, Chandio, P.30), the method comprising:
obtaining a tractogram of a human patient (obtain a tractogram of the human’s brain, P.25-27, P.30), the tractogram including tractogram streamlines (tractogram includes tractogram streamlines, P.27, P.30) and a white matter atlas (obtain a white matter model/atlas, P.26, P.30) including one or more bundles each including respective atlas streamlines (white matter model/atlas includes bundles each including respective atlas streamlines, Chandio, P.26, P.30); and
for at least one bundle of the atlas and its respective atlas streamlines, attributing, to the at least one bundle, respective tractogram streamlines (RecoBundles performs far and local pruning to attribute to the bundles respective streamlines that correspond to respective model/atlas streamlines of each of the bundles, P.30; attributing vertical and horizontal tractogram segment streamlines corresponding to a respective vertical and horizontal segment of the model/atlas streamlines of each of the bundles, Chandio, P.119-121), the respective tractogram streamlines including one or more first sets each of at least one tractogram streamline, where each first set corresponds to a respective set of at least one atlas streamline of the at least one bundle (RecoBundles performs far and local pruning to attribute to the bundles respective streamlines that correspond to respective model/atlas streamlines of each of the bundles, Chandio, P.30), and the respective tractogram streamlines further including one or more second sets each of at least one tractogram streamline, where each second set corresponds to a respective sectional portion of a respective set of at least one atlas streamline of the at least one bundle (attributing vertical and horizontal tractogram segment streamlines corresponding to a respective vertical and horizontal segment of the model/atlas streamlines of each of the bundles, Chandio, P.119-121).
Regarding claim 14, Chandio discloses wherein the attributing further comprises:
using a predetermined clustering algorithm to obtain a plurality of tractogram streamline clusters (RecoBundles takes as input the whole brain tractogram, Chandio, P.30; RecoBundles takes as input the whole brain tractogram and clusters the whole brain tractogram using the QuickBundles algorithm to obtain a plurality of streamline clusters, Garyfallidis ‘18, P.284, ¶7 – P.285, ¶5);
using the predetermined clustering algorithm to obtain a plurality of atlas streamline clusters (RecoBundles takes as input the whole brain model tractogram, Chandio, P.30; RecoBundles takes as input the whole brain model tractogram and clusters the whole brain model tractogram using the QuickBundles algorithm to obtain a plurality of model streamline clusters, Garyfallidis ‘18, P.284, ¶7 – P.285, ¶5);
selecting the one or more first sets from the plurality of tractogram streamline clusters, a respective tractogram streamline cluster being selected as a first set when the respective tractogram streamline cluster fulfills a proximity criterion with the plurality of atlas streamline clusters (RecoBundles selects tractogram streamline clusters if they fulfill a minimum average direct-flip distance (MDF) threshold with the model streamline clusters, Chandio, P.30, Garyfallidis ‘18, P.285, ¶5-6); and
selecting the one or more second sets from the plurality of tractogram streamline clusters, a respective tractogram streamline cluster being selected as a second set when the respective tractogram streamline cluster fulfills the proximity criterion with a respective plurality of sectional portions of the atlas streamline clusters (selecting vertical and horizontal tractogram segment streamlines corresponding to a respective vertical and horizontal segment of the model/atlas cluster streamlines of each of the bundles, Chandio, P.119-121).
