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, see Remarks, page 11, filed 25 March 2026, with respect to the objections to the drawings have been fully considered and are persuasive in light of the amendment. The objections to the drawings have been withdrawn.
Applicant’s arguments, see Remarks, page 11, filed 25 March 2026, with respect to the claim rejections under 35 U.S.C. 112(b) have been fully considered and are persuasive in light of the amendments. The rejections of claims 5 – 13 have been withdrawn.
Applicant’s arguments, see Remarks page 11, filed 25 March 2026, with respect to the rejection( of claims 1 – 13 under 35 USC 102 and 103 have been fully considered and are persuasive in light of the amendments to the claims. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Germano et al in view of Durve.
Applicant’s arguments regarding the appropriateness of modifications to Germano’s device are not compatible are not convincing. One of ordinary skill in the art, faced with the inlet, outlet, main channels, and bypass channels taught by Germano et al, would be able to adjust the material of the microfluidic chip to allow the appropriate levels of light or contrast. Likewise, if the optical filter of Germano et al is not desired, it would be obvious to one of ordinary skill in the art to remove it (see MPEP 2144.04(II) regarding elimination of an element and its function when undesired.).
Ultimately, Germano et al teaches a microfluidic chip which can be used to image cells passing through constrictions. This base device, (described by applicant as the core cell counting device and thin glass coverslip) would be functional with a traditional imaging system, such as that disclosed in Durve.
Status of Claims
Applicant's amendments to the claims filed 25 March 2026 have been entered. Applicant's remarks filed 25 March 2026 are acknowledged.
Claims 1, 5 – 7, and 13 are in status “Currently amended.” Claims 2 – 4 and 8 – 12 are in status “original.” Claims 14 – 20 are in withdrawn as due to non-elected subject matter.
Claim Rejections - 35 USC § 103
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claims 1 – 7 are rejected under 35 U.S.C. 103 as being unpatentable over Germano (US 20250216315 A1) in view of Durve et al (Durve M, Tiribocchi A, Bonaccorso F, Montessori A, Lauricella M, Bogdan M, Guzowski J, Succi S. “DropTrack—Automatic droplet tracking with YOLOv5 and DeepSORT for microfluidic applications.” Physics of Fluids. 2022; 34, 082003).
With regards to claim 1, Germano teaches;
The claimed “a microfluidic chip for implementing cell deformability” has been read on the taught ([0015], “Preferably, the minimum width dimension of the microfluidic channel is less than the diameter of a target cell type within the fluid when in a relaxed state, such that the target cell type is deformed from its relaxed shape as it flows through the microfluidic channel.”);
The claimed “an inlet configured to receive cells” has been read on the taught ([0011], “…a microfluidic channel configured to receive a flow of a cell-containing fluid through an inlet…”);
The claimed “an outlet configured to output the cells have entered the microfluidic chip via the inlet” has been read on the taught ([0105], “The cell counting device 1 may further includes a reservoir 80 at either end of the channel for receiving fluid F.”; Figure 5 shows that reservoir 80 is positioned to receive the downstream fluid flow.);
The claimed “a plurality of main channels disposed between the inlet and the outlet and provided with microconstrictions that are parallelized” has been read on the taught ([0105], “FIG. 5 shows the cell counting device 1 with a channel width that gets narrower, remains constant for a given length and widens again.”; [0109], “The microfluidic channels 10 have the same channel length and are arranged parallel to one another.”; See Figure 7 teaching a plurality of main channels);
The claimed main channels with microconstrictions being “parallelized such that images of the cells are captured within a single field of view (FOV)…” has been read on the taught ([0111], “For example, SPADs comprises of many pixels spanning a relatively large area…”);
The claimed “one or more bypass channels disposed between the inlet and the outlet and independent from the plurality of main channels, thereby stabilize the pressure drop between the inlet and the outlet” has been read on the taught ([0109], “The cell counting device 1 may include at least one pressure relief channel 90.”).
