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 .
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.
Response to Arguments
This is in response to applicant’s amendment/response filed on 03/26/2026, which have been entered and made of record.
Applicant’s arguments regarding claim rejections under 103 have been fully considered but they are not persuasive.
Applicant argues However, whether or not Lamash's spectral points of interest qualify as anatomical reference points, or whether Lamash teaches generating a contrast map based on the contrast enhanced spectral image data for segmenting tubular structures like arteries, using the contrast map to identify contrast in regions, and/or quantifying the relative contrast agent of each pixel in the image, as the Office argues, there is no disclosure in either Natanzon or Lamash of displaying different anatomical regions of a same reconstructed image in different contrasts by adjusting display parameter settings of the reconstructed image differently for the different anatomical regions. Specifically, Applicant finds no teaching of: "generating a first contrast-optimized image based on the MVI, the first contrast-optimized image showing a first anatomical region displayed using a first set of display parameters of the CT system selected to maximize a first desired contrast between different anatomical features of the first anatomical region, and a second anatomical region displayed using a second set of display parameters of the CT system selected to maximize a second desired contrast between different anatomical features of the second anatomical region, the second desired contrast different from the first desired contrast, the second set of display parameter settings different from the first set of display parameter settings," as required by amended claim 1.
Additionally, with regard to the display parameters, the portions of Natanzon cited by the Office on page 5 of the Office action in its rejection of claim 1 at best describe displaying a spectral diagram where different materials (air, bone, iodine, and kidney stone) are displayed in different colors (where Color and Material are read as display parameters (see paragraph [0151] of Natanzon)). However, the first and second sets of display parameter settings that are adjusted in amended claim 1 are window width/length and keV. There is no teaching in either Natanzon or Lamash of the first set of display parameter settings and the second set of display parameter settings including at least one of a window width (WW) setting, a window length (WL) setting, and a kiloelectron voltage (keV) setting, as required by amended claim 1.
Further, the Office cites Lamash as "determining the relative contrast agent of each pixel in the image" (see paragraph [0059] of Lamash), which it argues corresponds to determining a desired contrast of the anatomical regions. However, the first and second desired contrasts set forth in amended claim 4 refer to target contrasts that may be obtained by adjusting the display parameters via a set of algorithms. Amended claim 4 specifies that the first and second desired contrasts are generated by applying a set of one or more algorithms to the MVI, and that the display parameters are adjusted based on the first and second desired contrasts.
Examiner respectably disagrees Natanzon teaches the spectral imagery can be a combination of energy images or a single energy image (Para. 0140, 0151 and 0153). Each image is segmented into regions of interests (Para. 0108) and L locations (Para. 0020-0021). The image L locations have several energies or energy ranges associated with them(Para. 0065-0067). Each energy value for a given image location L represents contrast for different energies/energy ranges (Para. 0065) and spectral imaging resolves image contrasts into a plural of energy windows (Para. 0066-0067). Depending on the interest/diagnosis/material for the image locations specific energies/contrast are sought (Para. 0005 and 0069-0070). The images are sub-divided into one or several patches (Para. 0082 and 0096) associated with L Locations. The L locations, regions of interest, and patches can be anatomical regions as each are portions of spectral images. The patches can be combined to create partial or global probability maps used to generate material decomposition images(Para. 0139-0147). The probability maps created are used to illustrate material decomposition and indicate several different contrasts, such as bone, tissue, iodine (Contrast Agent), fat, uric acid, and more in the images (Para. 0153). These probability maps can be overlayed on the entirety of the spectral imagery or on a patch with any suitable color or grey-value coloring(Para. 0151). Thus, portions of the material decomposition images can have different energy levels associated at each pixel/voxel of the spectral images(Para. 0036-0037) based on a display parameter (Energy KeV Value, Para. 0066). Since in dual-energy imaging a low and high energy is measured for the imaging (Para. 0036 and 0066) as well as contrast is modulated by the amount and concentration of a specific material (Para. 0005).
While Natanzon and Lamash fail to explicitly disclose window width/length as display parameters. Profio teaches adjusting several parameters based on scanning and acquiring imaging information (Para. 0038). These parameters include reconstruction parameters specific to dual energy imaging, contrast injection parameters, volume, flow rate, window width/length, and algorithms for determining reconstruction kernels (Para. 0038).