Regarding claim 15, Chandio discloses selecting the one or more first sets further comprises:
computing a tractogram centroid for each respective tractogram streamline cluster using a predetermined centroid computation algorithm (RecoBundles selects tractogram streamline clusters if they fulfill a minimum average direct-flip distance (MDF) threshold with the model streamline clusters, Chandio, P.30; RecoBundles selects tractogram streamline clusters if the centroid of the tractogram streamline cluster fulfill a minimum average direct-flip distance (MDF) threshold with the centroid of the model streamline cluster, Garyfallidis ‘18, P.285, ¶3-8; RecoBundles computes the centroids of the tractogram streamline clusters, Garyfallidis ’18. P.285, ¶2-4);
computing a first atlas centroid for each respective atlas streamline cluster using the predetermined centroid computation algorithm (RecoBundles selects tractogram streamline clusters if they fulfill a minimum average direct-flip distance (MDF) threshold with the model streamline clusters, Chandio, P.30; RecoBundles selects tractogram streamline clusters if the centroid of the tractogram streamline cluster fulfill a minimum average direct-flip distance (MDF) threshold with the centroid of the model streamline clusters, Garyfallidis ‘18, P.285, ¶3-8; RecoBundles computes the centroid of the model streamline clusters, Garyfallidis ’18, P.285, ¶2-4)
identifying each tractogram streamline cluster for which a value of a predetermined distance between its tractogram centroid and each first atlas centroid is not above a predetermined threshold (RecoBundles selects tractogram streamline clusters if they fulfill a minimum average direct-flip distance (MDF) threshold with the model streamline clusters, Chandio, P.30; RecoBundles selects tractogram streamline clusters if the centroid of the tractogram streamline cluster fulfill a minimum average direct-flip distance (MDF) threshold with the centroid of the model streamline cluster, Garyfallidis ‘18, P.285, ¶3-8); and
selecting the one or more second sets further comprises, for each remaining tractogram streamline cluster:
determining a plurality of second atlas centroids each for a respective sectional portion of the respective plurality of sectional portions of the atlas streamline clusters (model bundles are subclustered and the centroids thereof are determined, Chandio, P.119-121);
identifying each tractogram streamline cluster for which the value of the predetermined distance between its tractogram centroid and each second atlas centroid is not above a predetermined threshold (selecting vertical and horizontal tractogram segment cluster streamlines corresponding to a respective vertical and horizontal segment of the model/atlas cluster streamlines of each of the bundles where the selection is made using a calculation of the closest centroid point between the centroids of the tractogram segment cluster streamlines and model/atlas cluster streamlines using the minimum direct-flip distance (MDF), Chandio, P.119-121).
Regarding claim 16, Chandio discloses wherein determining the plurality of second atlas centroids further comprises:
determining the value of a length of the tractogram centroid (length of the tractogram bundle/cluster, Chandio, P.119-121); and
for each first atlas centroid having a value of the length higher than the tractogram centroid, extracting one or more sectional portions of the first atlas centroid having a same value of the length as the tractogram centroid (vertical and horizontal tractogram segments are created as segments of the first model centroid, centroids of subsegments/subclusters of the model bundles, Chandio, P.119-121).
Regarding claim 17, Chandio discloses wherein extracting the one or more sectional portions of the first atlas centroid further comprises cutting iteratively the first atlas centroid using a predetermined offset (vertical and horizontal tractogram segments are created as segments of the first model centroid, centroids of subsegments/subclusters of the model bundles, wherein the segments are iteratively offset from one another, Chandio, P.119-121, Fig. 6.3)
Claims 18-20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Chandio as evidenced by Garyfallidis ’18, and as evidenced by Garyfallidis ’12.