However, Germano does not explicitly disclose wherein the microconstrictions that are parallelized such that images of the cells are recorded within a single field of view (FOV) by a camera when the cells pass through the microconstrictions simultaneously and are deformed therein.
In the analogous art of microfluidic devices, Durve et al teaches;
The claimed “microconstrictions that are parallelized such that images of the cells are recorded within a single field of view (FOV) by a camera when the cells pass through the microconstrictions” has been read on the taught (Page 082003-2, column 1, paragraph 3, “A digital camera connected to a microscope can conveniently be installed to observe small droplets within microfluidic chips and it would be totally sufficient for this purpose.”; Page 082003-3, column 1, paragraph 2, “Consequently, each experiment is documented in a video containing a few hundred images.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the microfluidic chip as taught by Germano with the camera as taught by Durve et al. According to MPEP 2143(I)(C), use of a known technique to improve similar devices in the same way may be prima facie obvious. In the case of the instant invention, the prior art of Germano teaches a “base” microfluidic device with parallelized microconstrictions that is suitable for imaging, upon which the claimed invention with a camera can be seen as an improvement. The prior art of Durve teaches a comparable device of a microfluidic chip that has been improved in the same way as the claimed invention with a camera. One of ordinary skill in the art could have applied the known “improvement” technique in the same way to the “base” device, for the predictable result of a system which could capture videos suitable for use with video data analysis, as taught by Durve et al (See Page 082003-3, column 1, paragraph 2).
With regards to claim 2, the device of claim 1 is obvious over Germano in view of Durve et al.
Germano additionally teaches;
The claimed “wherein the microconstrictions are categorized into m groups and the number of microconstrictions in each group is n, m and n being positive integers and greater than one, wherein the plurality of main channels are branched into m sub-channels, and each group of the microconstrictions is disposed in a separate respective sub-channel, and wherein the output of the sub-channels converge to a sink connecting to the outlet” has been read on the taught (See annotated Figure 7, reproduced below);
With regards to claim 3, the device of claim 1 is obvious over Germano in view of Durve et al.
Germano additionally teaches that the microconstrictions may have a width encompassing the claimed 9µm to 11µm, as read on the taught ([0029], “In some embodiments, the microfluidic channel has a minimum width dimension of 1 μm-20 μm, preferably 5-15 μm, more preferably 8-12 μm.”).
However, Germano does not explicitly disclose wherein each microconstriction has a width in a range from 9µm to 11µm, a height in a range from 25µm to 32µm, and a length in a range from 55µm to 75µm, wherein the width is measured in a first direction, the height is measured in a second direction perpendicular to the first direction, and the length is measured in a third direction perpendicular to both the first direction and the second direction, and wherein the third direction is in parallel with moving direction of the cells within the microconstrictions.
Germano does teach that the preferred dimensions of the microfluidic channel are dependent on the type of cell targeted for analysis, as read on the taught ([0019], “Preferably, the minimum width dimension of the microfluidic channel is less than the diameter of a target cell type within the fluid when in a relaxed state, such that the target cell type is deformed from its relaxed shape as it flows through the microfluidic channel…”).
Germano additionally teaches that it is desirable for cells to pass the constriction one-by-one, as read on the taught ([0029], “These channel widths are suitable to ensure that blood cells must pass through the channel one after another (and not side-by-side) whilst also ensuring that certain blood cell types must deform since these dimensions are smaller than the largest dimension of a blood cell.”).
Germano further teaches that a channel must be long enough to capture the required data according to the size of the imaging device, but not so long that the channel becomes clogged, as read on the taught ([0108], “Therefore, the channel length must be greater than the length of two adjacently positioned photodetectors 20, 60. Preferably, the channel length must not be too long that cells get stuck when deforming and passing through the microfluidic channel 10.”).