Applicant argues the first and second desired contrasts set forth in amended claim 4 refer to target contrasts that may be obtained by adjusting the display parameters via a set of algorithms. However, applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., algorithms and target contrasts) are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
Regarding the remaining arguments applicant argues with respect to the amended claim language, which is fully addressed in the prior art rejections set forth below.
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 1, 3, 21 are rejected under 35 U.S.C. 103 as being unpatentable over Natanzon et al U.S. Patent Application Publication No. 20230360201 A1 (hereinafter Natanzon) in view of Profio et al. U.S. Patent Application Publication No. 20180061045 A1 (hereinafter Profio).
Regarding claim 1, Natanzon teaches A method for a computed tomography (CT) system (Imaging Apparatus SIA, Para. 0064), the method comprising:
performing a CT scan (CT Scanner) of a patient injected with a contrast agent; (Para. 0069)
reconstructing (Reconstruction System RECON, Para. 0054) a monochromatic virtual image (MVI) (Spectral Imagery) based on projection data acquired during the CT scan; (Para. 0069)
generating a first contrast-optimized image(Combination of Energy Images, Para. 0015 and 0151) based on the MVI (Reconstructed Spectral Imagery), the first contrast-optimized image (Combination of Energy Images, Para. 0015 and 0151) showing a first anatomical region (Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097), displayed using a first set of display parameters (KeV Energy Window Para. 0066, Associated with the Image Location Para. 0015) of the CT System selected to maximize a first desired contrast between different anatomical features (Bone, Tissue, Fat, Other Materials, Para. 0153) of the first anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097), and a second anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) displayed using a second set of display parameters(KeV Energy Window Para. 0066, Associated with the Image Location Para. 0015) of the CT system selected to maximize a second desired contrast between different anatomical features (Bone, Tissue, Fat, Iodine, Other Materials, Para. 0153) of the second anatomical region(L Locations in Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097), the second desired contrast different from the first desired contrast, the second set of display parameter settings different from the first set of display parameter settings(KeV Energy Window Para. 0066, Associated with the Image Location Para. 0015); As stated above, Natanzon teaches the spectral imagery can be a combination of energy images or a single energy image (Para. 0140, 0151 and 0153). Each image is segmented into regions of interests (Para. 0108) and L locations (Para. 0020-0021). The image L locations have several energies or energy ranges associated with them(Para. 0065-0067). Each energy value for a given image location L represents contrast for different energies/energy ranges (Para. 0065) and spectral imaging resolves image contrasts into a plural of energy windows (Para. 0066-0067). Depending on the interest/diagnosis/material for the image locations specific energies/contrast are sought (Para. 0005 and 0069-0070). The images are sub-divided into one or several patches (Para. 0082 and 0096) associated with L Locations. The L locations, regions of interest, and patches can be anatomical regions as each are portions of spectral images. The patches can be combined to create partial or global probability maps used to generate material decomposition images(Para. 0139-0147). The probability maps created are used to illustrate material decomposition and indicate several different contrasts, such as bone, tissue, iodine (Contrast Agent), fat, uric acid, and more in the images (Para. 0153). These probability maps can be overlayed on the entirety of the spectral imagery or on a patch with any suitable color or grey-value coloring(Para. 0151). Thus, portions of the material decomposition images can have different energy levels associated at each pixel/voxel of the spectral images(Para. 0036-0037) based on a display parameter (Energy KeV Value, Para. 0066). Since in dual-energy imaging a low and high energy is measured for the imaging (Para. 0036 and 0066) as well as contrast is modulated by the amount and concentration of a specific material (Para. 0005).
