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 .
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)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(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.
Claim(s) 1-3, 6, and 11 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Quillent, A., Bismuth, V.J., Bloch, I., Kervazo, C. & Ladjal, S.. (2024). A deep learning method trained on synthetic data for digital breast tomosynthesis reconstruction. Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 227:1813-1825 Available from https://proceedings.mlr.press/v227/quillent24a.html..
Regarding Claim 1: Quillent discloses a method for providing quasi-isotropic images of an object, the method comprising the steps of:
providing one or more projection images obtained of the object within an angular range of less than 180 degrees relative to the object (page 1814, paragraph 2: “In this work, we tackle limited-angle sparse-view DBT reconstruction. Specifically, we propose a deep learning reconstruction method for a realistic DBT device with 9 projections acquired over a 25° angular range.”);
reconstructing a quasi-isotropic volume from the one or more projection images with an artefact-reduction and resolution enhancement artificial intelligence (abstract: “this procedure is composed of two steps: a classic reconstruction algorithm is first applied on normalised projections, then a deep neural network is tasked with erasing the artefacts present in the obtained volumes”; page 1817: “Reconstruction DBT volumes are reconstructed from normalized projections thanks to a FBP-based algorithm. The resolution used to perform this reconstruction is set on all three axes to the detector pixel size (i.e., 100 µm), resulting in isotropic voxels.”); and
generating one or more quasi-isotropic images from the quasi-isotropic volume (Figs. 6 and 7).
Regarding Claim 2: Quillent discloses the method of claim 1, wherein the one or more quasi-isotropic images comprises at least one plane orthogonal to the detector or containing any line between a detector and a focal point of a radiation source of an imaging system utilized for obtaining the one or more projection images (Fig. 6).
Regarding Claim 3: Quillent discloses the method of claim 2, wherein the one or more quasi-isotropic images comprises at least one of a plane, a 2D image, a slab or a 2D synthetic image, and combinations thereof (Figs. 6 and 7).
Regarding Claim 6: Quillent discloses the method of claim 1, wherein the object is a breast (Figs. 6 and 7) and wherein the method further comprising the step of classifying a tissue type for individual voxels in the quasi-isotropic volume (Fig. 2 description, page 1819: “Grey areas correspond to adipose tissues, white ones to glandular, and black ones
to the zero-padding.”).
Regarding Claim 11: Quillent discloses the method of claim 1, further comprising the steps of:
generating an uncertainty score for each voxel in the one or more quasi-isotropic images (heatmaps in fig. 4); and
displaying the uncertainty scores along with the one or more quasi-isotropic images (heatmaps in fig. 4)
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) 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Quillent in view of Bernard (US 20190325573 A1).
Regarding Claim 4: Quillent discloses the method of claim 2, wherein further comprising the steps of:
generating a standard reconstruction volume from the one or more projection images (abstract: “this procedure is composed of two steps: a classic reconstruction algorithm is first applied on normalised projections, then a deep neural network is tasked with erasing the artefacts present in the obtained volumes”); and
generating one or more standard images from the standard reconstruction volume; (Fig. 1).
Quillent fails to teach:
registering the one or more quasi-isotropic images to the standard reconstruction volume; and
d. synchronizing movement of a cursor in each of the one or more quasi-isotropic images and the one or more standard images.
Bernard teaches registering synthetic 2D images to a 3D volume and synchronizing movement of a cursor in each of the one or more images and the one or more standard images ([0054]; Fig. 2).
It would have been obvious to someone ordinary skill in the art to have modified the teachings of Quillent to incorporate the teachings of Bernard and register the one or more quasi-isotropic images to the standard reconstruction volume and synchronize movement of a cursor in each of the one or more quasi-isotropic images and the one or more standard images. One would be motivated to make such a modification on the basis of enabling direct validation of the enhancement and artefact reduction and increasing confidence in diagnosis.
Claim(s) 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Quillent in view of Vancamberg '568 (US 20160217568 A1).
Regarding Claim 5: Quillent discloses the method of claim 3, but fails to teach further comprising the step of employing the one or more quasi-isotropic images in a biopsy procedure.
However, employing DBT in guided biopsies is well known in the art, as shown by Vancamberg ‘568, [0010]-[0011].
Therefore, it would have been obvious to someone of ordinary skill in the art to have employed the reconstructed quasi-isotropic images of Quillent in a guided biopsy procedure. One would be motivated to do so on the basis of enabling more efficient and more accurate biopsies.
Claim(s) 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Quillent in view of Jerebko (US 20140348404 A1).
Regarding Claim 7: Quillent discloses the method of claim 6, but fails to teach further comprising the step of numerically decompressing the quasi-isotropic volume into a digital uncompressed volume.
Jerebko teaches numerically decompressing DBT images (Figs. 4-8, [0067-0068]).