Given these teachings, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the device of Germano with the recited dimensions of the microchannel, as optimization of a results-effective variable to achieve the well-known and expected result of a device which creates a detectable deformation of a target cell as it passes through a microchannel, without undue clogging or blockages.
With regards to claim 4, the device of claim 1 is obvious over Germano in view of Durve et al.
Germano additionally teaches a plurality of bypass channels having any viable configuration, as read on the taught ([0109], “The pressure relief channels 90 […] can have any viable design… any number of pressure relief channels 90 may be included in the device 1.”; Figure 6 shows sets of pressure relief channel flanking a main channel and microconstriction.);
Germano does not explicitly disclose wherein the one or more bypass channels consist of two bypass channels that surround the plurality of main channels. However, this is held to be mere rearrangement of parts, per MPEP 2144.04(VI)(C)—see In re Japikse, 181 F.2d 1019, 86 USPQ 70 (CCPA 1950). As the specification of the instant invention does not disclose any unexpected results due to the placement of the bypass channels, and given Germano et al’s teaching that bypass channels may have any viable configuration, the limitations of claim 4 are not sufficient to define the instant invention over the prior art of Germano.
With regards to claim 5, the device of claim 1 is obvious over Germano in view of Durve et al
Germano additionally teaches;
The claimed “the end of the microconstrictions facing the outlet are connected to a sink connecting to the outlet” has been read on the taught (Please see annotated Figure 7
Germano teaches that the device may include a plurality of microfluidic channels, as read on ([0047], “…the cell counting device comprises a plurality of microfluidic channels…”);
Germano additionally teaches a plurality of bypass channels having any viable configuration, as read on the taught ([0109], “The pressure relief channels 90 […] can have any viable design… any number of pressure relief channels 90 may be included in the device 1.”; Figure 6 shows sets of pressure relief channel flanking a main channel and microconstriction.);
Germano further teaches that the microfluidic channels may be branched, as read on the taught (Please see figure 7, reproduced on page 8 of this office action. Please also see Figure 8a, which shows more distinct branching of the microfluidic channels).
Germano does not explicitly disclose wherein the plurality of main channels consist of two main channels, and the microconstrictions consist of four groups of microconstrictions, wherein each main channel is branched into two sub-channels before reaching respective group of microconstrictions such that each group of the microconstrictions is disposed within respective sub-channel, and wherein the one or more bypass channels consist of two bypass channels that surround the main channels, the sub-channels, the microconstrictions, and the sink.
However, these limitations amount to mere duplication of parts and mere rearrangement of parts. According to MPEP 2144.04(VI)(B), “mere duplication of parts has no patentable significance unless a new and unexpected result is produced.”—see In re Harza, 274 F.2d 669, 124 USPQ 378 (CCPA 1960). Likewise, according to MPEP 2144.04(VI)(C), rearrangement of parts may be prima facie obvious provided the rearrangement does not change the operation of the device—see In re Japikse, 181 F.2d 1019, 86 USPQ 70 (CCPA 1950). As the specification of the instant invention does not disclose any unexpected results due to the placement or groupings of the channels, the limitations of claim 5 are not sufficient to define the instant invention over the prior art of Germano.
With regards to claim 6, the microfluidic chip of claim 1 is obvious over Germano in view of Durve et al.
