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 Status
The status of claims 1-20 is:
Claims 1-20 were pending as of the Non-Final Rejection mailed 10/01/2025.
Claims 1, 9, 13, 15, and 16 are amended as of the amendments and remarks received 01/30/2026.
Claims 2-3, 5-8, 10-12, 14, and 17-20 remain as originally presented as of the amendments and remarks received 01/30/2026.
Claim 21 is new as of the amendments and remarks received 01/30/2026.
Claim 4 is cancelled as of the amendments and remarks received 01/30/2026.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claim 21 is rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. The specification does not include the subsets claimed in claim 21, nor did the Applicant point to any part of the specification that supports the claim language in claim 21.
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.
Claim(s) 1-2, 5-6, 8 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Bredno et al. (U.S. 2017/0372117, hereinafter “Bredno”) in view of Monabbati et al. (Monabbati, S., Leo, P., Bera, K., Nezami, B. G., Michael, C. W., Harbhajanka, A., & Madabhushi, A. (2020, March). Texture features distinguish benign cell clusters from adenocarcinomas on bile duct brushing cytology images. In Medical Imaging 2020: Digital Pathology (Vol. 11320, pp. 123-133). SPIE., using the copy provided in the IDS mailed 09/13/2023, hereinafter “Monabbati”).
Regarding claim 1, Bredno discloses a method comprising:
accessing one or more digitized pathology images of a cell cluster area (Bredno [0063]: “A “sample” or “tissue sample” may be any solid or fluid sample obtained from, excreted by or secreted by any living organism, including without limitation, single celled organisms, such as bacteria, yeast, protozoans, and amoebas among others, multicellular organisms (such as plants or animals, including samples from a healthy or apparently healthy human subject or a human patient affected by a condition or disease to be diagnosed or investigated, such as cancer) which are suitable for histochemical or cytochemical analysis”);
segmenting the cell cluster area to identify segmented nuclei and non-nuclei regions (Bredno [0079]: “In some embodiments, the digital images received as input are pre-processed such as to detect nucleus centers and/or to segment the nuclei”; Bredno [0080]: “The nuclei are then subsequently segmented using thresholds individually computed for each nucleus”);
extracting a plurality of texture features from the segmented nuclei and the non-nuclei regions (Bredno [0088]: “After the nuclear feature metrics are computed, contextual information metrics are derived for each nucleus of interest (NoI). It is believed that the contextual information of a NoI, i.e. information describing neighboring nuclei or the image texture in a region centered at the NoI, provides useful evidence to predict its label”);
extracting a plurality of nuclear shape features from the segmented nuclei (Bredno [0074]: “Nuclear feature metrics are first computed for each cell or cell nucleus based on their visual properties and descriptors, e.g. morphology features, appearance features, and background features, each described below”; Bredno [0075]: “A “morphology feature” as used herein is, for example, a feature being indicative of the shape or dimensions of a nucleus or of a cell comprising the nucleus”), wherein the plurality of nuclear shape features include geometric features determined from individual ones of the segmented nuclei (Bredno [0074]: “Nuclear feature metrics are first computed for each cell or cell nucleus based on their visual properties and descriptors, e.g. morphology features, appearance features, and background features, each described below”); and
providing one or more of the plurality of nuclear shape features and one or more the plurality of texture features to a machine learning model configured to generate a cytological diagnosis of the epithelial cells within the cell cluster area (Bredno [0139]: “After the nuclear metrics and contextual information metrics are derived by the feature extraction module, the metrics are provided to a classification module to detect and label cell nuclei according to type (e.g. tumor, immune, stroma, etc.) or a response to a particular stain (e.g. stain indicative of the presence of PDL1). In some embodiments, the classifier is trained and then used to distinguish five classes of nuclei in PD-L1 stained tissue including positive tumor, negative tumor, positive lymphocytes, non-target stain, and others (see FIGS. 7A and 7B, which shows five classes of nuclei in PD-L1 stained lung tissue images where positive tumor, negative tumor, positive lymphocytes, non-target stain, and others are indicated by green arrows (“E”), blue arrows (“A”), red arrows (“B”), yellow arrows (“C”), and cyan arrows (“D”), respectively)”, the different classes are the cytological diagnosis of the cells).