Regarding claim 18, Chandio discloses a system (a computer, P.133-141, P.166) comprising:
a processor coupled to a memory, the memory having recorded thereon instructions that, when executed by the processor, cause the processor to perform (a computer executing algorithms stored as computer code on the computer, P.133-141, P.166) segmenting of a human patient tractogram into one or more white matter streamline bundles (RecoBundles algorithm segments a human patient tractogram into one or more white matter streamline bundles, Chandio, P.30) by being configured to:
obtain a tractogram of a human patient (obtain a tractogram of the human’s brain, P.25-27, P.30), the tractogram including tractogram streamlines (tractogram includes tractogram streamlines, P.27, P.30) and a white matter atlas (obtain a white matter model/atlas, P.26, P.30) including one or more bundles each including respective atlas streamlines (white matter model/atlas includes bundles each including respective atlas streamlines, Chandio, P.26, P.30); and
for at least one bundle of the atlas and its respective atlas streamlines, attributing, to the at least one bundle, respective tractogram streamlines (RecoBundles performs far and local pruning to attribute to the bundles respective streamlines that correspond to respective model/atlas streamlines of each of the bundles, P.30; attributing vertical and horizontal tractogram segment streamlines corresponding to a respective vertical and horizontal segment of the model/atlas streamlines of each of the bundles, Chandio, P.119-121), the respective tractogram streamlines including one or more first sets each of at least one tractogram streamline, where each first set corresponds to a respective set of at least one atlas streamline of the at least one bundle (RecoBundles performs far and local pruning to attribute to the bundles respective streamlines that correspond to respective model/atlas streamlines of each of the bundles, Chandio, P.30), and the respective tractogram streamlines further including one or more second sets each of at least one tractogram streamline, where each second set corresponds to a respective sectional portion of a respective set of at least one atlas streamline of the at least one bundle (attributing vertical and horizontal tractogram segment streamlines corresponding to a respective vertical and horizontal segment of the model/atlas streamlines of each of the bundles, Chandio, P.119-121).
Regarding claim 19, Chandio discloses the processor is further configured to attribute by being further configured to:
use a predetermined clustering algorithm to obtain a plurality of tractogram streamline clusters (RecoBundles takes as input the whole brain tractogram, Chandio, P.30; RecoBundles takes as input the whole brain tractogram and clusters the whole brain tractogram using the QuickBundles algorithm to obtain a plurality of streamline clusters, Garyfallidis ‘18, P.284, ¶7 – P.285, ¶5);
use the predetermined clustering algorithm to obtain a plurality of atlas streamline clusters (RecoBundles takes as input the whole brain model tractogram, Chandio, P.30; RecoBundles takes as input the whole brain model tractogram and clusters the whole brain model tractogram using the QuickBundles algorithm to obtain a plurality of model streamline clusters, Garyfallidis ‘18, P.284, ¶7 – P.285, ¶5);
select the one or more first sets from the plurality of tractogram streamline clusters, a respective tractogram streamline cluster being selected as a first set when the respective tractogram streamline cluster fulfills a proximity criterion with the plurality of atlas streamline clusters (RecoBundles selects tractogram streamline clusters if they fulfill a minimum average direct-flip distance (MDF) threshold with the model streamline clusters, Chandio, P.30, Garyfallidis ‘18, P.285, ¶5-6); and
select the one or more second sets from the plurality of tractogram streamline clusters, a respective tractogram streamline cluster being selected as a second set when the respective tractogram streamline cluster fulfills the proximity criterion with a respective plurality of sectional portions of the atlas streamline clusters (selecting vertical and horizontal tractogram segment streamlines corresponding to a respective vertical and horizontal segment of the model/atlas cluster streamlines of each of the bundles, Chandio, P.119-121).