It would have been obvious to someone of ordinary skill in the art to have modified Quillent to incorporate the teachings of Jerebko and numerically decompress the quasi-isotropic volume into a digital uncompressed volume. One would be motivated to make such a modification on the basis of rendering how tissue behaves without mechanical pressure and enabling better diagnostics.
Claim(s) 8 and 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Quillent in view of Jerebko, in further view of Boone (US 20080187095 A1).
Regarding Claim 8: Quillent in view of Jerebko discloses the method of claim 7, but both fail to teach further comprising the step of manipulating the digital uncompressed breast to form additional views of the breast.
Boone teaches manipulating an uncompressed volume to form additional (compressed) views of the breast (Fig. 4).
It would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have applied Boone’s techniques to the uncompressed volume of Jerebko. One would be motivated to make such a modification on the basis of improving the visualization and reducing additional imaging.
Regarding Claim 9: Quillent in view of Jerebko, in further view of Boone, discloses the method of claim 8, wherein the step of manipulating the digital uncompressed breast comprises forming a digital compressed view of the breast (Boone: Fig. 4).
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Quillent in view of Jerebko, in further view of Bernard.
Regarding Claim 10: Quillent in view of Jerebko discloses the method of claim 7, further comprising the steps of:
generating a standard reconstruction volume from the one or more projection images (Jerebko: [0004]).
Both fail to teach:
registering the digital uncompressed volume with the standard reconstructed volume.
Bernard teaches registering synthetic volume to an imaged volume ([0054]; Fig. 2). It would have been obvious to register the digital uncompressed volume with the standard reconstructed volume in order to facilitate comparison and spatial correspondence between the two volumes.
Claim(s) 12-14 and 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Vancamberg ‘924(US 20250176924 A1) in view of Quillent.
Regarding Claim 12: Vancamberg ‘924 discloses a mammography imaging system comprising: method for providing artefact-reduced images of a breast, the method comprising the steps of:
providing a mammography imaging system comprising:
a radiation source operable at to emit radiation (Fig. 1, 16),
a detector alignable with the radiation source, the detector having a surface on which the breast to be imaged is adapted to be positioned (18);
a controller (32) operably connected to the radiation source and the detector to control the operation of the radiation source and detector to generate image data of the breast in an imaging procedure performed by the imaging system, the controller including a central processing unit and interconnected database containing processor-executable instructions for processing the image data from the detector to create one or more projection images,
a display operably connected to the controller for presenting information to a user (38); and
a user interface operably connected to the controller to enable user input to the controller (44),
placing the breast on the surface of the detector (Fig. 2);
operating the radiation source over a limited angular range relative to the breast to obtain image data (Fig. 2);
processing the image data to form the one or more projection images (Fig. 9).
Vancamberg ‘924 fails to teach a method for providing artefact-reduced images of a breast, the method comprising the steps of:
reconstructing a quasi-isotropic volume from the one or more projection images with an artefact-reduction and resolution enhancement artificial intelligence; and
generating one or more quasi-isotropic images from the quasi-isotropic volume.
Quillent teaches:
reconstructing a quasi-isotropic volume from the one or more projection images with an artefact-reduction and resolution enhancement artificial intelligence (abstract: “this procedure is composed of two steps: a classic reconstruction algorithm is first applied on normalised projections, then a deep neural network is tasked with erasing the artefacts present in the obtained volumes”; page 1817: “Reconstruction DBT volumes are reconstructed from normalized projections thanks to a FBP-based algorithm. The resolution used to perform this reconstruction is set on all three axes to the detector pixel size (i.e., 100 µm), resulting in isotropic voxels.”); and
generating one or more quasi-isotropic images from the quasi-isotropic volume (Figs. 6 and 7).
It would have been obvious to someone of ordinary skill in the art to have modified Vancamberg ‘924 to incorporate the image processing techniques of Quillent. One would be motivated to make such a modification on the basis of reducing artifacts in images of a breast.