Bredno does not explicitly disclose the method, comprising:
wherein the cells are epithelial cells and are obtained from a bile duct of a patient having a bile duct stricture (However, Bredno does disclose that the sample can be any cells collected from a living organism [0063]).
However, Monabbati teaches the method, comprising:
wherein the epithelial cells are obtained from a bile duct of a patient having a bile duct stricture (Monabbati Page 3: “Hence, bile duct brushings (BDBs) are the preferred cytopathology test to obtain samples from the bile duct due to their low complication rate”).
It would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to incorporate using bile duct epithelial cells as taught by Monabbati with the method of Bredno because bile duct cancer, specifically cholangiocarcinoma, only has a 6% survival rate when diagnosed late and as such, finding a way to diagnose bile duct cancer earlier would be would improve health outcomes (Monabbati Page 2). This motivation for the combination of Bredno and Monabbati is supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention and exemplary rationale (A) Combining prior art elements according to known methods to yield predictable results.
Regarding claim 2, Bredno discloses the method, further comprising:
placing the epithelial cells on a slide (Bredno [0064]: “One method of producing a digital image includes determining a scan area comprising a region of the microscope slide that includes at least a portion of the specimen. The scan area may be divided into a plurality of “snapshots.” An image can be produced by combining the individual “snapshots.” In some embodiments, the imaging apparatus 12 produces a high-resolution image of the entire specimen, one example for such an apparatus being the VENTANA iScan HT slide scanner from Ventana Medical Systems, Inc. (Tucson, Ariz.)”); and
and obtaining an image of the slide to form a whole slide image, wherein the one or more digitized pathology images comprise the whole slide image (Bredno [0064]: “One method of producing a digital image includes determining a scan area comprising a region of the microscope slide that includes at least a portion of the specimen. The scan area may be divided into a plurality of “snapshots.” An image can be produced by combining the individual “snapshots.” In some embodiments, the imaging apparatus 12 produces a high-resolution image of the entire specimen, one example for such an apparatus being the VENTANA iScan HT slide scanner from Ventana Medical Systems, Inc. (Tucson, Ariz.)”).
Bredno does not explicitly disclose the method, further comprising:
inserting a cytology brush into the bile duct of the patient to obtain a brush specimen comprising the epithelial cells from the bile duct stricture.
However, Monabbati teaches the method, further comprising:
inserting a cytology brush into the bile duct of the patient to obtain a brush specimen comprising the epithelial cells from the bile duct stricture (Monabbati Page 3: “Hence, bile duct brushings (BDBs) are the preferred cytopathology test to obtain samples from the bile duct due to their low complication rate”).
It would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to incorporate using a cytology brush as taught by Monabbati with the method of Bredno because it would improve the method as obtaining the cells using a cytology brush has a lower complication rate than other methods of obtaining the cells (Monabbati Page 3). This motivation for the combination of Bredno and Monabbati is supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention and exemplary rationale (D) Applying a known technique to a known device (method, or product) ready for improvement to yield predictable results.
Regarding claim 5, Bredno discloses the method, wherein the plurality of texture features include one or more of Gabor features, Law's features, Haralick features, and CoLlAGe (Co-occurrence of Local Anisotropic Gradient Orientations) features (Bredno [0094]: “In some embodiments, the textural features computed include features such as histogram of intensities, histogram of gradient magnitude and gradient orientation, Gabor features, and Haralick features, each of which are described further herein”).
