DETAILED ACTION
Claim Rejections - 35 USC § 102
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)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 2, 3, 11-15, 19, and 20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Lo et al. (Pub. No. US 2019/0302000).
Regarding claim 2, Lo teaches an image-activated (image based) particle sorting system, comprising: a particle flow device comprising (i) a substrate and a channel formed on the substrate and configured to allow individual particles to flow through the channel along a flow direction to a first region of the channel, and (ii) two or more output paths branching from the channel at a second region proximate to the first region in the channel [Para. 9 and 11, fig. 1A and related description]; an imaging system interfaced with the particle flow device and configured to obtain image data associated with a particle flowing in the first region through the channel [Para. 9 and 11]; a control command unit (data processing and control unit) comprising a processor configured to produce a control command indicative of a particle class (subsets) determined based at least in part on a gating model (support vector machine (SVM)) and the image data [Para. 9, 99 “support vector machine”, and 100 “subsets”]; wherein: (i) the control command is produced when the particle (cell/particle) is flowing through the channel, and (ii) the gating model (support vector machine (SVM)) comprises a machine learning model trained to predict the particle class (subsets) based at least in part on the image data [Para. 9 “cells”, “channel”, “control command”; Para. 11; Para. 104 “The extracted morphology parameters were used for supervised machine learning to generate criteria for real-time image-based cell sorting.”; Para. 108 “subsets”; and Para 100 “subsets”]; and an actuator operatively coupled to the particle flow device and in communication with the control command unit (data processing and control unit) configured to direct the particle into an output path of the two or more output paths based at least in part on the control command and thereby sort the individual particles during flow in the channel [Para. 44, actuator, control unit, control command; Para. 9 and 11, output path, two or more output paths, control command, particles, etc…].
Regarding claim 3, Lo teaches wherein the image-activated particle sorting system has a latency of less than about 15 milliseconds, wherein the latency is measured from (i) a first time point at which the image data is obtained by the imaging system to (ii) a second time point at which the particle is being directed by the actuator into the output path [Para. 11].
Regarding claim 11, Lo teaches wherein the imaging system comprises one or more light sources configured to provide an input light to the first region of the particle flow device, and an optical imager configured to capture imaging data from the individual particles illuminated by the input light in the first region [Para. 127].
Regarding claim 12, Lo teaches wherein the one or more light sources comprise at least one of a laser or a light emitting diode (LED) [Para. 128].
Regarding claim 13, Lo teaches wherein the optical imager comprises an objective lens optically coupled to at least one of a band-pass optical filter or a photomultiplier tube [Para. 129].
Regarding claim 14, Lo teaches wherein the optical imager further comprises one or more light guide elements configured to direct the input light to the first region, to direct light emitted or scattered by the individual particles to an optical element of the optical imager, or both [Para. 130].
Regarding claim 15, Lo teaches wherein the optical imager comprises two or more photomultiplier tubes configured to generate two or more corresponding signals based at least in part on two or more bands or types of light emitted or scattered by the individual particles [Para. 132].
Regarding claim 19, Lo teaches wherein the particle flow device comprises a microfluidic device or a flow cell integrated with the actuator on the substrate of the microfluidic device or the flow cell [Para. 125].
Regarding claim 20, Lo teaches wherein the actuator comprises a piezoelectric actuator coupled to the substrate and configured to produce a deflection to cause the particle to move in a direction that directs the particle along a trajectory to the output path of the two or more output paths [Para. 126].
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.
Claims 4, 7, 8, 16, 17, and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Lo et al. (Pub. No. US 2019/0302000) in view of Zordan et al. (Pub. No. US 2022/0156482).
Regarding claim 4, Lo teaches having a gating model (support vector machine (SVM)) [Para. 99].
However, Lo doesn’t explicitly teach the rest of claim limitations.