reconstructing (Computerized System MD Para. 0070-0073, Fig. 2-3 and 5 and (Reconstruction System RECON, Para. 0054) a first basis material decomposition (MD) image based on the acquired projection data, the first MD image including anatomical regions (Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) having a 1:1 correspondence to anatomical regions (Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097)) of the first contrast-optimized image(Combination of Energy Images, Para. 0015 and 0151) with respect to size and positioning; (Natanzon teaches splitting the spectral image into patches that can be any size or shape, Para. 0017. The patches include Regions of Interest for different materials, Para. 0148 Fig. 8. Specifically, Fig. 8D and 8E are 1:1 regions of interests for different materials)
generating one or more colorized overlays (Partial or Global Probability Map Overlay, Para. 0151) from the first MD image, each colorized overlay applying one or more colors (Color or Grey-Value Coded, Para. 0083 and 0151) to the anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) to show spectral decomposition (Four-Material Type Decomposition) information relating to the anatomical region (Fig. 8, Para. 0151 and 0153);
superimposing the one or more colorized overlays(Partial or Global Probability Map Overlay, Para. 0151) on the first contrast-optimized image(Combination of Energy Images, Para. 0015 and 0151);
and displaying the first contrast-optimized image(Combination of Energy Images, Para. 0015 and 0151)including the one or more colorized overlays(Partial or Global Probability Map Overlay, Para. 0151) on a display screen (Display Device DD) of the CT system; (Para. 0056 and 0061)
wherein the first set of display parameter settings(KeV Energy Window Para. 0066, Associated with the Image Location Para. 0015) and the second set of display parameter settings include at least one of a (KeV Energy Window, Para. 0066).
However, Natanzon fails to teach:
wherein the first set of display parameter settings and the second set of display parameter settings include at least one of a window width (WW) setting, a window length (WL) setting.
Natanzon and Profio are analogous to the claimed invention because both of them are in the same field of Spectral Image Processing for Computed Tomography.
Profio teaches:
wherein the first set of display parameter settings(Reconstruction Parameters and Settings Para. 0038) and the second set of display parameter settings(Reconstruction Parameters and Settings Para. 0038) include at least one of a window width (WW) setting (Para. 0038), a window length (WL) setting (Para. 0038) and a kiloelectron voltage (keV) setting (KeV Energy Levels Para. 0068).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Contrast-Optimized images to incorporate Profio’s Reconstruction Parameters. Since doing so would provide the benefit of adjusting settings when acquiring CT images for better performance, quality, and optimizations. Considering selecting effective combinations of settings of different parameters is difficult with conventional imaging systems. (Profio, Para. 0002)
Regarding claim 3, Natanzon teaches the method of claim 1, wherein:
a first colorized overlay (Color Coding) of the one or more colorized overlays applies a first set of colors to a first anatomical region (Color Codes for the Material with the Highest Probability), and applies no color to a second anatomical region (Grey-Value Coding, Para. 0151);
and a second colorized overlay (Color Coding) of the one or more colorized overlays applies no color to the first anatomical region (Grey-Value Coding), and applies a second set of colors to the second anatomical region; (Color Coding, Para. 0151)
wherein the second set of colors is different from the first set of colors(Color Coding and Gray-Value Coding, Para. 0151).
Regarding claim 21, Natanzon teaches the method of claim 1, wherein reconstructing (Reconstruction System RECON, Para. 0054) the MVI (Reconstructed Spectral Imagery) based on projection data acquired during the CT scan further comprises selecting a first convolution algorithm (Reconstruction Algorithms, Para. 0062) to adjust a first set of frequency components of a first set of projection data corresponding to the first anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097), and selecting a second convolution algorithm(Reconstruction Algorithms, Para. 0062) to adjust a second set of frequency components of a second set of projection data corresponding to the second anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097), the second convolution algorithm different from the first convolutional algorithm.Natanzon teaches that one or more different reconstruction algorithms can be implemented (Para. 0062).
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Natanzon et al U.S. Patent Application Publication No. 20230360201 A1 (hereinafter Natanzon) in view of view of Profio et al. U.S. Patent Application Publication No. 20180061045 A1 (hereinafter Profio) in further view of Lamash et al U.S. Patent Application Publication No. 20160321803 A (hereinafter Lamash)
Regarding claim 4, Natanzon teaches the method of claim 1, wherein generating the first contrast-optimized image (Combination of Energy Images, Para. 0015 and 0151) based on the MVI(Reconstructed Spectral Imagery) further comprises:
segmenting(Segmentation Algorithm Para. 0108 or Sub-dividing Spectral Imagery into Patches, Para. 0082) the first anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) and the second anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) of the MVI(Reconstructed Spectral Imagery);
and adjusting the first set of display parameter settings(KeV Energy Window Para. 0066, Associated with the Image Location Para. 0015) of the CT system for the first segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) to achieve the first desired contrast, and adjusting the second set of display parameter settings(KeV Energy Window Para. 0066, Associated with the Image Location Para. 0015) of the CT system for the second segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) to achieve the second desired contrast.