Germano et al further teaches;
The claimed “delivering means configured to deliver the cells to the microfluidic chip via the inlet such that the cells are deformed by the microconstrictions” has been read on the taught ([0082], “The flow of cells 40 through the microfluidic channel 10 may be […] generated mechanically, for example, by injecting the fluid F into the device 1 via a syringe.”);
An image capturing device “configured to collect data of the cells when the cells travel through the parallelized microconstrictions to generate collected data” has been read on the taught ([0083], “The cell counting device 1 shown in FIGS. 1a, 1b and 1c further includes a first photodetector 20 arranged to receive light 30 that has passed through the microfluidic channel 10 at a first measurement point 12.”; Photodetector 20 reads on an image capturing device.);
The claimed “the collected data being related to morphological and motional parameters of the cells” has been read on the taught ([0085], “As shown in graph 52, the interruption time T is determined by a reduction in signal intensity until it returns to its original intensity value. The processing unit is configured to distinguish the size of the cell 40 passing based on the measured interruption time T thereby determining the presence of the target cell type.”; Interruption time T reads on collected data being related to motional parameters of the cells.);
The claimed “a computing device,” and said computing device being “configured to determine the cell deformability based on the collected data received from the image capturing device” has been read on the taught ([0013], “Preferably, the processing unit of the cell counting device is configured to determine the presence of a target cell type based on both: the interruption time due to the passage of a cell across the first measurement point and the intensity variation of the signal during the interruption time.”; The processing unit reads on a computing device. See also [0085].).
However, Germano does not explicitly disclose a camera, and wherein the computing device includes a computation framework that is implemented with an artificial neural network (ANN).
The use of a camera is obvious in view of Durve et al, following the analysis of the system established in claim 1.
Durve et al further teaches;
The claimed “a computational framework that is implemented with an artificial neural network (ANN)” has been read on the taught (I. Introduction, paragraph 3, “… ML techniques have been employed to predict fluid and flow properties using digital images of the experimental setup and to estimate the size distribution of the droplets in an emulsion.”; I. Introduction, paragraph 5, “We combined the latest you only look once (YOLOv5) algorithm for droplet recognition and the DeepSORT algorithm for droplet tracking in a single tool to achieve this goal.”; ML, machine learning, reads on an artificial neural network. See also the abstract, which describes deep-learning and deep neural networks.).
“Wherein the ANN is configured to determine the cell deformability based on the collected data received from the camera” has been read on the taught (VI. Conclusion, paragraph 3, “Many quantities of interest can be computed using these two pieces of information, such as counting droplets; tracking the center of mass of the droplets as they move; and measuring droplet size deformations over time, droplet volumes, and the flux of the droplets.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system for determining cell deformability as taught by Germano with the artificial neural network as taught by Durve et al, for the benefit of expediting the cell deformation analysis (Durve et al, I. Introduction, paragraph 3, “A manual procedure of analyzing the videos frame-by-frame takes significant time and effort and would become practically unfeasible if a few thousand frames generated by a few experiments were to be analyzed. On the contrary, using a machine learning approach to automate the monitoring of microfluidic experiments is expected to expedite the analysis, save resources, and considerably enhance the observation and characterization of physical quantities.”).
With regards to claim 7, the device of claim 6 is obvious over Germano in view of Durve et al.
Germano additionally teaches;
The claimed “wherein the delivering means includes a syringe pump that pumps a fluid sample including the cells into the inlet of the microfluidic chip such that the cells flow through the plurality of main channels under pressure difference between the inlet and the outlet and are deformed when travelling through the microconstrictions” has been read on the taught ([0082], “The flow of cells 40 through the microfluidic channel 10 may be […] generated mechanically, for example, by injecting the fluid F into the device 1 via a syringe.”; A mechanically generated flow via a syringe reads on a syringe pump.).
The claim language of “that pumps a fluid sample including the cells into the inlet of the microfluidic chip such that the cells flow through the plurality of main channels under pressure difference between the inlet and the outlet and are deformed when travelling through the parallelized microconstrictions” is functional language and has been given the appropriate patentable weight. Please see MPEP 2114(II), and Hewlett-Packard Co. v. Bausch & Lomb Inc., 909 F.2d 1464, 1469, 15 USPQ2d 1525, 1528 (Fed. Cir. 1990). As Germano in view of Durve et al teaches all of the structural limitations of the apparatus as defined in claim 7, this additional limitation does not define the instant application over the prior art.