Regarding claim 6, Bredno discloses the method,
wherein the plurality of texture features are computed for each pixel within the one or more digitized pathology images (Bredno [0089]: “Contextual information may be derived by any method known to those of skill in the art. In some embodiments, the contextual information is derived from at least one of (1) a context-texture method; (2) a context-texton method; (3) a context-CRF method; and (4) a context-Bag of Words (BoW) method. In some embodiments, the contextual information requires the computation of additional features from all image pixels in a neighborhood of each nucleus (see, for example, the Context-Texture Method and the Context-Texton Method herein)”); and
wherein statistical measures are computed for each texture feature over the cell cluster area (Bredno [0102]: “In some embodiments, the textural features are computed from different image channels. For example, the different image channels may be based on the stains or counterstains used in preparing the tissue samples (e.g. the hematoxylin, luminance, IHC channels, PDL1 stain channels). In some embodiments, the differences in signals from the different image channels are captured to compute intensity-based features which may be helpful in describing tissue structures. This is achieved by “binning” the range of values, i.e. the entire range of values (intensities) is divided into a series of small intervals—and then how many values fall into each interval is counted. Thus, an “intensity-based feature” may be a binned intensity value of a pixel or a set of pixels. These features may be supplied to the classification module. In other embodiments, gradient features are determined by computing the gradient magnitude and gradient orientation of the image. In some embodiments, the gradient features include a histogram of gradient magnitude and/or a histogram of the gradient vector orientation. For example, the gradient features may include a 10-bin histogram of gradient magnitude, and a 10-bin histogram of the gradient vector orientation. These features are computed, for example, selectively for pixels within a patch, wherein the patch can be identified e.g. by a superpixel generation algorithm. It is believed that these features may differentiate homogeneous from inhomogeneous regions, and differentiate regions with similarly oriented edges from regions with randomly oriented edges. The calculation of histogram is similar to the above with regard to the “binning” of a range of values. In addition to a histogram, in some embodiments, different descriptive statistics like mean, standard deviation, curtosis, percentiles, etc. may be derived as features of the gradient magnitude and gradient orientation. These features may be supplied to the classification module”).
Regarding claim 8, Bredno discloses the method, wherein the plurality of texture features are determined at an aggregate level on the cell cluster area (Bredno [0088]: “After the nuclear feature metrics are computed, contextual information metrics are derived for each nucleus of interest (NoI). It is believed that the contextual information of a NoI, i.e. information describing neighboring nuclei or the image texture in a region centered at the NoI, provides useful evidence to predict its label”, the features are derived for the aggregate nuclei of interest) to investigate interplay between the segmented nuclei and cytoplasm surrounding the segmented nuclei (this limitation seems to be a motivation or intended use and does not have patentable weight).
Regarding claim 12, Bredno discloses the method, further comprising:
identifying a plurality of diagnostic features from the plurality of texture features and the plurality of nuclear shape features (Bredno [0150]: “In some embodiments, the context-Bow method classifies the NoI in a test image by: (a) generating a nuclear feature vector for each nucleus of the test image based on one or more nuclear features extracted from the nucleus; (b) assigning each individual neighboring nucleus of the NoI to one of the pretrained C clusters by: (c1) measuring the Euclidean distance from the nuclear feature vector of each individual neighboring nucleus to the centers of the C clusters; and (c2) assigning the individual neighboring nucleus to the cluster whose center is closest to the nuclear feature vector of that nucleus; (d) determining contextual features of the NoI by calculating a histogram of the cluster assignments of the neighboring nuclei; and (e) combining the nuclear feature vector of the NoI with the contextual features into a complete feature vector for the NoI (f) applying the trained classification model on the complete feature vector of the NoI to classify it”).
Claim(s) 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over the Bredno and Monabbati combination in view of Shah et al. (Shah, P., Chakraborty, C., & Ray, A. K. (2010, June). Morphometric pattern analysis of basal cell nuclei for oral cancer screening. In 2010 4th International Conference on Bioinformatics and Biomedical Engineering (pp. 1-4). IEEE., hereinafter “Shah”).
Regarding claim 9, the Bredno and Monabbati combination does not explicitly disclose the method, further comprising:
forming an elliptical bounding box around each of the segmented nuclei, wherein the elliptical bounding box is used to compute one or more of the plurality of nuclear shape features.
However, Shah teaches the method, further comprising:
forming an elliptical bounding box around each of the segmented nuclei (Shah Fig. 1: shows the elliptical bounding boxes), wherein the elliptical bounding box is used to compute one or more of the plurality of nuclear shape features (Shah Page 3: “Eccentricity is calculated by the following equation … where a and b indicate major and minor axis. Which are obtained by elliptical approximation”).
