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 .
Election/Restrictions
Applicant’s election without traverse of Claim 1-9 and 16-20 in the reply filed on 05/11/2026 is acknowledged.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 03/15/2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-5, 16-18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Meyer et al. (WO 2020219915 A1) in view of Fischl et al. US PG-Pub(US 20150289779 A1).
Regarding Claim 1, Meyer teaches a machine for detecting a lesion in a brain magnetic resonance imaging (MRI) image(See ¶[0072], ¶[0084], and ¶[0089]), the machine comprising: at least one processor configured to execute instructions(¶[0028] discloses “the system includes: one or more processors”); at least one memory in communication with the processor(¶[0028] discloses “a memory device coupled to the one or more processors”), the memory being configured to store the instructions and be accessible by the processor to execute the instructions, wherein the instructions are operable to process the image(¶[0028], “storing instructions which, when executed by the one or more processors, cause the system to perform functions”, memory is coupled to the processor to process MR images.); a convolutional neural network in communication with the processor(¶[0028] discloses a CNN in communication with the processor.), the neural network comprising: an outer encoding layer configured to receive the image and apply an outer digital filter to the image to produce an outer filtered image map with large- scale features(¶[0077], “the U-DCNN 600 to include two layers of encoding 660, 670, and two layers of decoding 680, 690. In some embodiments the input image 625 is chosen as random values sampled from a normal distribution similar to a generative adversarial network, as in [4], and in some embodiments the first values of the U-DCNN’ s 600 weights and biases may be assigned randomly. In some embodiments, a Gaussian filter is applied to a noisy target image as the input. The Gaussian filter may be a Gaussian filter with a large standard deviation. The noisy input images 625 may also be down sampled by a selected factor prior to running iterations of the U- DCNN 600. For brain MRI, the filtered image can provide information about overall brain structure and a good estimation of regional intensity values. Therefore, the generation process may focus more on reconstructing the fine details missed from the filtered image and allows a faster convergence.”, ¶[0077] discloses the CNN has two layers of encoding 660 and 670 which is an inner and outer layer and the outer layer appears to disclose processing the image through a gaussian filter to produce a map with large scale features.);at least one inner encoding layer to receive both the image via a skip connection and the outer filtered image and apply an inner digital filter distinct from the outer digital filter to the outer filtered image to produce an inner filtered image map with small scale features, while retaining a set of original image features from the image (¶[0078], “The final connection layer 655 can perform convolutions on the input image and concatenate the results to the final set of features for output prediction. According to some embodiments of the present disclosure, the network can leverage information from the filtered input to correct errors caused by the reconstruction process. The final connection layer 655 may also help to make the range and distribution of predicted intensity values similar to the input. Additional embodiments incorporate more than one input to the U-DCNN 600, such as additional inputs configured from high signal to noise ratio image data gathered from selected acquisition sequences.”[0043] “FIG. 6 illustrates the network structure for an embodiment of an Unsupervised Deep Convolutional Neural Network (U-DCNN) with N layers. The values nE, nD and nS correspond to the number of features for the encoding, decoding and skip-connections respectively. K refers to kernel size.”, ¶[0078] discloses processing the image and applying the image to a filter to produce a image with small scale features and retaining the original features from the image. ¶[0043] discloses the encoding layer have a skip connection.);at least one inner decoding layer to receive the inner filtered image map and apply an inner inverse convolution to the inner filtered image map to produce an inner decoded image map comprising a set of inner image features extracted from the image by the inner encoding layer and an outer decoding layer to receive the inner decoded image map and apply an outer inverse convolution to the inner decoded image map to produce an outer decoded image map comprising a set of outer image features extracted from the image by the outer encoding layer ([0073] “As depicted in FIG. 6, embodiments of the present disclosure include a U-Net-like architecture. The encoding path can capture image characteristics at various resolutions and the decoding path can generate the output image 650 based on those condensed image characteristics. For each denoising case, the network 600 can be given an input image 625 and fitted to the raw noisy MRI, which can be the target image used for calculating network loss.”, ¶[0073] discloses decoding the encoded image to generate an output image. ¶[0077]-¶[0078] disclose the U-DCNN 600 to include two layers of encoding 660, 670, and two layers of decoding 680, 690 ); ; and a user interface, wherein the instructions, when executed at the processor, are further operable to display the set of outer image features at the user interface.(¶[0079] Embodiments of the present disclosure may be implemented as a system with one or more processors and a memory device coupled to the one or more processors, with the memory device storing instructions which can be executed by the one or more processors to cause the system to perform denoising using the U-DCNN 600. The system can include a display for viewing the denoised MR image 705 data for each iteration 605, and a user interface 158 that allows a user to select the number of iterations the system will perform, ¶[0079] disclose a user interface to display output images onto.)