However, Natanzon fails to teach:
assessing an organ perfusion status of the contrast agent at a respective plurality of anatomical reference points of the first anatomical region and the second anatomical region;
based on the assessed organ perfusion status of the contrast agent, applying a set of one or more algorithms to the reconstructed MVI to determine the first desired contrast of the first segmented anatomical region and the second desired contrast of the second segmented anatomical region;
Profio teaches:
assessing an organ perfusion status (Perfusion Analysis, Para. 0022) of the contrast agent (Contrast Injection Parameters or Reconstruction Parameters, Para. 0038) One of the available scanning protocols used which includes specific scanning parameters and reconstruction parameters is Neurological perfusion analysis (Para. 0022).
based on the assessed organ perfusion status(Perfusion Analysis, Para. 0022) of the contrast agent(Contrast Injection Parameters or Reconstruction Parameters, Para. 0038), applying a set of one or more algorithms (Algorithm to Determine Reconstruction Kernel, Para. 0038) to the reconstructed MVI (Image Type Monochromatic, Para. 0038)
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Spectral-Image Based Material Decomposition to incorporate Profio’s Reconstruction Parameters. Since doing so would provide the benefit of adjusting settings when acquiring CT images for better performance, quality, and optimizations. Considering selecting effective combinations of settings of different parameters is difficult with conventional imaging systems. (Profio, Para. 0002)
However, Profio fails to teach:
a respective plurality of anatomical reference points of the first anatomical region and the second anatomical region;
determine the first desired contrast of the first segmented anatomical region and the second desired contrast of the second segmented anatomical region;
Natanzon, Lamash, and Profio are analogous to the claimed invention because all of them are in the same field of processing imagery in computed tomography.
Lamash teaches:
assessing an organ perfusion status(Flow Reserve Analysis and Acute Coronary Syndrome Risk Assessment, Para. 0040) of the contrast agent at a respective plurality of anatomical reference points(Segmentation of the Tubular Structure (Lumen), Para. 0041) of the first anatomical region (Segment of a Tubular Structure (Lumen)) and the second anatomical region(Segment of a Tubular Structure (Lumen));
based on the assessed organ perfusion status(Flow Reserve Analysis and Acute Coronary Syndrome Risk Assessment, Para. 0040) of the contrast agent(Contrast Agent Spectral Response Curve), applying a set of one or more algorithms to the reconstructed MVI(Contrast Enhanced Spectral Image, Para. 0032) to determine the first desired contrast(Calculating a Relative Contrast Agent Para. 0039 and Iteratively Updating/Refining the Contrast Map Para. 0012-0014) of the first segmented anatomical region(Segment of a Tubular Structure (Lumen)) and the second desired contrast of the second segmented anatomical region(Segment of a Tubular Structure (Lumen)); Lamash teaches generating a contrast map based on the contrast enhanced spectral image data (Para. 0012) for segmenting tubular structures like arteries to assess them (Para. 0011, 0040). The contrast map can be used to identify contrast in regions and analyze material build-up from the spectral image data (Para. 0076). Lamash quantifies the amount of contrast-agent (Para. 0059) in the spectral analysis image data and determines the relative contrast agent of each pixel in the image. Each pixel of the image would correspond to portion of the arteries. The tubular structures can be segmented (Para. 0032, Para. 0048-0051, Fig. 5). Different regions of interest of the spectral analysis image data can be determined and measured specifically. (Fig. 7, Para. 0059 and 0062).
