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 .
Information Disclosure Statement
The information disclosure statement (IDS) was filed on 12/16/2024. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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.
Claims 1-5, 7-12, 14-18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Chirol et. al. (Chirol, Clementine, et al. "Pore, live root and necromass quantification in complex heterogeneous wetland soils using X-ray computed tomography." Geoderma 387 (2021): 114898. (Year: 2021)) in view of Madabhushi et. al. (US Pub. No. 20190279359 A1) .
As per claim 1, Chirol teaches “A method for root system analysis of a three-dimensional (3D) volume of a soil core sample, comprising: normalizing image slices of an x-ray computed tomography (XCT) scan of the soil core sample; segmenting image slices of the XCT scan by clustering image features… using the segmented image slices; and… segmenting the 3D volume of the soil core sample using the… model” (See page 2 fig. 1 and abstract “Yet despite recent progress in the application of X-ray Computed Microtomography (µCT) to soil structure in agricultural science, applications to the more complex and hetero geneous substrates found in natural soils, specifically wetland soils, remain sparse. We apply X-ray µCT to a complex heterogenous soil and develop a robust segmentation method to quantify the pores, live roots and necromass. This approach significantly improves the detection of the organic matter elements, and gives us unprecedented detail and resolution in the segmentation of pores, live roots and necromass at a high spatial resolution (62.5 µm in this study).” See also pages 5-6 sections 2.2 and 2.3. Page 5 column 1 paragraph 1 shows “The volume reconstruction step was undertaken using Nikon’s in- house software CT-Pro 3D (Ray, 2011): the software finds the center of rotation of the raw X-ray projections and converts the 2D radial slices into a 3D volumetric model defined by co-registered z-slices…” See fig. 5 along with fig. 4 and fig. 3 and page 5 column 2 paragraph 3 shows normalizing image slices by masking and clustering image features “We first applied a method called hysteresis thresholding to distinguish the high-density inorganics from pores and organic matter. This method considers two thresholds: voxels below the low threshold have a high likelihood of being part of a pore or organic element and are systematically segmented, while voxels below the high threshold are only segmented if they are connected to the low threshold elements. … The output binary masks from hysteresis thresholding and Frangi tubular shape enhancement were combined, adopting a single threshold to separate pores from organic matter. ”. See also page 5 section 2.2. which shows normalization. See also page 6 section 2.4 to section 3.1 along with fig. 6. Page 6 column 2 paragraphs 1-3 shows “The 3D binary masks NFF5000, FF5000 and FF2500 were used for a detailed topological analysis of the pores and organic matter elements using the automated software plugin BoneJ for ImageJ (Doube et al., 2010; Schindelin et al., 2012)… In order to compare this 3D rendering with the actual sample, and check that the root and pore elements visible to the naked eye are correctly identified, the core was cut open with a serrated knife along a pre-marked section one day after scanning… Observation of the segmented horizontal slices provides insight into the different types of pores and organic matter elements detected by our segmentation method (Fig. 6)…” Examiner interprets “image features” as pores and organic elements. Page 7 section 4.Discussion also shows segmentation by image features “The approach outlined in this paper has multiple potential applications for soil science. The three-phase segmentation (pores, organic matter elements, sediment matrix) allows the study of pore-root in teractions…”. See also page8 fig. 7. Chirol), however Chirol does not teach “clustering image features using Gaussian Mixture Model (GMM); training a random forest (RF) model… in response to accuracy of the trained RF model satisfying a threshold condition… using the trained RF model”