Meyer does not explicitly teach detecting a focal cortical dysplasia lesion in a brain magnetic resonance imaging (MRI) image
Fischl teaches detecting a focal cortical dysplasia lesion in a brain magnetic resonance imaging (MRI) image (¶[0038] “As will be described, using an MRI system such as the MRI system 100 described above, one aspect of the present invention provides a method for detecting and localizing focal cortical dysplasias (“FCDs”).”, ¶[0038] discloses detecting focal cortical dysplasia in MRI images.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the claimed invention as taught by Meyer with Fischl in order to determine FCD in MRI images. One skilled in the art would have been motivated to modify Meyer in this manner in order for automated detection of focal cortical dysplasias in medical images. (Fischl, ¶[0038])
Regarding Claim 2, the combination of Meyer and Fischl teach the machine of claim 1, where Meyer further teaches wherein the instructions, when executed at the processor, are operable to sequence the image into a three-dimensional array comprising a plurality of voxels(¶[0083]-¶[0086] disclose sequencing the image into a 3d array with voxels.).
Regarding Claim 3, the combination of Meyer and Fischl teach the machine of claim 2, where Meyer further teaches wherein the instructions, when executed at the processor, are further operable to convert the three-dimensional array into a plurality of two-dimensional array slices(¶[0083]-¶[0086] disclose converting the 3d array into 2d slices.).
Regarding Claim 4, the combination of Meyer and Fischl teach the machine of claim 3, where Meyer further teaches wherein the instructions, when executed at the processor, are further operable to process the three-dimensional array and the two- dimensional array slices simultaneously. (¶[0083] disclose processing the 3d and 2d slices of the MRI brain images during acquisition time.)
Regarding Claim 5, the combination of Meyer and Fischl teach the machine of claim 4, where Fischl further teaches wherein the instructions, when executed at the processor, are further operable to produce a probability map. (¶[0059]-¶[0064] discloses determining a probability of a lesion being present in the image.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the claimed invention as taught by Meyer with Fischl in order to generate a probability map for the lesion. One skilled in the art would have been motivated to modify Meyer in this manner in order for automated detection of focal cortical dysplasias in medical images. (Fischl, ¶[0038])
Regarding Claim 16, Meyer teaches a method for detecting a lesion in an image(See ¶[0072], ¶[0084], and ¶[0089]), the method comprising the steps of: at a first encoding layer of a convolutional neural network, applying a first digital filter to the image to produce a large-scale filtered image map(¶[0077], “the U-DCNN 600 to include two layers of encoding 660, 670, and two layers of decoding 680, 690. In some embodiments the input image 625 is chosen as random values sampled from a normal distribution similar to a generative adversarial network, as in [4], and in some embodiments the first values of the U-DCNN’ s 600 weights and biases may be assigned randomly. In some embodiments, a Gaussian filter is applied to a noisy target image as the input. The Gaussian filter may be a Gaussian filter with a large standard deviation. The noisy input images 625 may also be down sampled by a selected factor prior to running iterations of the U- DCNN 600. For brain MRI, the filtered image can provide information about overall brain structure and a good estimation of regional intensity values. Therefore, the generation process may focus more on reconstructing the fine details missed from the filtered image and allows a faster convergence.”, ¶[0077] discloses the CNN has two layers of encoding 660 and 670 which is an inner and outer layer and the outer layer appears to disclose processing the image through a gaussian filter to produce a map with large scale features.); at a second encoding layer of the convolutional neural network, applying a small-scale filter to both the image and the large-scale filtered image map to produce a small-scale filtered image map with small scale features that retains a set of original image features from the image(¶[0078], “The final connection layer 655 can perform convolutions on the input image and concatenate the results to the final set of features for output prediction. According to some embodiments of the present disclosure, the network can leverage information from the filtered input to correct errors caused by the reconstruction process. The final connection layer 655 may also help to make the range and distribution of predicted intensity values similar to the input. Additional embodiments incorporate more than one input to the U-DCNN 600, such as additional inputs configured from high signal to noise ratio image data gathered from selected acquisition sequences.”