Claims 8 – 10 are rejected under 35 U.S.C. 103 as being unpatentable Germano (US 20250216315 A1) in view of Durve et al (Durve M, Tiribocchi A, Bonaccorso F, Montessori A, Lauricella M, Bogdan M, Guzowski J, Succi S. “DropTrack—Automatic droplet tracking with YOLOv5 and DeepSORT for microfluidic applications.” Physics of Fluids. 2022; 34, 082003) as applied to claim 6 above, and further in view of Lee et al (Lee K, Kim S-E, Doh J, Kim K, Chung WK. “User-friendly image-activated microfluidic cell sorting technique using an optimized fast deep learning algorithm.” Lab Chip. 2021; 21, 1798).
With regards to claim 8, the device of claim 6 is obvious over Germano in view of Durve et al.
However, this combination does not explicitly disclose wherein the computation framework is configured to automate generation of a training set by using background subtraction method for training the ANN.
In the analogous art of microfluidic devices which use artificial neural networks for image processing, Lee et al teaches;
The claimed “wherein the computation framework is configured to automate generation of a training set by using background subtraction method for training the ANN” has been read on the taught (2.7 Image Processing Algorithm, paragraph 2, “The camera (acquisition) thread continuously captures
microscopic 720 × 112 × 3-pixel images at 2000 fps, saves the image data and capture times into a queue, and transfers these to the image processing thread. When the image processing thread receives the data, the background is subtracted to leave an image containing only cells.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the microfluidic system including an ANN as taught by Germano in view of Durve with the automatic generation of a training set using a background subtraction method as taught by Lee et al. According to MPEP 2143(I)(C), the use of a known technique to improve similar devices in the same way may be prima facie obvious. In the case of the instant invention, the prior art of Germano in view of Durve et al teaches a “base” device of a system for determining cell deformability, upon which the use of a configuration for generation of a training data set can be seen as an “improvement.” The prior art of Lee et al teaches comparable microfluidic devices which have been improved by use of the particular method of background subtraction. One of ordinary skill in the art could have applied the known “improvement” technique in the same way to the microfluidic device of Germano in view of Durve et al, for the predictable result of automatically generating a set of data for cell identification and deformation measurements.
With regards to claim 9, the device of claim 8 is obvious over Germano in view of Durve et al and further in view of Lee et al.
Neither Germano nor Lee et al explicitly disclose wherein the ANN includes a cell detector for detecting positions of the cells, the cell detector being selected from a group consisting of YOLOv5, YOLOv6, and YOLOv7.
Durve et al further discloses;
The claimed “wherein the ANN includes a cell detector for detecting positions of the cells, the cell detector being selected from a group consisting of YOLOv5, YOLOv6, and YOLOv7” has been read on the taught (I. Introduction, paragraph 5, “We combined the latest you only look once (YOLOv5) algorithm for droplet recognition and the DeepSORT algorithm for droplet tracking in a single tool to achieve this goal.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the microfluidic system including an ANN as taught by Germano in view of Durve et al in view of Lee et al, with the YOLOv5 algorithm as taught by Durve et al, for the benefit of using an algorithm with superior speed and accuracy (III. Algorithms, A. You only look once (YOLO), paragraph 1, “Due to their superior speed and accuracy, the YOLO networks are deployed for environmental monitoring, quality control processing, and checking protocol compliance, to name but a few applications.”).
With regards to claim 10, the device of claim 9 is obvious over Germano in view of Durve et al and further in view of Lee et al.
Neither Germano nor Lee et al explicitly disclose wherein the ANN includes a cell tracker for tracking trajectory of the cells, the cell tracker being selected from a group consisting of Deep SORT and Strong SORT, wherein the cell detector and the cell tracker determine passage time for each of the cells that have passed through the microconstrictions.