However, Zordan teaches wherein the gating model comprises a convolutional neural network (CNN) based Artificial Intelligence (Al) model (convolutional neural network) [Para. 7, and 27].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Lo’s image-based sorting decision logic by replacing Lo’s SVM gating criterion with Zordan’s classifier that fine tunes a convolutional neural network and user artificial intelligence for real time image classification during active sorting. This medication improves Lo to reduce manual gating bias and improve flexible image-based sorting.
Regarding claim 7, Lo in view of Zordan further in view of Roth teaches all claim limitations stated above. Furthermore, Roth teaches wherein the CNN comprises a UNet model [Para. 50 and 56].
Regarding claim 8, Lo in view of Zordan further in view of Roth teaches all claim limitations stated above. Furthermore, Roth teaches wherein the U-Net model (U-Net architecture) is optimized to reduce an initial kernel (initial filters) count of initial convolution kernels in the U-Net model [Para. 56, 25, and 31].
Regarding claim 16, Lo teaches wherein the imaging system comprises a time domain signal data associated with the particle imaged in the first region on the particle flow device [Para. 134].
However, Lo doesn’t explicitly teach the rest of having a digitizer.
Zordan teaches wherein the imaging system comprises a digitizer (A/D converter) configured to obtain the image data that comprises time domain signal data associated with the particle imaged in the first region on the particle flow device [Para. 42].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Lo’s image-based sorting decision logic by replacing Lo’s SVM gating criterion with Zordan’s classifier that fine tunes a convolutional neural network and user artificial intelligence for real time image classification during active sorting. This medication improves Lo to reduce manual gating bias and improve flexible image-based sorting.
Regarding claim 17, Lo teaches a data processing unit in communication with the imaging system and the control command unit, wherein the data processing unit is configured to process the image data obtained by the imaging system [Para. 63].
However, Lo doesn’t explicitly teach the rest of claim limitations.
Zordan teaches output a particle image for the particle to be used as input to the gating model [Para. 29].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Lo’s image-based sorting decision logic by replacing Lo’s SVM gating criterion with Zordan’s classifier that fine tunes a convolutional neural network and user artificial intelligence for real time image classification during active sorting. This medication improves Lo to reduce manual gating bias and improve flexible image-based sorting.
Regarding claim 21, Lo teaches wherein the system further comprises a digitizer or a digital signal processing (DSP) module [Para. 170 and 68]
However, Lo doesn’t explicitly teach the rest of claim limitations.
Zordan teaches the Digi wherein the digitizer (A/D converter) is configured to capture the image data of the individual particles, and wherein the DSP module is configured to reconstruct a particle image via a temporal-spatial transformation [Para. 42].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Lo’s image-based sorting decision logic by replacing Lo’s SVM gating criterion with Zordan’s classifier that fine tunes a convolutional neural network and user artificial intelligence for real time image classification during active sorting. This medication improves Lo to reduce manual gating bias and improve flexible image-based sorting.
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Lo et al. (Pub. No. US 2019/0302000) in view of Zordan et al. (Pub. No. US 2022/0156482) further in view of Roth et al. (Pub. No. US 2021/0334955).
Regarding claim 5, Lo teaches a gating model using the processor of the control command unit [Para. 99 and 11].
However, Lo in view of Zordan doesn’t explicitly teach the claim limitations.
Roth teaches a kernel count of initial convolutional kernels (initial filters) of the Al model (U-Net architecture) is lower than 10 (eight) such that a training time (training time per active iteration) to train the gating model using the processor of the control command unit is no more than 2 hours (around 45 minutes) [Para. 56 and 67].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Lo’s processor-based sorting decision logic, as modified by Zordan’s convolutional neural network classifier, by using Roth’s U-net architecture having initial filters set to eight and training it on datasets having a training time per active iteration of around 45 minutes. This medication improves Lo by providing a compact neural network configuration that supports faster training and use in real-time image-based sorting.
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Lo et al. (Pub. No. US 2019/0302000) in view of Zordan et al. (Pub. No. US 2022/0156482) further in view of Roth et al. (Pub. No. US 2021/0334955) further in view of Skala et a. (Pub. No. US 2021/0049346).