[0043] “FIG. 6 illustrates the network structure for an embodiment of an Unsupervised Deep Convolutional Neural Network (U-DCNN) with N layers. The values nE, nD and nS correspond to the number of features for the encoding, decoding and skip-connections respectively. K refers to kernel size.”, ¶[0078] discloses processing the image and applying the image to a filter to produce a image with small scale features and retaining the original features from the image. ¶[0043] discloses the encoding layer have a skip connection.); at a first decoding layer, applying a first inverse convolution to the small-scale filtered image map to produce a first decoded image map comprising small-scale image features extracted from the image by the second encoding layer; at a second decoding layer, applying a second inverse convolution to the first decoded image map to produce a second decoded image map comprising a second set of image features extracted from the image by the first encoding layer([0073] “As depicted in FIG. 6, embodiments of the present disclosure include a U-Net-like architecture. The encoding path can capture image characteristics at various resolutions and the decoding path can generate the output image 650 based on those condensed image characteristics. For each denoising case, the network 600 can be given an input image 625 and fitted to the raw noisy MRI, which can be the target image used for calculating network loss.”, ¶[0073] discloses decoding the encoded image to generate multiple output images. ¶[0077]-¶[0078] disclose the U-DCNN 600 to include two layers of encoding 660, 670, and two layers of decoding 680, 690 ); ; and at a user interface, displaying the second decoded image map.(¶[0079] Embodiments of the present disclosure may be implemented as a system with one or more processors and a memory device coupled to the one or more processors, with the memory device storing instructions which can be executed by the one or more processors to cause the system to perform denoising using the U-DCNN 600. The system can include a display for viewing the denoised MR image 705 data for each iteration 605, and a user interface 158 that allows a user to select the number of iterations the system will perform, ¶[0079] disclose a user interface to display output images onto.)
Meyer does not explicitly teach detecting a focal cortical dysplasia lesion in a brain magnetic resonance imaging (MRI) image
Fischl teaches detecting a focal cortical dysplasia lesion in a brain magnetic resonance imaging (MRI) image (¶[0038] “As will be described, using an MRI system such as the MRI system 100 described above, one aspect of the present invention provides a method for detecting and localizing focal cortical dysplasias (“FCDs”).”, ¶[0038] discloses detecting focal cortical dysplasia in MRI images.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the claimed invention as taught by Meyer with Fischl in order to determine FCD in MRI images. One skilled in the art would have been motivated to modify Meyer in this manner in order for automated detection of focal cortical dysplasias in medical images. (Fischl, ¶[0038])
Regarding Claim 17, the combination of Meyer and Fischl teach the method of claim 16, further comprising the step of converting the image into a voxel array comprising a plurality of voxels before the step of applying the first digital filter (¶[0077]-¶[0078] and ¶[0083]-¶[0086] disclose converting the image into voxel arrays.)
Regarding Claim 18, the combination of Meyer and Fischl teach the method of claim 17, further comprising the step of converting the image into a slice array comprising a plurality of two-dimensional image slices before the step of applying the first digital filter. (¶[0083]-¶[0086] disclose converting the 3d array into 2d slices.).
Regarding Claim 20, the combination of Meyer and Fischl teach the method of claim 16, further comprising the step of applying a boundary algorithm to the image prior to the step of applying the first digital filter, wherein the step of applying the boundary algorithm comprises the step of removing any outer edges of the image comprising at least one of skin, bone, and cerebrospinal fluid. (¶[0075] discloses removing noise from edges of the image and ¶[0050] discloses the region of interest are specific organs, tissues or fluids of the subject.)