Durve et al additionally teaches;
The claimed “wherein the ANN includes a cell tracker for tracking trajectory of the cells, the cell tracker being selected from a group consisting of Deep SORT and Strong SORT” has been read on the taught (I. Introduction, paragraph 5, “We combined the latest you only look once (YOLOv5) algorithm for droplet recognition and the DeepSORT algorithm for droplet tracking in a single tool to achieve this goal.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system including an ANN and cell detector as taught by Germano in view of Durve et al and further in view of Lee et al with the DeepSORT cell tracker as taught by Durve et al, for the benefit of using an open-source module for tracking cells between different imaging frames (Durve, III. Algorithms, B. DeepSORT, paragraph 1, “The DeepSORT algorithm is employed for tracking all detected objects between two successive frames.”; II. Experimental Setup, paragraph 2, “This paper aims to introduce state-of-the-art open-source algorithms…”).
The claim language of “wherein the cell detector and the cell tracker determine passage time for each of the cells that have passed through the microconstrictions” is functional language that has been given the appropriate patentable weight. Please see MPEP 2114(II), and Hewlett-Packard Co. v. Bausch & Lomb Inc., 909 F.2d 1464, 1469, 15 USPQ2d 1525, 1528 (Fed. Cir. 1990). As the combination of Germano in view of Durve et al in view of Lee et al teaches all of the structural limitations of the apparatus as defined in claim 10, this additional limitation does not define the instant application over the prior art.
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable Germano (US 20250216315 A1) in view of Durve et al (Durve M, Tiribocchi A, Bonaccorso F, Montessori A, Lauricella M, Bogdan M, Guzowski J, Succi S. “DropTrack—Automatic droplet tracking with YOLOv5 and DeepSORT for microfluidic applications.” Physics of Fluids. 2022; 34, 082003) in view of Lee et al (Lee K, Kim S-E, Doh J, Kim K, Chung WK. “User-friendly image-activated microfluidic cell sorting technique using an optimized fast deep learning algorithm.” Lab Chip. 2021; 21, 1798) as applied to claim 10 above, and further in view of Rosenbluth et al (Rosenbluth M, Lam W, Fletcher D. “Analyzing cell mechanics in hematologic diseases with microfluidic biophysical flow cytometry.” Lab Chip. 2008; 8, 1062).
With regards to claim 11, the device of claim 10 is over Germano in view of Durve et al and further in view of Lee et al.
However, this combination does not explicitly disclose wherein the ANN is configured to set focusing areas for determining entry time and leaving time of the cells when traveling through the microconstrictions.
In the analogous art of microfluidic devices for measuring cell deformability, Rosenbluth et al teaches;
“Wherein the entry time and leaving time of cells travelling through microconstrictions is tracked using an automated imaging system to gather data on cell deformability” has been read on the taught (Introduction, paragraph 7, “Our biophysical flow cytometry system uses automated image analysis to track large numbers of individual cells as they traverse a microfluidic capillary network and measures the effect of cell deformability and cell size on cellular transit times.”);
“Wherein focusing areas are set for determining the entry time and leaving time of cells” has been read on the taught (Experiment, Automated Transit Time Analysis, paragraph 1, “To detect cell transit time, regions of interest (ROIs) were selected for each of the microchannels and the channels leading into them”; Cell transit timers read on the entry and leaving time. The regions of interest read on focusing areas.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system including an ANN as taught by Germano in view of Durve et al in view of Lee et al with the system configured to set focusing areas as taught by Rosenbluth et al. According to MPEP 2143(I)(C), the use of a known technique to improve similar devices in the same way may be prima facie obvious. In the case of the instant invention, the prior art of Germano in view of Durve et al in view of Lee et al teaches a “base” device of a system for determining cell deformability including a neural network, upon which the use of a particular segmentation model can be seen as an “improvement.” The prior art of Rosenbluth et al teaches a “comparable” device of a microfluidic system with automated image analysis for measuring cell deformability, that has been improved in the same way by having set focusing areas. One of ordinary skill in the art could have applied the known improvement technique of setting a focusing area in the same way to the processing system including an ANN, for the predictable result of automatically calculating cell transit times over a standardized area.