The claim language of anatomical reference points is broad and the measured spectral points of interests (Para. 0062) reads on the anatomical reference points. Similarly segmented anatomical regions reads on the segmented tubular structure (Para. 0011 and 0041). Lamash suggests the approach taught can be used on various organs (Para. 0054). Arteries are found all over the human body associated organs. For example, arteries are blood vessels that carry oxygenated blood away from the heart to the rest of the body and are composed of multiple tissues which work together to transport blood. An organ is defined as a collection of tissues that work together to perform a specific function, and Lamash’s method can be applied to other organ’s arteries. Thus, Lamash teaches assessing an organ perfusion status (Contrast Map, Para. 0076) of the contrast agent as a respective plurality of anatomical reference points (measured spectral points of interests Para. 0062) of the plurality of segmented anatomical regions (segmented tubular structure, Para. 0011 and 0041).
“Desired contrast” is broad language and subjective. The “desired contrast” varies based on the technician/doctor performing the scan, the disease/problem being looked for, patient, and the organs. Because Lamash finds the relative contrast of each pixel and creates a contrast map that will be used to identify contrast in regions of arteries which are quantified (Para. 0012, 0059, 0076). The “desired contrast” can be the amount of contrast that shows coronary artery disease (Para. 0005) and acute coronary syndrome (Para. 0008).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Spectral-Image Based Material Decomposition altered by Profio’s Reconstruction Parameters to incorporate Lamash’s Assessment of Organ Perfusion Status Involving Contrast Agent. Since doing so would provide the benefit of leveraging the mutual relation between segmentation and quantitate contrast-agent mapping to detect and prevent acute coronary syndrome. (Lamash, Para. 0008 and 0012).
Claims 5-7 are rejected under 35 U.S.C. 103 as being unpatentable over Natanzon et al U.S. Patent Application Publication No. 20230360201 A1 (hereinafter Natanzon) in view of Profio et al. U.S. Patent Application Publication No. 20180061045 A1 (hereinafter Profio) and Lamash et al U.S. Patent Application Publication No. 20160321803 A (hereinafter Lamash) in further view of Hoffmann et al German Patent Application No. 102019210473 A1 (hereinafter Hoffmann)
Regarding claim 5, Natanzon, Profio, and Lamash fail to teach The method of claim 3, further comprising using a tissue assessment deep learning (DL) model to identify diseased tissues in one or both of the first contrast-optimized image and the first MD image; wherein the first colorized overlay shows healthy tissues of the first anatomical region in a first color, and shows the identified diseased tissues of the first anatomical region in a second color, wherein the first color and the second color are selected to highlight a contrast between the healthy tissues and the diseased tissues.
Natanzon, Profio, Lamash, and Hoffman are analogous to the claimed invention because all of them are in the same field of processing imagery in computed tomography.
However, Hoffman teaches the method of claim 3, further comprising using a tissue assessment deep learning (DL) model (Machine Learning Algorithm) to identify diseased tissues in one or both of the first contrast-optimized image (Contrast-Suppressed Data) and the first MD image (Detects change in tissue types, Page 5 Para. 3); wherein the first colorized overlay shows healthy tissues of the first anatomical region in a first color (Tissues Displayed Differently with Color or Textures, Page 7, Para. 4), and shows the identified diseased tissues of the first anatomical region in a second color, wherein the first color and the second color are selected to highlight a contrast between the healthy tissues and the diseased tissues. (Page 4 Para. 3 and Page 7 Para. 4) Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Spectral-Image Based Material Decomposition altered by Profio’s Reconstruction Parameters and Lamash’s Assessment of Organ Perfusion Status Involving Contrast Agent to incorporate Hoffman’s Machine Learning Model that Detects Changes in Tissues and Displays them Based on Color/Texture. Since doing so would provide the benefit of leveraging AI to detect changes in tissues to contribute to diagnosis and treatment reliability. (Hoffman, Page 5, Para. 4) Then color-coding such detections has the advantage of increasing the visual readability of the changes in the tissue.
Regarding claim 6, Natanzon, Profio, and Lamash fail to teach the method of claim 5, wherein the tissue assessment DL model is a neural network trained on healthy and diseased tissue types of the first anatomical region.