Claims 6-9 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Meyer et al. (WO 2020219915 A1) in view of Fischl et al. US PG-Pub(US 20150289779 A1) in view of Carnell et al. US PG-Pub(US 20220222816 A1).
Regarding Claim 6, while the combination of Meyer and Fischl teach the machine of claim 5, they do not explicitly teach wherein the instructions, when executed at the processor, are further operable to generate an overlay from the probability map and the image.
Carnell teaches wherein the instructions, when executed at the processor, are further operable to generate an overlay from the probability map and the image ([0092] “The image display (105) can be configured to display one more output images—e.g., output images 107a and 107b shown in FIG. 6, which each include an overlay 108 of the data of the lesion probability map generator over the normalized MRI image data set 109.”, ¶[0092] disclose the probability map is overlayed over a normalized MRI image set.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the claimed invention as taught by Meyer and Fischl with Carnell in order to generate an overlay based on probability map and an image. One skilled in the art would have been motivated to modify Meyer and Fischl in this manner in order for identification of lesions in MRI image. (Carnell, ¶[0001])
Regarding Claim 7, the combination of Meyer, Fischl and Carnell teach the machine of claim 6, where Carnell further teaches wherein the instructions, when executed at the processor, are operable to compute a probability score for each of a plurality of pixels in the image ([0010] “a voxel classifier (103) for calculating for each of said input voxels one or more class probabilities of such voxel to contain a lesion of a particular type or being a non-lesion, wherein such class probabilities are calculated using a computational model; [0011] a lesion probability map generator (104) for receiving the data produced by the voxel classifier (103) and producing probability intensity map for each of lesion types, in which one or more areas classified as lesion are highlighted,” this section of the prior art discloses using a classifier to determine the probability of a lesion in the image.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the claimed invention as taught by Meyer and Fischl with Carnell in order to determine a probability score in the image. One skilled in the art would have been motivated to modify Meyer and Fischl in this manner in order for identification of lesions in MRI image. (Carnell, ¶[0001])
Regarding Claim 8, the combination of Meyer, Fischl and Carnell teach The machine of claim 7, where Carnell further teaches wherein the instructions, when executed at the processor, are operable to apply the probability score to produce the overlay. (¶[0010]-¶[0012] disclose determining a probability of a lesion in the MRI image and outputting the lesion probability map based on the probability value)
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the claimed invention as taught by Meyer and Fischl with Carnell in order to determine a probability score in the image for generating an overlay. One skilled in the art would have been motivated to modify Meyer and Fischl in this manner in order for identification of lesions in MRI image. (Carnell, ¶[0001])
Regarding Claim 9, the combination of Meyer, Fischl and Carnell teach the machine of claim 8, Meyer further teaches wherein the instructions, when executed at the processor, are further operable to apply a boundary algorithm to the image prior to sending the image to the convolutional neural network to remove outer edges of the image comprising at least one of skin, bone, and cerebrospinal fluid. (¶[0075] discloses removing noise from edges of the image and ¶[0050] discloses the region of interest are specific organs, tissues or fluids of the subject.)
Regarding Claim 19, while the combination of Meyer and Fischl teach the method of claim 18, they do not explicitly teach further comprising the step of applying a threshold to the second decoded image map to produce an overlay.
Carnell teaches further comprising the step of applying a threshold to the second decoded image map to produce an overlay. (¶[0090] disclose applying a threshold to remove values in a probability map that aren’t related to the lesion and ¶[0091] discloses displaying the produced probability map on a display device.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the claimed invention as taught by Meyer and Fischl with Carnell in order to determine a probability score in the image for generating an overlay. One skilled in the art would have been motivated to modify Meyer and Fischl in this manner in order for identification of lesions in MRI image. (Carnell, ¶[0001])
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HAN D HOANG whose telephone number is (571)272-4344. The examiner can normally be reached Monday-Friday 8-5.
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, JOHN M VILLECCO can be reached at 571-272-7319. 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.
/HAN HOANG/Primary Examiner, Art Unit 2661
Prosecution Insights