Regarding claim 20, Chandio discloses the processor is further configured to select the one or more first sets by being further configured to:
compute a tractogram centroid for each respective tractogram streamline cluster using a predetermined centroid computation algorithm (RecoBundles selects tractogram streamline clusters if they fulfill a minimum average direct-flip distance (MDF) threshold with the model streamline clusters, Chandio, P.30; RecoBundles selects tractogram streamline clusters if the centroid of the tractogram streamline cluster fulfill a minimum average direct-flip distance (MDF) threshold with the centroid of the model streamline cluster, Garyfallidis ‘18, P.285, ¶3-8; RecoBundles computes the centroids of the tractogram streamline clusters, Garyfallidis ’18. P.285, ¶2-4);
compute a first atlas centroid for each respective atlas streamline cluster using the predetermined centroid computation algorithm (RecoBundles selects tractogram streamline clusters if they fulfill a minimum average direct-flip distance (MDF) threshold with the model streamline clusters, Chandio, P.30; RecoBundles selects tractogram streamline clusters if the centroid of the tractogram streamline cluster fulfill a minimum average direct-flip distance (MDF) threshold with the centroid of the model streamline clusters, Garyfallidis ‘18, P.285, ¶3-8; RecoBundles computes the centroid of the model streamline clusters, Garyfallidis ’18, P.285, ¶2-4)
identify each tractogram streamline cluster for which a value of a predetermined distance between its tractogram centroid and each first atlas centroid is not above a predetermined threshold (RecoBundles selects tractogram streamline clusters if they fulfill a minimum average direct-flip distance (MDF) threshold with the model streamline clusters, Chandio, P.30; RecoBundles selects tractogram streamline clusters if the centroid of the tractogram streamline cluster fulfill a minimum average direct-flip distance (MDF) threshold with the centroid of the model streamline cluster, Garyfallidis ‘18, P.285, ¶3-8); and
wherein the processor is further configured to select the one or more second sets further comprises, for each remaining tractogram streamline cluster:
determine a plurality of second atlas centroids each for a respective sectional portion of the respective plurality of sectional portions of the atlas streamline clusters (model bundles are subclustered and the centroids thereof are determined, Chandio, P.119-121);
identify each tractogram streamline cluster for which the value of the predetermined distance between its tractogram centroid and each second atlas centroid is not above a predetermined threshold (selecting vertical and horizontal tractogram segment cluster streamlines corresponding to a respective vertical and horizontal segment of the model/atlas cluster streamlines of each of the bundles where the selection is made using a calculation of the closest centroid point between the centroids of the tractogram segment cluster streamlines and model/atlas cluster streamlines using the minimum direct-flip distance (MDF), Chandio, P.119-121).
Allowable Subject Matter
Claims 7 and 10 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter:
Regarding claim 7, Chandio discloses the predetermined clustering algorithm (RecoBundles takes as input the whole brain tractogram and whole brain model tractogram, Chandio, P.30; RecoBundles takes as input the whole brain tractogram and whole brain model tractogram, and clusters the whole brain tractogram and whole brain model tractogram using the QuickBundles algorithm to obtain a plurality of streamline clusters for the whole brain tractogram and whole brain model tractogram, Garyfallidis ‘18, P.284, ¶7 – P.285, ¶5; QuickBundles algorithm, Garyfallidis ’12, P.4, ¶2 – P.5, ¶3) further comprises, after assigning all streamlines of the plurality of streamlines (RecoBundles performs far and local pruning after finding the corresponding streamlines of the whole brain tractogram using the whole brain model tractogram, Chandio, P.30; RecoBundles performs far and local pruning after clustering using the QuickBundles algorithm, Garyfallidis ’18, P.285, ¶2-5):
re-computing the centroid of each streamline cluster using a predetermined centroid computation algorithm (RecoBundles uses the QuickBundles/SLR algorithm to recompute the centroid of each streamline cluster, Garyfallidis ’18, P.285, ¶4-5);
for each streamline assigned to a respective streamline cluster (RecoBundles performs far pruning for each streamline assigned to a respective streamline cluster, Chandio, P.30, Garyfallidis ’18, P.285, ¶4-6), and with respect to the predetermined distance (RecoBundles performs far pruning using the minimum average direct flip distance, Chandio, P.30, Garyfallidis ’18, P.285, ¶4-6):
computing a respective distance value between the streamline and the centroid of the respective streamline cluster (RecoBundles performs far pruning by computing the minimum average direct flip distance (MDF) between the streamline and the centroid of each streamline cluster, Chandio, P.30, Garyfallidis ’18, P.285, ¶5-6); and
un-assigning the streamline from the respective streamline cluster if the respective distance value is above the predetermined threshold (RecoBundles performs far pruning by excluding/removing streamlines from the respective streamline cluster if the MDF value is above a threshold, Chandio, P.30, Garfallidis ’18, P.285, ¶5-6);
re-computing again the centroid of each streamline cluster using the predetermined centroid computation algorithm (RecoBundles uses the QuickBundles/SLR algorithm to recompute the centroid of each streamline cluster after far pruning and before local pruning, Garyfallidis ’18, P.285, ¶5).