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Germano (US 20250216315 A1) in view of Durve et al (Durve M, Tiribocchi A, Bonaccorso F, Montessori A, Lauricella M, Bogdan M, Guzowski J, Succi S. “DropTrack—Automatic droplet tracking with YOLOv5 and DeepSORT for microfluidic applications.” Physics of Fluids. 2022; 34, 082003) in view of Lee et al (Lee K, Kim S-E, Doh J, Kim K, Chung WK. “User-friendly image-activated microfluidic cell sorting technique using an optimized fast deep learning algorithm.” Lab Chip. 2021; 21, 1798) as applied to claim 10 above, and further in view of Jha et al (Jha D, Smedsrud PH, Riegler MO, Johansen D, De Lange T, Halvorsen P, Johansen HD. “ResUNet++: An Advanced Architecture for Medical Image Segmentation," 2019 IEEE International Symposium on Multimedia (ISM), San Diego, CA, USA, 2019, pp. 225-2255; cited on the IDS provided 03 February 2023).
With regards to claim 12, the device of claim 10 is obvious over Germano in view of Durve et al and further in view of Lee et al.
However, this combination does not teach wherein the ANN includes a segmentation model for determining the deformation index and size for each of the cells that have passed through the microconstrictions.
In the analogous art of medical image segmentation, Jha et al teaches;
“Wherein pixel-wise segmentation of a medical image is performed using a neural network” has been read on the taught (I. Introduction, paragraph 5, “We propose the novel ResUNet++ architecture, which is a semantic segmentation neural network…”; VI. Discussion, paragraph 3, “We conclude that the application of ResUNet++ should not only limited to biomedical image segmentation but could also be expanded to the natural image segmentation and other pixel-wise classification tasks…”).
One of ordinary skill in the art will recognize that an imaging device which does not move, which is positioned towards a flat image plane, and which does not change parameters between images will generate an image wherein each pixel corresponds to a given dimension in the plane of the image. As such, a pixel-wise classification of an image allows for comparison between object sizes.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the device as taught by Germano in view of Durve et al in view of Lee et al with the segmentation architecture as taught by Jha et al. According to MPEP 2143(I)(C), the use of a known technique to improve similar devices in the same way may be prima facie obvious. In the case of the instant invention, the prior art of Germano in view of Durve et al and further in view of Lee et al teaches a “base” device of a system for determining cell deformability including a neural network, upon which the use of a segmentation model can be seen as an “improvement.” The prior art of Jha et al teaches medical systems including neural networks which have been improved by use of a segmentation model. One of ordinary skill in the art could have applied the known “improvement” technique in the same way to the microfluidic device of Germano in view of Durve et al in view of Lee et al, for the predictable result of creating segmented images for further data processing.
The claim language of “for determining deformation index and size for each of the cells that have passed through the microconstrictions” is functional language and has been given the appropriate patentable weight. Please see MPEP 2114(II), and Hewlett-Packard Co. v. Bausch & Lomb Inc., 909 F.2d 1464, 1469, 15 USPQ2d 1525, 1528 (Fed. Cir. 1990). As the combination disclosed above teaches all of the structural limitations of the apparatus as defined in claim 12, this additional limitation does not define the instant application over the prior art.
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Germano (US 20250216315 A1) in view of Durve et al (Durve M, Tiribocchi A, Bonaccorso F, Montessori A, Lauricella M, Bogdan M, Guzowski J, Succi S. “DropTrack—Automatic droplet tracking with YOLOv5 and DeepSORT for microfluidic applications.” Physics of Fluids. 2022; 34, 082003) in view of Lee et al (Lee K, Kim S-E, Doh J, Kim K, Chung WK. “User-friendly image-activated microfluidic cell sorting technique using an optimized fast deep learning algorithm.” Lab Chip. 2021; 21, 1798) in view of Jha et al (Jha D, Smedsrud PH, Riegler MO, Johansen D, De Lange T, Halvorsen P, Johansen HD. “ResUNet++: An Advanced Architecture for Medical Image Segmentation," 2019 IEEE International Symposium on Multimedia (ISM), San Diego, CA, USA, 2019, pp. 225-2255; cited on the IDS provided 03 February 2023) as applied to claim 12 above, and further in view of Bento et al (Bento D, Rodrigues RO, Faustino V, Pinho D, Fernandes CS, Pereira AI, Garcia V, Miranda JM, Lima R. “Deformation of Red Blood Cells, Air Bubbles, and Droplets in Microfluidic Devices: Flow Visualizations and Measurements.” Micromachines. 2018; 9(4): 151).