However, Hoffman teaches the method of claim 5, wherein the tissue assessment DL model is a neural network (Machine Learning Algorithm) trained on healthy and diseased tissue types of the first anatomical region. (Page 6 Para.3-5) Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Spectral-Image Based Material Decomposition altered by Profio’s Reconstruction Parameters and Lamash’s Assessment of Organ Perfusion Status Involving Contrast Agent Hoffman’s Tissue Assessment Model that is Trained to Determine Healthy and Diseased Tissues. Since doing so would provide the benefit of leveraging artificial intelligence to help determine changes in tissue from spectral images obtained from a CT scanner, which increase diagnosis and treatment reliability. (Hoffman, Page 5 Para. 4)
Regarding claim 7, Natanzon teaches the method of claim 5, wherein the first anatomical region includes bone tissues. (Para. 0070)
Claims 8-10 are rejected under 35 U.S.C. 103 as being unpatentable over Natanzon et al U.S. Patent Application Publication No. 20230360201 A1 (hereinafter Natanzon) in view of Profio et al. U.S. Patent Application Publication No. 20180061045 A1 (hereinafter Profio), Lamash et al U.S. Patent Application Publication No. 20160321803 A (hereinafter Lamash), and Hoffmann et al German Patent Application No. 102019210473 A1 (hereinafter Hoffmann) in further view of Rix et al United Kingdom Patent Application No. 2594759 A (hereinafter Rix).
Regarding claim 8, Natanzon and Hoffman teach wherein the first colorized overlay uses color to distinguish between the different segmented portions. (Natanzon Para. 0151 and Hoffman Page 7 Para. 4)
However, Natanzon, Profio, Lamash and Hoffman fail to teach further comprising using a bone marrow segmentation model to segment the bone tissues into portions of different densities.
Natanzon, Profio, Lamash, Hoffman, and Rix are analogous to the claimed invention because all of them are in the same field of processing medical imaging from a CT scanner.
Rix teaches the method of claim 7, further comprising using a bone marrow segmentation model (Segmentation Method, Page 8 Lines 30-32 and Page 9 Lines 1-2) to segment the bone tissues (Page 9 Lines 31-32 and Page 10 Lines 1-10) into portions of different densities. (Page 13 Lines 21-31 and Page 14 Lines 1-2) Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Spectral-Image Based Material Decomposition altered by Profio’s Reconstruction Parameters, Lamash’s Assessment of Organ Perfusion Status Involving Contrast Agent, and Hoffman’s Tissue Assessment Model to incorporate Rix’s Tissue Segmentation Model. Both Natanzon and Hoffman utilize a machine learning algorithm and use images of tissues obtained from a CT scanner. Hence, combining Rix’s tissue segmentation model with Natanzon’s or Hoffman’s colorized overlays that showcase changes in tissues is appropriate. Since, leveraging AI to detect changes in tissues to contribute to diagnosis and treatment reliability. (Hoffman, Page 5, Para. 4)
Regarding claim 9, Natanzon, Profio, and Lamash fail to teach the method of claim 8, wherein one or both of the tissue assessment DL model and the bone marrow segmentation model take image data from a water-hydroxyapatite (HAP) image as input.
However, Hoffman teaches the method of claim 8, wherein at least one of the tissue assessment DL model (Machine Learning Algorithm, Page 5 Para. 3)and the bone marrow segmentation model take image data from a water-hydroxyapatite (HAP) image (Water/Edema Content) as input. (Page 6 Para. 3-4) Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Spectral-Image Based Material Decomposition altered by Profio’s Reconstruction Parameters and Lamash’s Assessment of Organ Perfusion Status Involving Contrast Agent to incorporate Hoffman’s Machine Learning Model that Utilizes Water-Hydroxyapatite Images as Input. Since doing so would provide the benefit of leveraging AI to detect changes in tissues by water/edema content which contributes to diagnosis and treatment reliability. (Hoffman, Page 5, Para. 4)
Natanzon, Profio, Lamash, and Hoffman fail to teach a bone marrow segmentation model.
Rix teaches a bone marrow segmentation model. (Segmentation method, Page 8 Lines 30-32 and Page 9 Lines 1-2) Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to modified Natanzon’s Generation of Spectral-Image Based Material Decomposition altered by Profio’s Reconstruction Parameters, Lamash’s Assessment of Organ Perfusion Status Involving Contrast Agent, and Hoffman’s Machine Learning Model that Utilizes Water-Hydroxyapatite Images as Input to incorporate Rix’s Segmentation Model. Since doing so would provide the benefit of leveraging AI to segment the bone tissue based on biomarker densities which contributes to diagnosis and treatment reliability. (Hoffman, Page 5, Para. 4)
Regarding claim 10, Natanzon, Profio, Lamash, and Hoffman fail to teach the method of claim 8, wherein the bone marrow segmentation model includes a neural network trained on bone tissue in spectral CT images.