Madabhushi teaches “clustering image features using Gaussian Mixture Model (GMM);” (See paragraphs 25 and 48 “[0025] Embodiments perform a clustering analysis of TILs identified in the image. Workflow 100 further includes, at 140, performing a clustering analysis based, at least in part, on the extracted set of morphological or contextual features. Gaussian mixture models are probabilistic models that assume all the data points are generated from a mixture of a finite number of Gaussian distributions with unknown parameters…” “[0048]… In one embodiment, the segmented nucleus classified as a lymphocyte is assigned to one of the plurality of clusters based on the set of contextual features using a Dirichlet Process Gaussian Mixture Model (DPGMM).” Madabhushi) “training a random forest (RF) model… in response to accuracy of the trained RF model satisfying a threshold condition… using the trained RF model” (See paragraphs 51-52 “[0051]… The machine learning classifier computes the classification based, at least in part, on the frequency distribution… In another embodiment, the machine learning classifier is another type of machine learning classifier or deep learning classifier. For example, in one embodiment, the machine learning classifier may be a quadratic discriminant analysis (QDA) classifier, a random forests classifier, or a support vector machine (SVM).” “[0053]… [0053] In one embodiment, the operations 600 further include training the machine learning classifier. In this embodiment, the machine learning classifier is trained and tested using a training set of images and a testing set of images. Training the machine learning classifier may include training the machine learning classifier until a threshold level of accuracy is achieved, until a threshold time has been spent training the machine learning classifier… Training the machine learning classifier may also include determining which features extracted from a segmented nucleus, which contextual features, or which number of clusters, is most discriminative in distinguishing a positive class from a negative class…” See also paragraphs 43, 48 and 61-67. Madabhushi)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Chirol with the teachings of Madabhushi to cluster image features utilizing a Gaussian Mixture Model and segmenting using a random forest model. The modification would have been motivated by the desire to have increased accuracy when predicting quantitative measures, in addition to being non-destructive and less complex, therefore it is an improvement, as suggested by Madabhushi (See paragraph 18 “[0018] Embodiments non-destructively identify TIL cluster families and their spatial architecture represented in routine H&E stained images, obviating the need for more expensive, complex, tissue-destructive techniques like QIF or IHC. Embodiments derive quantitative measurements from the identified TIL cluster families represented in the H&E stained images, and the spatial architecture of the TIL cluster families. Embodiments further predict recurrence in NSCLC based on the derived quantitative measurements with increased accuracy compared to existing approaches.” Madabhushi)
Claim 8 is rejected under the same analysis of claim 1.
Claim 15 is rejected under the same analysis of claim 1. (The processed workflow of instructions was computed through an application on a computer. It is well known in the art that computers utilize computer readable media for applications. See page 2 fig. 1 “Fig. 1. Data acquisition and processing workflow. The overall processing time from scanning to obtention of output parameters is about four days on a high performance computing suite.” See also pages 10-11 section 5. Conclusion “This study applied X-ray Computed Microtomography to a highly heterogenous saltmarsh sediment core. We developed a hybrid seg mentation method… ” Chirol)
As per claim 2 Chirol in view of Madabhushi teaches “the method of claim 1, wherein the image features comprise necromass, biomass, sediment, and pores.” (See Page 7 section 4.Discussion paragraph 2 “The approach outlined in this paper has multiple potential applications for soil science. The three-phase segmentation (pores, organic matter elements, sediment matrix) allows the study of pore-root interactions…”. See also page 8 fig. 7 “Fig. 7. Segmented volume visualization using different segmentation methods and noise thresholds. Grey = pores; green = organic matter; brown = inorganic matter.”. See also page 11 fig. 11 “Fig. 11. Effect of the Frangi filter on the extent, bulk volume, number of branches and root system depth of surface-connected “live” roots (green) and on the bulk volume of the necromass (dark red).”, see page 7 column 2 paragraph 2 “Fig. 11 shows the potential of the Frangi filter to detect the necro mass as well as the surface-connected live root system. The live root phase highlights one large Spartina root that branches out into smaller horizontal roots at about 80 mm depth.” . Examiner interprets the live roots as biomass. See also page 9 column 1 paragraph 2 “…Our approach can further the state of knowledge by providing a robust way of estimating root biomass.” Chirol)
Claim 9 is rejected under the same analysis of claim 2.
Claim 16 is rejected under the same analysis of claim 2.