Regarding Claim 13: Vancamberg ‘924 in view of Quillent discloses the method of claim 12, wherein the mammography imaging system includes a compression paddle moveable relative to the detector surface (Vancamberg ‘924: Figs. 1 and 2), and wherein the method further comprises the steps of:
compressing the breast between the compression plate and the surface of the detector at a first compression (Vancamberg ‘924: Fig. 9, CC image 400);
operating the radiation source over a limited angular range relative to the breast to generate a first set of projection images of the breast (Vancamberg ‘924: Fig. 9, 400);
applying a resolution enhancement artificial intelligence to the first set of one or more projection images to generate a first quasi-isotropic volume (Quillent: abstract: “this procedure is composed of two steps: a classic reconstruction algorithm is first applied on normalised projections, then a deep neural network is tasked with erasing the artefacts present in the obtained volumes”; page 1817: “Reconstruction DBT volumes are reconstructed from normalized projections thanks to a FBP-based algorithm. The resolution used to perform this reconstruction is set on all three axes to the detector pixel size (i.e., 100 µm), resulting in isotropic voxels.”);
generating one or more first quasi-isotropic images from the first quasi-isotropic volume (Quillent: Figs. 6 and 7);
compressing the breast between the compression plate and the surface of the detector at a second compression (Vancamberg ‘924: Fig. 9, MLO image 402);
operating the radiation source over a limited angular range relative to the breast to generate a second set of projection images of the breast (Vancamberg ‘924: Fig. 9, MLO image 402);
applying a resolution enhancement artificial intelligence to the second standard reconstructed volume to form a second quasi-isotropic volume (Quillent: abstract: “this procedure is composed of two steps: a classic reconstruction algorithm is first applied on normalised projections, then a deep neural network is tasked with erasing the artefacts present in the obtained volumes”; page 1817: “Reconstruction DBT volumes are reconstructed from normalized projections thanks to a FBP-based algorithm. The resolution used to perform this reconstruction is set on all three axes to the detector pixel size (i.e., 100 µm), resulting in isotropic voxels.”);
generating one or more second quasi-isotropic images from the second quasi-isotropic volume (Quillent: Figs. 6 and 7); and
determining a property of tissue forming a lesion in the breast from a comparison of the one or more first quasi-isotropic images with the one or more second quasi-isotropic images to assess mechanical properties of the lesions within the imaged breast (Vancamberg ‘924: Fig. 9).
Regarding Claim 14: Vancamberg ‘924 in view of Quillent discloses the method of claim 12, further comprising the step of classifying a tissue type for individual voxels in the quasi-isotropic volume (Fig. 2 description, page 1819: “Grey areas correspond to adipose tissues, white ones to glandular, and black ones to the zero-padding.”).
Regarding Claim 18: Vancamberg ‘924 discloses a mammography imaging system comprising:
a radiation source operable at to emit radiation (Fig. 1, 16),
a detector alignable with the radiation source, the detector having a surface on which a breast to be imaged is adapted to be positioned (18);
a controller operably connected to the radiation source and the detector to control the operation of the radiation source and detector to generate image data of the breast in an imaging procedure performed by the imaging system, the controller including a central processing unit and interconnected database containing processor-executable instructions for processing the image data from the detector to create one or more projection images of the breast (32),
a display operably connected to the controller for presenting information to a user (38); and
a user interface operably connected to the controller to enable user input to the controller (44).
Vancamberg ‘924 fails to teach:
wherein the controller is configured to apply a resolution enhancement artificial intelligence to the one or more projection images to reconstruct a quasi-isotropic volume of the breast, and to generate one more one or more quasi-isotropic images from the quasi-isotropic volume.
Quillent teaches:
wherein the controller is configured to apply a resolution enhancement artificial intelligence to the one or more projection images to reconstruct a quasi-isotropic volume of the breast, and to generate one more one or more quasi-isotropic images from the quasi-isotropic volume (abstract: “this procedure is composed of two steps: a classic reconstruction algorithm is first applied on normalised projections, then a deep neural network is tasked with erasing the artefacts present in the obtained volumes”; page 1817: “Reconstruction DBT volumes are reconstructed from normalized projections thanks to a FBP-based algorithm. The resolution used to perform this reconstruction is set on all three axes to the detector pixel size (i.e., 100 µm), resulting in isotropic voxels.”; Figs. 6 and 7).
It would have been obvious to someone of ordinary skill in the art to have modified Vancamberg ‘924 to incorporate the image processing techniques of Quillent. One would be motivated to make such a modification on the basis of reducing artifacts in images of a breast.
Regarding Claim 19: Vancamberg ‘924 in view of Quillent discloses the imaging system of claim 18, wherein the imaging system is a mammography imaging system including a compression paddle (Vancamberg ‘924: Fig. 2) moveable relative to the detector surface by the controller to compress a breast therebetween, and wherein the controller is configured to determine a property of tissue forming a lesion in the breast from a comparison of one or more first quasi-isotropic images obtained at a first compression (Vancamberg ‘924: Fig. 9, CC image 400) with the one or more second quasi-isotropic images obtained at a second compression (Vancamberg ‘924: Fig. 9, MLO image 402) to enable differentiation of tissues forming the lesions from other breast tissue as a result of determining mechanical properties of the tissue within the imaged breast.
Regarding Claim 20: Vancamberg ‘924 in view of Quillent discloses the imaging system of claim 18, wherein the controller is further configured to classify a tissue type for individual voxels in the quasi-isotropic volume (Quillent: Fig. 2 description, page 1819: “Grey areas correspond to adipose tissues, white ones to glandular, and black ones to the zero-padding.”).