However, Rix teaches the method of claim 8, wherein the bone marrow segmentation model (Segmentation model, Page 8 Lines 30-32 and Page 9 Lines 1-2) includes a neural network trained on bone tissue (Page 9 Lines 31-32 and Page 10 Lines 1-7) in spectral CT images. (Page 12 Lines 24-32) Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Spectral-Image Based Material Decomposition altered by Profio’s Reconstruction Parameters, Lamash’s Assessment of Organ Perfusion Status Involving Contrast Agent, and Hoffman’s Machine Learning Model that Utilizes Water-Hydroxyapatite Images as Input to incorporate Rix’s Tissue Segmentation Model Trained on Spectral CT Images. Both Natanzon and Hoffman utilize machine learning algorithms on spectral images, hence incorporating Rix’s machine learning algorithm that segments tissue into Natanzon’s or Hoffman’s is straightforward. Since doing so would provide the benefit of leveraging AI to segment the spectral images to increase diagnosis and treatment reliability.
Claims 11-13 are rejected under 35 U.S.C. 103 as being unpatentable over Natanzon et al U.S. Patent Application Publication No. 20230360201 A1 (hereinafter Natanzon) in view of in view of Profio et al. U.S. Patent Application Publication No. 20180061045 A1 (hereinafter Profio) in further view of Avinash et al. U.S. Patent No. 8761479 B2-IDS REF (hereinafter Avinash) and Min et al. U.S. Patent Application Publication No. 20220392065 A1 (hereinafter Min).
Regarding claim 11, Natanzon teaches the method of claim 1, further comprising:
retrieving a second MVI (Reconstructed Spectral Imagery, Para. 0061-0062) of the patient generated from a different image dataset of a previous scan and stored in a picture archiving and communications system (PACS) coupled to the CT system (Para. 0074);
generating a second contrast-optimized image(Combination of Energy Images, Para. 0015 and 0151) based on the second MVI (Reconstructed Spectral Imagery), using a same set of display parameters (KeV Energy Window Para. 0066, Associated with the Image Location Para. 0015) selected for generating the first contrast-optimized image(Combination of Energy Images, Para. 0015 and 0151);
reconstructing (Computerized System MD Para. 0070-0073, Fig. 2-3 and 5 and (Reconstruction System RECON, Para. 0054) a second MD (Material Decomposition Imaging, Para. 0070) image based on projection data used to generate the second MVI (Reconstructed Spectral Imagery);
generating a second set of colorized overlays(Partial or Global Probability Map Overlay, Para. 0151) from the second MD(Material Decomposition Imaging, Para. 0070) image, using a same procedure used to generate the one or more colorized overlays(Partial or Global Probability Map Overlay, Para. 0151) from the first MD image; (Para. 0151 and 0153)
However, Natanzon and Profio fail to teach the method of claim 1, further comprising:
performing an automated comparison of features between the first contrast-optimized image and the second contrast-optimized image;
generating an automated report including both of the first contrast-optimized image and the second contrast-optimized image, the automated report describing at least a progression of a disease in an anatomical region of the patient, the progression of the disease determined by comparing a first size of a first area of diseased tissue in the first contrast-optimized image with a second size of a second area of diseased tissue in the second contrast-optimized image;
and sending the report to a user of the CT system.
Natanzon, Profio, and Avinash are analogous to the claimed invention because all of them are in the field of analyzing spectral CT data.
