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 .
Response to Arguments
Applicant’s arguments with respect to claim(s) 1, 5, 8, 10, 12-13, 16-18, 23-24 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.
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, 5, 8, 10, 12-13, 16-18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sanchez-Martin et al. (US2020/0232901) in view of Yamada et al. (US2018/0299382), Sugimoto (US2021/0310053) and Song et al. (US2019/0080453).
To claim 1, Sanchez-Martin teach a cell analysis method for analyzing cells using an artificial intelligence algorithm, the method comprising:
labelling cells in a sample, wherein each cell has a first target that is labeled with a first fluorescence label detectable within a first fluorescence waveform range, and a second target that is labelled with a second fluorescence label detectable within a second fluorescence waveform range different from the first fluorescence waveform range of the first fluorescence label (paragraph 0038, obviously different fluorescence labels with different waveform ranges correspond to different targets);
flowing the sample into a flow cell, wherein a cell in the sample has the first and second target that are labeled with the first and second fluorescence labels, respectively, before flowing the sample into the flow cell (50 of Fig. 1, flow cytometer system);
capturing, by an imaging unit, images of said cell in the sample passing through the flow cell to generate a pair of analysis target images of said cell passing through the flow cell, wherein the pair of analysis target images include a first fluorescence image representative of the first target of said cell labelled with the first fluorescence label and a second fluorescence image representative of the second target of said cell labelled with the second fluorescence label (paragraphs 0041-0044, detector would be an obvious imaging unit);
inputting the set of analysis data into the at least one processing device that runs an artificial intelligence algorithm (paragraph 0036, machine learning sorting module may use any suitable machine learning technique, including but not limited to statistical classification, supervised learning, unsupervised learning, artificial neural networks, deep learning neural networks, cluster analysis, random forest, dimensionality reduction, binary classification, decision tree, etc. to select configuration settings and to adjust configuration settings during cell sorting), wherein the artificial intelligence algorithm learns to output a judgement of whether a cell is with or without a chromosomal abnormality; executing the artificial intelligence algorithm running on the at least one processing device to analyze the set of analysis data and to output the judgement of whether said cell represented by the set of the analysis data is with or without the chromosomal abnormality; and based on the judgement outputted by the artificial intelligence algorithm, generating an analysis result indicating whether said cell represented by the set of the analysis data is with or without the chromosomal abnormality (Figs. 1-5; paragraphs 0047-0065).
But, Sanchez-Martin do not expressly disclose wherein each cell has a first target chromosomal gene that is labeled with a first fluorescence label that has a first fluorescence waveform range, and a second target chromosomal gene that is labelled with a second fluorescence label that has a second fluorescence waveform range different from the first fluorescence waveform range of the first fluorescence label; integrating, by at least one processing device, the first and second fluorescence images in the pair to generate a set of analysis data, wherein the set of analysis data corresponds to the pair of the integrated first and second fluorescence images; wherein the artificial intelligence algorithm has a neural network structure having an intermediate layer that is weighted in advance with positive and negative training data representative of cells with a chromosomal abnormality and cells without a chromosomal abnormality so that the artificial intelligence algorithm.
However, a trained neural network being weighted in advance with positive and negative training data is well-known in the art.
Yamada teach a cell analysis method for analyzing cells, the method comprising: labelling cells in a sample, wherein each cell has a first target chromosomal gene that is labeled with a first fluorescence label that has a first fluorescence waveform range, and a second target chromosomal gene that is labelled with a second fluorescence label that has a second fluorescence waveform range different from the first fluorescence waveform range of the first fluorescence label (paragraphs 0028, 0037, 0040, 0059, BCR gene on chromosome and an ABL gene on chromosome are set as target sites), wherein each cell has a first target chromosomal gene that is labeled with a first fluorescence label that has a first fluorescence waveform range, and a second target chromosomal gene that is labelled with a second fluorescence label that has a second fluorescence waveform range different from the first fluorescence waveform range of the first fluorescence label (paragraphs 0053); flowing the sample into a flow cell, wherein each of at least some of the cells in the sample has the first and second target chromosomal genes that are labeled before flowing the sample into the flow cell (paragraphs 0034-0038); capturing, by an imaging unit, images of cells in the sample passing through the flow cell to generate pairs of analysis target images of the cells passing through the flow cell, wherein each pair of analysis target images include a first fluorescence image representative of the first target chromosomal gene of one cell labelled with the first fluorescence label and a second fluorescence image representative of the second target chromosomal gene of said one cell labelled with the second fluorescence label (paragraph 0039); integrating, by at least one processing device, the first and second fluorescence images in each pair to generate sets of analysis data, wherein each set of analysis data corresponds to a pair of the integrated first and second fluorescence images (paragraphs 0039-0040); inputting the sets of analysis data into the at least one processing device to output a judgement of whether a cell is with or without a chromosomal abnormality; executing the at least one processing device to analyze the sets of analysis data and to output the judgement of whether the cell represented by each set of the analysis data is with or without the chromosomal abnormality; and based on the judgement outputted by the artificial intelligence algorithm, generating an analysis result indicating whether the cell represented by each set of the analysis data is with or without the chromosomal abnormality (Fig. 11; paragraphs 0004, 0028-0030, 0056-0063, 0070, 0075-0076), which would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate into the method of Sanchez-Martin, in order to further detail implementation of flow cell analysis.