Claim(s) 15, 16, and 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Vancamberg ‘924 in view of Quillent, in further view of Jerebko.
Regarding Claim 15: Vancamberg ‘924 in view of Quillent discloses the method of claim 14, but both fail to teach further comprising the step of decompressing the quasi-isotropic volume into a digital uncompressed volume.
Jerebko teaches numerically decompressing DBT images (Figs. 4-8, [0067-0068]).
It would have been obvious to someone of ordinary skill in the art to have modified the combination of Vancamberg ‘924 and Quillent to incorporate the teachings of Jerebko and numerically decompress the quasi-isotropic volume into a digital uncompressed volume. One would be motivated to make such a modification on the basis of rendering how tissue behaves without mechanical pressure and enabling better diagnostics.
Regarding Claim 16: Vancamberg ‘924 in view of Quillent, in further view of Jerebko discloses the method of claim 15, further comprising the step of numerically decompressing the quasi-isotropic volume into a digital uncompressed volume (Jerebko: Figs. 4-8, [0067-0068]).
Regarding Claim 21: Vancamberg ‘924 in view of Quillent discloses the imaging system of claim 20, but both fail to teach wherein the controller is further configured to numerically decompress the quasi-isotropic volume into a digital uncompressed volume.
Jerebko teaches numerically decompressing DBT images (Figs. 4-8, [0067-0068]).
It would have been obvious to someone of ordinary skill in the art to have modified the combination of Vancamberg ‘924 and Quillent to incorporate the teachings of Jerebko and numerically decompress the quasi-isotropic volume into a digital uncompressed volume. One would be motivated to make such a modification on the basis of rendering how tissue behaves without mechanical pressure and enabling better diagnostics.
Claim(s) 17 and 22 is/are rejected under 35 U.S.C. 103 as being unpatentable over Vancamberg ‘924 in view of Quillent, in further view of Bernard.
Regarding Claim 17: Vancamberg ‘924 in view of Quillent discloses the method of claim 12, further comprising the steps of:
generating a standard reconstruction volume from the one or more projection images (abstract: “this procedure is composed of two steps: a classic reconstruction algorithm is first applied on normalised projections, then a deep neural network is tasked with erasing the artefacts present in the obtained volumes”); and
generating one or more standard images from the standard reconstruction volume (Fig. 1).
Vancamberg ‘924 and Quillent fail to teach:
registering the one or more quasi-isotropic images to the standard reconstruction volume; and
synchronizing movement of a cursor in each of the one or more quasi-isotropic images and the one or more standard reconstruction images.
Bernard teaches registering synthetic 2D images to a 3D volume and synchronizing movement of a cursor in each of the one or more images and the one or more standard images ([0054]; Fig. 2).
It would have been obvious to someone ordinary skill in the art to have modified the combination of Vancamberg ‘924 and Quillent to incorporate the teachings of Bernard and register the one or more quasi-isotropic images to the standard reconstruction volume and synchronize movement of a cursor in each of the one or more quasi-isotropic images and the one or more standard images. One would be motivated to make such a modification on the basis of enabling direct validation of the enhancement and artefact reduction and increasing confidence in diagnosis.
Regarding Claim 22: Vancamberg ‘924 in view of Quillent discloses the imaging system of claim 20, wherein the controller is further configured to reconstruct a standard reconstruction volume from the one or more projection images (abstract: “this procedure is composed of two steps: a classic reconstruction algorithm is first applied on normalised projections, then a deep neural network is tasked with erasing the artefacts present in the obtained volumes”), to generate one or more standard reconstruction images from the standard reconstruction volume (Fig. 1).
Vancamberg ‘924 and Quillent fail to teach to register the one or more quasi-isotropic images to the one or more standard reconstruction images and to synchronize movement of a cursor in each of the one or more quasi-isotropic images and the one or more standard reconstruction images.
Bernard teaches registering synthetic 2D images to a 3D volume and synchronizing movement of a cursor in each of the one or more images and the one or more standard images ([0054]; Fig. 2).
It would have been obvious to someone ordinary skill in the art to have modified the combination of Vancamberg ‘924 and Quillent to incorporate the teachings of Bernard and register the one or more quasi-isotropic images to the standard reconstruction volume and synchronize movement of a cursor in each of the one or more quasi-isotropic images and the one or more standard images. One would be motivated to make such a modification on the basis of enabling direct validation of the enhancement and artefact reduction and increasing confidence in diagnosis.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MIYA DOWNING whose telephone number is (703)756-1840. The examiner can normally be reached Monday - Friday 8:00 AM - 5:00 PM ET.
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, David Makiya can be reached at (571) 272-2273. 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.
/MIYA DOWNING/Examiner, Art Unit 2884
/DAVID J MAKIYA/Supervisory Patent Examiner, Art Unit 2884
Prosecution Insights