As per claim 3, Chirol in view of Madabhushi teaches “The method of claim 2, wherein the image features further comprise live roots, dead roots, and a combination of both.” ( See page 11 fig. 11 “Fig. 11. Effect of the Frangi filter on the extent, bulk volume, number of branches and root system depth of surface-connected “live” roots (green) and on the bulk volume of the necromass (dark red).”, see page 7 column 2 paragraph 2 “Fig. 11 shows the potential of the Frangi filter to detect the necro mass as well as the surface-connected live root system. The live root phase highlights one large Spartina root that branches out into smaller horizontal roots at about 80 mm depth.” . Examiner interprets the live roots as biomass. See also page 9 column 1 paragraph 2 “…Our approach can further the state of knowledge by providing a robust way of estimating root biomass.” Necromass is interpreted as dead roots, see page 10 column 2 paragraph 1 “… this method is more versatile because it requires no prior knowledge of the core con tent, and because it distinguishes between the live root system and the necromass. Our analysis of the pore and organic matter elements’ volume and structure shows clear interactions between the two phases: root decay is a source of porosity in the sediment, while the presence of areas of lower density with a higher concentration of pores determine where roots are able to develop.” Chirol)
Claim 10 is rejected under the same analysis of claim 3.
Claim 17 is rejected under the same analysis of claim 3.
As per claim 4, Chirol in view of Madabhushi teaches “The method of claim 1, wherein the RF model is retrained if the accuracy of the trained RF model does not satisfy the threshold condition.” ((See paragraphs 51-52 “[0051]… The machine learning classifier computes the classification based, at least in part, on the frequency distribution… In another embodiment, the machine learning classifier is another type of machine learning classifier or deep learning classifier. For example, in one embodiment, the machine learning classifier may be a quadratic discriminant analysis (QDA) classifier, a random forests classifier, or a support vector machine (SVM).” “[0053]… [0053] In one embodiment, the operations 600 further include training the machine learning classifier. In this embodiment, the machine learning classifier is trained and tested using a training set of images and a testing set of images. Training the machine learning classifier may include training the machine learning classifier until a threshold level of accuracy is achieved, until a threshold time has been spent training the machine learning classifier… Training the machine learning classifier may also include determining which features extracted from a segmented nucleus, which contextual features, or which number of clusters, is most discriminative in distinguishing a positive class from a negative class…” See also paragraphs 43, 48 and 61-67. Madabhushi)
Claim 11 is rejected under the same analysis of claim 4
As per claim 5, Chirol in view of Madabhushi teaches “The method of claim 1, wherein normalizing the image slices comprises a linear correction based upon at least one reference material.” (See page 4 fig. 3 “Fig. 3. Removal of the autocompaction effect on grayscales using a downcore linear fit. The correction factor at each z-slice is given by subtracting the linear fit from the uncorrected mean grayscale then adding the mean grayscale of the whole core. The method does not remove the logarithmic trend at the top of the sample so as to not excessively distort the grayscale values of the pores and organic matter.” Examiner interprets “reference material” as the sample used as the reference. See also page 5 column 1 paragraph 2 “Compared to other soils where the material density is consistent throughout, another challenge of clay-dominated coastal sediment… In our sample, a linear trend in grayscale values is found with an R 2 value of 0.75 (Fig. 3); a lack of a similar trend in the PVC tube around the sample (not shown) confirms that this trend is due to auto compaction rather than an artefact of scanning. In order to more consistently distinguish the mineral phase from the porosity and organic matter, this downcore trend is removed using a linear interpolation (Fig. 3). In practice, this means smoothing out the microporosity through the sample, which decreases with depth and affects the gray scale value of inorganic voxels due to the partial volume effect.” See also page 5 section 2.2. Chirol)
Claim 12 is rejected under the same analysis of claim 5.
Claim 18 is rejected under the same analysis of claim 5.