Sugimoto teach artificial intelligence trained with both positive and negative training data (paragraphs 0016, 0086, 0098, 0140) to identify and detect anomaly (paragraph 0099) in cell images obtained through flow cell process (paragraphs 0010, 0012, 0063, 0101), which corresponds to flow cytometer of Sanchez-Martin and Yamada.
In furthering anomaly detection of Sugimoto, Song teach using a convolutional neural network trained with both positive and negative training data (paragraphs 0006-0007, 0060) to identify a cancer cells within a digital image (paragraphs 0003-0005), which correspond to Sanchez-Martin’s teaching.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate teaching of Sugimoto and Song into the method of Sanchez-Martin and Yamada, in order to further implementation detail of flow cytometer system.
To claim 16, Sanchez-Martin, Yamada, Sugimoto and Song teach a cell analysis system for analyzing cells using an artificial intelligence algorithm, the cell analysis device (as explained in response to claim 1 above).
To claim 17, Sanchez-Martin, Yamada, Sugimoto and Song teach a cell analysis system (as explained in response to claim 1 above).
To claim 18, Sanchez-Martin, Yamada, Sugimoto and Song teach a non-transitory computer readable medium having stored therein a computer program for analyzing cells, that, when executed on a computer (as explained in response to claim 1 above).
To claim 5, Sanchez-Martin, Yamada, Sugimoto and Song teach claim 1.
Sanchez-Martin, Yamada, Sugimoto and Song teach wherein the first and second target chromosomal genes are labeled by an in-situ hybridization method (Yamada, paragraph 0028).
To claim 8, Sanchez-Martin, Yamada, Sugimoto and Song teach claim 1.
Sanchez-Martin, Yamada, Sugimoto and Song teach wherein the pair of analysis target images shows an identical field of view of said one cell and is captured at different wavelengths of light (Yamada, paragraphs 0032-0037).
To claim 10, Sanchez-Martin, Yamada, Sugimoto and Song teach claim 8.
Sanchez-Martin, Yamada, Sugimoto and Song teach wherein the pair of analysis target images include a bright field image of said cell and the first and second fluorescence image of said cell (Yamada, paragraph 0053).
To claim 12, Sanchez-Martin, Yamada, Sugimoto and Song teach claim 1.
Sanchez-Martin, Yamada, Sugimoto and Song teach wherein the artificial intelligence algorithm is a deep learning algorithm having a neural network structure (Sanchez-Martin, paragraph 0036).
To claim 13, Sanchez-Martin, Yamada, Sugimoto and Song teach claim 12.
Sanchez-Martin, Yamada, Sugimoto and Song teach wherein the analysis data includes a brightness of each pixel in each analysis target image (Yamada, paragraphs 0040, 0053, 0066).
Claim(s) 23-24 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sanchez-Martin et al. (US2020/0232901) in view of Yamada et al. (US2018/0299382), Sugimoto (US2021/0310053), Song et al. (US2019/0080453) and Kouchi et al. (US5741213).
To claim 23, Sanchez-Martin, Yamada, Sugimoto and Song teach claim 8.
But, Sanchez-Martin, Yamada, Sugimoto and Song do not expressly disclose wherein generating the analysis data includes performing a trimming process on the analysis target images to determine a center of gravity of each cell in the analysis target images and size each of the analysis target images to be comparable to the training data.
However, trimming is an obvious feature in neural network.
Kouchi teach using neural network to analyze image to identify object blood cell (abstract, column 2 lines 30-55), comprises: performing a trimming process on the analysis target images to determine a center of gravity of said cell in the analysis target images and size each of the analysis target images to be comparable to the training data (Figs. 1, 12-13; column 7 line 63 to column 8 line 23, trimmed input image as referenced), which would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate into the method of Sanchez-Martin, Yamada, Sugimoto and Song, in order to further neural network processing.
To claim 24, Sanchez-Martin, Yamada, Sugimoto and Song teach claim 8.
Sanchez-Martin, Yamada, Sugimoto, Song and Kouchi teach wherein the positive and negative training data is generated from training target images of the cells with a chromosomal abnormality and the cells without a chromosomal abnormality, and generating the training data includes performing a trimming process on the training target images identical to a trimming process performed on the analysis target images (as explained in response to claim 23 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 ZHIYU LU whose telephone number is (571)272-2837. The examiner can normally be reached Weekdays: 8:30AM - 5:00PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Stephen R Koziol can be reached at (408) 918-7630. 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.
ZHIYU . LU
Primary Examiner
Art Unit 2669
/ZHIYU LU/Primary Examiner, Art Unit 2665 January 3, 2026