However, Chandio does not appear to disclose the combination of:
for each streamline un-assigned to another respective streamline cluster, and with respect to the predetermined distance:
computing a respective distance value between the streamline and the centroid of each streamline cluster; and
determining a streamline cluster having a smallest distance value:
if the respective distance value is below the predetermined threshold, re-assigning an unassigned streamline to the determined streamline cluster,
else creating a subsequent streamline cluster and re-assigning the subsequent streamline to a subsequent streamline cluster.
Regarding claim 10, Chandio discloses to obtain the at least part of the one or more initial sets:
computing a binary mask from the white matter atlas, the binary mask comprising binary-valued voxels, wherein a binary-valued voxel has a value of one when said voxel intersects a part of one atlas streamlines from the retrieved all white matter atlas streamlines and a value of zero otherwise (a seed mask wherein only white matter regions are used as seeding voxels for tracking the streamlines, i.e., white matter regions are labeled as 1 and all other regions are labeled as 0, Chandio, P.11, P.107, P.117).
However, Chandio does not appear to disclose applying the binary mask to exclude each initial set of tractogram streamlines having a centroid comprising at least one point in a voxel having a value of zero.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Chandio et al. (“Bundle analytics, a computational framework for investigating the shapes and profiles of brain pathways across populations” 2020) discloses using the RecoBundles and QuickBundles algorithms as part of the BUNA algorithm to segment whole brain tractograms.
Garyfallidis et al. (“Robust and efficient linear registration of white-matter fascicles in the space of streamlines” 2015) discloses using the QuickBundles algorithm to segment whole brain tractograms.
Garyfallidis et al. (“QuickBundlesX: Sequential clustering of millions of streamlines in multiple levels of detail at record execution time” 2016) discloses using the QuickBundles algorithm with different levels of coarseness to segment whole brain tractograms.
Wanyan et al. (“Important new insights for the reduction of false positives in tractograms emerge from streamline-based registration and pruning” 2017) discloses using the QuickBundles algorithm and pruning to segment whole brain tractograms.
Guevara et al. (“Automatic fiber bundle segmentation in massive tractography datasets using multi-subject bundle atlas” 2012) discloses using the “Guevara” algorithm to segment whole brain tractograms including addition of discarded streamlines using a distance threshold.
Labra et al. (“Fast automatic segmentation of white matter streamlines based on a multi-subject bundle atlas” 2017”) discloses using a variant of the QuickBundles algorithm and pruning to segment whole brain tractograms.
Vazquez et al. (“Automatic group-wise whole-brain short association fiber bundle labeling based on clustering and cortical surface information” 2020) discloses using a variant of the QuickBundles algorithm and pruning to segment whole brain tractograms.
Cao et al. (“A data-driven voxel-wise white matter fiber clustering model based on priori anatomical data” 2018) discloses using a combined parcellation and clustering method, wherein the parcellation method uses a mask of the white matter atlas to determine fractional anisotropy across the streamlines to differentiate between white matter and gray matter, wherein the clustering method uses the minimum direct-flip distance as a distance threshold to assign streamlines to clusters, and the combined parcellation and clustering method uses the intersection of the fractional anisotropy from the mask with the centroid to inform the clustering.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Johnathan Maynard whose telephone number is (571)272-7977. The examiner can normally be reached 10 AM - 6 PM.
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 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.
/J.M./Examiner, Art Unit 3798
/KEITH M RAYMOND/Supervisory Patent Examiner, Art Unit 3798