As per claim 7, Chirol in view of Madabhushi teaches “The method of claim 5, wherein normalizing the image slices further comprises masking.” (See fig. 5 along with fig. 4 and page 5 column 2 paragraph 3 shows normalizing image slices by masking and clustering image features “We first applied a method called hysteresis thresholding to distinguish the high-density inorganics from pores and organic matter. This method considers two thresholds: voxels below the low threshold have a high likelihood of being part of a pore or organic element and are systematically segmented, while voxels below the high threshold are only segmented if they are connected to the low threshold elements. … The output binary masks from hysteresis thresholding and Frangi tubular shape enhancement were combined, adopting a single threshold to separate pores from organic matter. ”. See also page 6 section 2.4 to section 3.1 along with fig. 6. Page 6 column 2 paragraphs 1-3 shows “The 3D binary masks NFF5000, FF5000 and FF2500 were used for a detailed topological analysis of the pores and organic matter elements using the automated software plugin BoneJ for ImageJ (Doube et al., 2010; Schindelin et al., 2012)… In order to compare this 3D rendering with the actual sample, and check that the root and pore elements visible to the naked eye are correctly identified, the core was cut open with a serrated knife along a pre-marked section one day after scanning… Observation of the segmented horizontal slices provides insight into the different types of pores and organic matter elements detected by our segmentation method (Fig. 6)… See also page 5 section 2.2. Chirol)
Claim 14 is rejected under the same analysis of claim 7.
Claim 20 is rejected under the same analysis of claim 6.
Claims 6, 13 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Chirol in view of Madabhushi and further in view of Couture et. al. (US Pub. No. 20210102907 A1).
As per claim 6, Chirol in view of Madabhushi already teaches “The method of claim 5, wherein the at least one reference material…”, however Chirol in view of Madabhushi does not teach “the at least one reference material is high-density polyethylene (HDPE).”
Couture teaches “the at least one reference material is high-density polyethylene (HDPE).” (See paragraphs 223 “[0223]… In an embodiment, a piece of HDPE plastic (plastic member) is located at a top of the field of view of the scanner, such that the X-ray scanning beam strikes the plastic piece and yields a signal which is used for calibration/normalization of each image. In embodiments, the HDPE plastic member may be a contrast block as shown in FIGS. 21A-21B and described below.”, see also paragraph 246 “FIG. 21A. Since, performance of an X-ray scanning system changes with changes in the operating temperature, in an embodiment, a contrast block is inserted in a region 2104 of scanning system 2102 as the contrast block enables correction of the X-ray beam output intensity and detector sensitivity with temperature of the X-ray scanning system. FIG. 21B illustrates a contrast block employed in the scanning system of FIG. 21A, in accordance with an embodiment of the present specification. In an embodiment, contrast block 2106 is a plastic (HDPE) block which is inserted in a field of view of the scanning system 2102.” See also figs. 20A, 21A-21D. Couture)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Chirol with the teachings of Madabhushi and Couture utilize HDPE as the reference material used for normalization. The modification would have been motivated by the desire to enable correction of the x-ray beam, therefore it is an improvement, as suggested by Couture (See also paragraph 246 “FIG. 21A. Since, performance of an X-ray scanning system changes with changes in the operating temperature, in an embodiment, a contrast block is inserted in a region 2104 of scanning system 2102 as the contrast block enables correction of the X-ray beam output intensity and detector sensitivity with temperature of the X-ray scanning system. FIG. 21B illustrates a contrast block employed in the scanning system of FIG. 21A, in accordance with an embodiment of the present specification. In an embodiment, contrast block 2106 is a plastic (HDPE) block which is inserted in a field of view of the scanning system 2102.” See also figs. 20A, 21A-21D. Couture)
Claim 13 is rejected under the same analysis of claim 6.
Claim 19 is rejected under the same analysis of claim 6.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DYLAN J MENDEZ MUNIZ whose telephone number is (703)756-5672. The examiner can normally be reached M-F, 8AM - 5PM ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Vu Le can be reached at (571) 272-7332. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/DYLAN JOHN MENDEZ MUNIZ/Examiner, Art Unit 2675
/VU LE/Supervisory Patent Examiner, Art Unit 2668
Prosecution Insights