It would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to incorporate computing shape features using an elliptical bounding box as taught by Shah with the method of Bredno and Monabbati because the dimensions of nuclei can indicate if a cell is benign or malignant (Shah Page 1). This motivation for the combination of Bredno, Monabbati, and Shah is supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention and exemplary rationale (A) Combining prior art elements according to known methods to yield predictable results.
Regarding claim 10, the Bredno and Monabbati combination does not explicitly disclose the method, wherein the plurality of nuclear shape features comprise one or more of an area, a major axis length of the elliptical bounding box, a minor axis length of the elliptical bounding box, an orientation of a major axis length, an equivalent diameter, a solidity, and a perimeter.
However, Shah teaches the method, wherein the plurality of nuclear shape features comprise one or more of an area, a major axis length of the elliptical bounding box, a minor axis length of the elliptical bounding box, an orientation of a major axis length, an equivalent diameter, a solidity, and a perimeter (Shah Page 3: “The following features are evaluated for nucleus. a) area, b) perimeter, c) compactness, d) eccentricity”).
It would have been obvious to combine the Bredno and Monabbati combination with Shah for the same reasons as for claim 9 above.
Claim(s) 11 is rejected under 35 U.S.C. 103 as being unpatentable over the Bredno and Monabbati combination in view of Rahmadwati et al. (Rahmadwati, Naghdy, G., Ros, M., & Todd, C. (2012, February). Morphological characteristics of cervical cells for cervical cancer diagnosis. In Proceedings of the 2011 2nd International Congress on Computer Applications and Computational Science: Volume 2 (pp. 235-243). Berlin, Heidelberg: Springer Berlin Heidelberg., hereinafter “Rahmadwati”).
Regarding claim 11, the Bredno and Monabbati combination does not explicitly disclose the method, wherein the plurality of nuclear shape features comprise a nuclei-to-cytoplasm ratio determined for the cell cluster area by dividing a total nuclear area of the cell cluster area by a non-nuclear area of the cell cluster area.
However, Rahmadwati teaches the method, wherein the plurality of nuclear shape features comprise a nuclei-to-cytoplasm ratio determined for the cell cluster area (Rahmadwati Page 3: “Using the histology images acquired from the pathology laboratories in an Indonesian hospital, this study aims to classify cervical biopsy images based on four well known discriminatory features a) the ratio of nuclei to cytoplasm”) by dividing a total nuclear area of the cell cluster area by a non-nuclear area of the cell cluster area (Rahmadwati Page 5: “The areas of each corresponding nuclei and cytoplasm detected are calculated in order to calculate the feature referred to as nuclei to cytoplasm (N/C) ratio”).
It would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the nuclei-to-cytoplasm ratio as taught by Rahmadwati with the method of Bredno and Monabbati because a high nuclei to cytoplasm ratio can indicate malignant tissue (Rahmadwati Page 5). This motivation for the combination of Bredno, Monabbati, and Rahmadwati is supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention and exemplary rationale (A) Combining prior art elements according to known methods to yield predictable results.
Claim(s) 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Vu in view of Monabbati and Yip et al. (U.S. Patent Publication No 2021/0166380, hereinafter “Yip”).