With regards to claim 13, the device of claim 12 is obvious over Germano in view of Durve et al in view of Lee et al and further in view of Jha et al.
However, Germano in view of Durve et al in view of Lee et al does not teach wherein the segmentation model is ResUnet++ and wherein the deformation index is defined by (H-W)/(H+W), H being the length of a cell when the cell is within a microconstriction, W being the width of the cell when the cell is within the microconstriction.
Jha et al additionally teaches;
“Wherein pixel-wise segmentation of a medical image is performed using ResUnet++” has been read on the taught (I. Introduction, paragraph 4, “In this paper, we propose the ResUNet++ architecture for medical image segmentation.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the device as taught by Germano in view of Durve et al in view of Lee et al with the segmentation architecture as taught by Jha et al. According to MPEP 2143(I)(C), the use of a known technique to improve similar devices in the same way may be prima facie obvious. In the case of the instant invention, the prior art of Germano in view of Durve et al in view of Lee et al teaches a “base” device of a system for determining cell deformability including a neural network, upon which the use of a particular segmentation model can be seen as an “improvement.” The prior art of Jha et al teaches medical systems including neural networks which have been improved by use of the particular segmentation model. One of ordinary skill in the art could have applied the known “improvement” technique in the same way to the microfluidic device of Germano in view of Durve et al in view of Lee et al, for the predictable result of creating segmented images for further data processing.
However, this combination does not teach wherein the deformation index is defined by (H-W)/(H+W), H being the length of a cell when the cell is within a microconstriction, W being the width of the cell when the cell is within the microconstriction.
In the analogous art of cell deformation measurements, Bento et al teaches;
The claimed “wherein the deformation index is defined by (H-W)/(H+W), H being the length of a cell when the cell is within a microconstriction, W being the width of the cell when the cell is within the microconstriction” has been read on the taught (2. Deformation of RBCs in Microfluidic Devices, Paragraph 4, “The deformation index (DI), also known as elongation index, most of the times is calculated by (X - Y)/(X + Y) where X and Y represent the major and minor lengths of the ellipse, respectively (see Figure 2).”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the device as taught by Germano in view of Durve et al in view of Lee et al in view of Jha et al with the deformation index as taught by Bento et al. According to MPEP 2143(I)(C), the use of a known technique to improve similar devices in the same way may be prima facie obvious. In the case of the instant invention, the prior art of Germano in view of Durve et al in view of Lee et al in view of Jha et al teaches a “base” device of a system for determining cell deformability, upon which the use of a particular deformation index formula can be seen as an “improvement.” The prior art of Bento et al teaches comparable microfluidic devices which have been improved by use of the particular deformation index formula. One of ordinary skill in the art could have applied the known “improvement” technique in the same way to the microfluidic device of Germano in view of Durve et al in view of Lee et al and further in view of Jha et al, for the predictable result of calculating the cell deformability using a classically accepted method.
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 ALISON CLAIRE GERHARD whose telephone number is (571)270-0945. The examiner can normally be reached M-F, 9:00 - 5:30pm EST.
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, Lyle Alexander can be reached at (571) 272-1254. 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.
/ALISON CLAIRE GERHARD/Examiner, Art Unit 1797 /LYLE ALEXANDER/Supervisory Patent Examiner, Art Unit 1797
Prosecution Insights