Regarding claim 6, Lo in view of Zordan doesn’t explicitly teach the claim limitations.
However, Roth teaches wherein a kernel count of initial convolutional kernels (initial filters) of the Al model is lower than 10 (eight) [Para. 56].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Lo’s processor-based sorting decision logic, as modified by Zordan’s convolutional neural network classifier, by using Roth’s U-net architecture having initial filters set to eight and training it on datasets having a training time per active iteration of around 45 minutes. This medication improves Lo by providing a compact neural network configuration that supports faster training and use in real-time image-based sorting.
Lo in view of Zordan further in view of Roth doesn’t explicitly teach a classification accuracy of the gating model for determining particle classes of the individual particles is at least 90%.
However, Skala teaches a classification accuracy of the gating model for determining particle classes of the individual particles is at least 90% [Para. 49].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Lo’s in view of Zordan further in view of Roth’s CNN classifier, by tuning the trained CNN classifier to meet Skala’s accuracy level of at least 90%. This modification improves Lo by proving a CNN classifier with an expressly taught high classification-accuracy target for image-based cell/particle classification.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Lo et al. (Pub. No. US 2019/0302000) in view of Zordan et al. (Pub. No. US 2022/0156482) further in view of Yao et al. (Pub. No. US 2019/0294929).
Regarding claim 9, Roth teaches wherein the U-Net model (U-Net architecture) is optimized to reduce an initial kernel (initial filters) count of initial convolution kernels in the U-Net model [Para. 56, 25, and 31].
However, Lo in view of Zordan further in view of Roth doesn’t explicitly teach the rest of claim limitations.
However, Yao teaches wherein the U-Net model is optimized to reduce an initial kernel count of initial convolution kernels for reducing a model parameter, a model size (size of the convolutional neural network), a training time reduction, and an inference time (computation cost) [Para. 8, 57 and 58].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Lo’s in view of Zordan further in view of Roth’s real-time sorting decision model by applying Yao’s filter pruning technique to remove redundant filters and reduce parameters. This modification improves Lo’s by enabling Lo better support real-time inference in an image-activated sorting system.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Lo et al. (Pub. No. US 2019/0302000) in view of Herbig et al. (Pub. No. US 2021/0089751).
Regarding claim 10, Lo doesn’t explicitly teach the claim limitations.
Herbig teaches the individual particles are label-free (marker free), the imaging system is configured to obtain transmission images (bright-field images) of the individual particles, and the control command unit is configured to generate control commands for the individual particles based at least in part on the gating model and corresponding transmission images [Para. 6, 23, 27 and 44].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Lo’s image-based sorting system by using Herbig’s marker-free bright field image classification as the image-input basis for the sorting decision and control command. This medication improves Lo by avoiding fluorescent labeling while preserving rea-time image-based classification and sorting.
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Lo et al. (Pub. No. US 2019/0302000) in view of Zordan et al. (Pub. No. US 2022/0156482) further in view of Shashou et al. (Pub. No. US 2021/0120935).
Regarding claim 18, Lo in view of Zordan doesn’t explicitly teach the claim limitations.
However, Shashou teaches wherein the control command unit comprises a first processor and the data processing unit comprises a second processor, wherein the second processor is different from the first processor [Para. 166 and 167].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Lo in view of Zordan’s data processing and control unit by splitting image control functions across Shashou’s first processor and second processor architecture. This medication improves Lo by task-specializing processing resources so that camera/control operations and image-information extraction can run on separate dedicated processors.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SOLOMON G BEZUAYEHU whose telephone number is (571)270-7452. The examiner can normally be reached on Monday-Friday 10 AM-7 PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, O’Neal Mistry can be reached on 313-446-4912. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-0101 (IN USA OR CANADA) or 571-272-1000.
/SOLOMON G BEZUAYEHU/ Primary Examiner, Art Unit 2666
Prosecution Insights