Regarding claim 19, Vu discloses operations comprising:
accessing one or more digitized pathology images of a cell cluster are comprising epithelial cells, the one or more digitized pathology images comprising a cell cluster area including epithelial cells (Vu Fig. 1: shows the input is a digitized pathology image);
segmenting the cell cluster area to identify segmented nuclei and non-nuclei regions (Vu Page 3: “We developed an approach of convolutional neural networks (CNNs) to precisely segment nuclei. The method is composed of three major steps: (1) nuclei blob and boundary detection via CNNs, (2) separation of touching (or overlapping) nuclei by combining the nuclei blob and boundary detection results through a watershed algorithm, and (3) final segmentation of individual nuclei. The entire workflow is shown in Figure 1”);
extracting a plurality of texture features from the segmented nuclei and the non-nuclei regions (Vu Page 3: “Next, it extracts a collection of statistical and morphological features from the LUAD and LUSC probability maps as input into a random forest regression model to classify each WSI”; Vu Page 2: “Accurate quantitative characterizations of the shape, size, and texture properties of nuclei are key components of the study of the tumor systems biology and the complex patterns of interaction between tumor cells and other cells”; according to biologyonline.com (Cell morphology - definition and examples - biology online dictionary. Biology Articles, Tutorials & Dictionary Online. (2021, August 14). https://web.archive.org/web/20210920203156/https://www.biologyonline.com/dictionary/cell-morphology), cell morphological features include “size, form, shape, structure, color, texture, and pattern”) and extracting a plurality of nuclear shape features from the segmented nuclei (Vu Page 3: “Next, it extracts a collection of statistical and morphological features from the LUAD and LUSC probability maps as input into a random forest regression model to classify each WSI”; Vu Page 2: “Accurate quantitative characterizations of the shape, size, and texture properties of nuclei are key components of the study of the tumor systems biology and the complex patterns of interaction between tumor cells and other cells”; according to biologyonline.com (Cell morphology - definition and examples - biology online dictionary. Biology Articles, Tutorials & Dictionary Online. (2021, August 14). https://web.archive.org/web/20210920203156/https://www.biologyonline.com/dictionary/cell-morphology), cell morphological features include “size, form, shape, structure, color, texture, and pattern”); and
a machine learning model configured to classify the epithelial cells as malignant or non-malignant based upon one or more of the plurality of texture features and one or more of the plurality of nuclear shape features (Vu Page 2: “This method is the first 3-class network that aims to classify each WSI into diagnostic and non-diagnostic areas”).
Vu does not explicitly disclose operations, comprising:
wherein the epithelial cells are obtained from a stricture within a bile duct of a patient.
However, Monabbati teaches the operation, comprising:
wherein the epithelial cells are obtained from a stricture within a bile duct of a patient (Monabbati Page 3: “Hence, bile duct brushings (BDBs) are the preferred cytopathology test to obtain samples from the bile duct due to their low complication rate”).
It would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to incorporate using bile duct epithelial cells as taught by Monabbati with the operations of Vu because bile duct cancer, specifically cholangiocarcinoma, only has a 6% survival rate when diagnosed late and as such, finding a way to diagnose bile duct cancer earlier would be would improve health outcomes (Monabbati Page 2). This motivation for the combination of Vu and Monabbati is supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention and exemplary rationale (A) Combining prior art elements according to known methods to yield predictable results.
The Vu and Monabbati combination does not explicitly disclose a memory or the circuits configured to perform the operations.
However, Yip teaches a memory (Yip [0433]: “The computer-readable media may include executable computer-readable code stored thereon for programming a computer (e.g., comprising a processor(s) and GPU(s)) to the techniques herein. Examples of such computer-readable storage media include a hard disk, a CD-ROM, digital versatile disks (DVDs), an optical storage device, a magnetic storage device, a ROM (Read Only Memory), a PROM (Programmable Read Only Memory), an EPROM (Erasable Programmable Read Only Memory), an EEPROM (Electrically Erasable Programmable Read Only Memory) and a Flash memory”) and the circuits configured to perform the operations (Yip [0433]: “More generally, the processing units of the computing device 1300 may represent a CPU-type processing unit, a GPU-type processing unit, a TPU-type processing unit, a field-programmable gate array (FPGA), another class of digital signal processor (DSP), or other hardware logic components that can be driven by a CPU”).
It would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the memory and the circuits as taught by Yip with Vu and Monabbati because it would improve the invention by allowing the device to perform the operations. This motivation for the combination of Vu, Monabbati, and Yip is supported by KSR exemplary rationale (D) Applying a known technique to a known device (method, or product) ready for improvement to yield predictable results.
Regarding claim 20, Vu discloses the apparatus, further comprising:
a diagnostic feature identification circuit configured to identify a plurality of diagnostic features from the plurality of texture features and the plurality of nuclear shape features (Vu Fig. 4 description: “Workflow for training the neural network to classify input patches as either non-diagnostic (ND), lung adenocarcinoma (LUAD), or lung squamous cell carcinoma (LUSC)”; Wu Page 13: “The experimental results show that use of a deep learning network and a random forest regression model, which uses statistical and morphological features extracted from images, can achieve good classification accuracy”), wherein the machine learning circuit is configured to operate upon the plurality of diagnostic features to classify the cell cluster area (Vu Fig. 4 description: “Workflow for training the neural network to classify input patches as either non-diagnostic (ND), lung adenocarcinoma (LUAD), or lung squamous cell carcinoma (LUSC)”; Wu Page 13: “The experimental results show that use of a deep learning network and a random forest regression model, which uses statistical and morphological features extracted from images, can achieve good classification accuracy”).
Allowable Subject Matter
Claims 15-18 are allowed.
Claims 3, 7, and 13-14 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.
Claim 21 was not disclosed in the prior art, but is rejected under 35 USC 112(a) for including new matter as stated above.
Response to Arguments
Applicant’s arguments with respect to claim(s) 1-3, and 5-14 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Applicant’s arguments with respect to the allowability of claim 15 and its dependent claims in light of the amendments to claim 15 are persuasive. The 103 rejection of claim 15 and its dependent claims has been withdrawn in light of the amendments and claims 15-18 are allowable.
Applicant's arguments regarding claims 19-20 have been fully considered but they are not persuasive. Applicant argues on pages 11-12 of Applicant’s arguments and remarks that Vu does not discloses classifying the epithelial cells as malignant or non-malignant based upon one or more of the plurality of textual features and one or more of the plurality of nuclear shape features. Examiner respectfully disagrees. First, Vu classifies the cells as either non-diagnostic, lung adenocarcinoma, or lung squamous cell carcinoma (Page 3). Those classifications include two malignant classifications (the two cancers) and a non-malignant classification (non-diagnostic). This is within the BRI of the claim as there is no limitation in the claim requiring a strict binary classification as Applicant is characterizing. One of ordinary skill in the art would understand the two cancer classifications to be malignant classifications and the non-diagnostic classification as being a non-malignant classification. As such, Vu discloses that claim limitation. Second, Vu discloses making the classification based on the texture features and the shape features (Vu Page 3: “Next, it extracts a collection of statistical and morphological features from the LUAD and LUSC probability maps as input into a random forest regression model to classify each WSI”; Vu Page 2: “Accurate quantitative characterizations of the shape, size, and texture properties of nuclei are key components of the study of the tumor systems biology and the complex patterns of interaction between tumor cells and other cells”; according to biologyonline.com (Cell morphology - definition and examples - biology online dictionary. Biology Articles, Tutorials & Dictionary Online. (2021, August 14). https://web.archive.org/web/20210920203156/https://www.biologyonline.com/dictionary/cell-morphology), cell morphological features include “size, form, shape, structure, color, texture, and pattern”; Vu Page 3: “Next, it extracts a collection of statistical and morphological features from the LUAD and LUSC probability maps as input into a random forest regression model to classify each WSI”). Applicant attempts to use the argument that it used from claim 1 that the features in Vu are region level characteristics and not nucleus-level features on page 12 of Applicant’s arguments and remarks. However, claim 19 does not have the claim limitation that Applicant amended into claim 1 that the plurality of nuclear shape features include geometric features determined from individual ones of the segmented nuclei. Thus, Vu’s disclosure falls within the BRI of the claims because the features extracted by Vu, despite being regional, are still extracted from the nuclei as the nuclei are a part of the region that is extracted. Therefore, Vu discloses the claim limitations of claims 19 and the 103 rejection of claim 19 is maintained.
The rejection of claim 20 is maintained for the same reasons as for claim 19 above.
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 AIDAN KEUP whose telephone number is (703)756-4578. The examiner can normally be reached Monday - Friday 8:00-4:00.
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, Emily Terrell can be reached at (571) 270-3717. 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.
/AIDAN KEUP/ Examiner, Art Unit 2666
/Molly Wilburn/ Primary Examiner, Art Unit 2666
Prosecution Insights