Avinash teaches the method of claim 1, further comprising:
performing an (Comparative Analysis, Col. 6 Lines 43-52 and Col. 8 Lines 44-58) of features between the first contrast-optimized image(First Image Region 194, Col. 8 Lines 37-43) and the second contrast-optimized image(Second Image Region 212, Col. 8 Lines 59-66);
generating an automated report (Fig.10) including both of the first contrast-optimized image (First Image Region 194, Col. 8 Lines 37-43) and the second contrast-optimized image (Second Image Region 212, Col. 8 Lines 59-66);
and sending the report to a user of the CT system. (Col. 8 Lines 18-25)
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Spectral-Image Based Material Decomposition altered by Profio’s Reconstruction Parameters to incorporate Avinash’s Automated Report that Displays Multiple Spectral Images, Compares Regions of the Image, and Sends it to the User of the CT. Since doing so would provide the benefit of increasing the visual readability of the images which are desirable in analyzing and visualizing spectral CT data. (Avinash, Col. 2 Para. 23-25)
However, Natanzon, Profio, and Avinash fails to teach the method of claim 1, further comprising:
the automated report describing at least a progression of a disease in an anatomical region of the patient, the progression of the disease determined by comparing a first size of a first area of diseased tissue in the first contrast-optimized image with a second size of a second area of diseased tissue in the second contrast-optimized image;
Natanzon, Profio, Avinash, and Min are analogous to the claimed invention because all of them are in the field of analyzing medical images.
Min teaches:
retrieving a second MVI (Medical Image from CT Scanned Data, Para. 0191) of the patient generated from a different image dataset of a previous scan (Para. 0198).
performing an automated comparison (Comparing Images Overtime, Para. 0236) of features between the first contrast-optimized image (Medical Image) and the second contrast-optimized image (Medical Image at a Different Time, Para. 0287);
the automated report (Patient-Specific Medical Report) describing at least a progression of a disease (Track Disease Progression) in an anatomical region (Arteries or Plaque) of the patient, the progression of the disease determined by comparing a first size of a first area of diseased tissue in the first contrast-optimized image with a second size (Identified Features and Quantified Measurements) of a second area of diseased tissue in the second contrast-optimized image (Para. 0186 and 0187). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Spectral-Image Based Material Decomposition altered by Profio’s Reconstruction Parameters and Avinash’s Automated Report that Displays Multiple Spectral Images, Compares Regions of the Image, and Sends it to the User of the CT to incorporate Min’s Automated Report that Tracks Disease Progression. Since doing so would provide the benefit of increasing the visual readability of the progression of disease through colored images by comparing them in a visual report.
Regarding claim 12, Natanzon, Profio, and Avinash fail to teach the method of claim 11, wherein the description of the progression of the disease in the automated report includes a textual description of a measured difference between the first area of diseased tissue and the second area of diseased tissue.
However, Min further teaches the method of claim 11, wherein the description of the progression of the disease in the automated report (Patient-Specific Medical Report) includes a textual description (Analysis Results) of a measured difference (Quantified Parameters) between the first area (Previous Scan) of diseased tissue and the second area (Current Scan) of diseased tissue. (Para. 0198 and 0201) Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Spectral-Image Based Material Decomposition altered by Profio’s Reconstruction Parameters and Avinash’s Automated Report that Displays Multiple Spectral Images, Compares Regions of the Image, and Sends it to the User of the CT to incorporate Min’s Automated Report that Tracks Disease Progression and Provides a Textual Description. Since doing so would provide the benefit of increasing the visual readability of the progression of disease through colored images by comparing them in a visual report.
Regarding claim 13, Natanzon and Profio fail to teach the method of claim 11, wherein the description of the progression of the disease automated report includes a graphic depicting the first contrast-optimized image and the second contrast-optimized image side by side.
However, Avinash teaches the method of claim 11, wherein the description of the progression of the disease automated report (Textual Data, Col. 8 Para. 26-36) includes a graphic depicting the first contrast-optimized image (First Image Region 194, Col. 8 Lines 37-43) and the second contrast-optimized image (Second Image Region 212, Col. 8 Lines 59-66) side by side. (Fig.10) Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Spectral-Image Based Material Decomposition altered by Profio’s Reconstruction Parameters to incorporate Avinash’s Display of Multiple Spectral Images Side-By-Side. Since doing so would provide the benefit of increasing the visual readability of the images which are desirable in analyzing and visualizing spectral CT data. (Avinash, Col. 2 Para. 23-25)
Claims 14 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Natanzon et al U.S. Patent Application Publication No. 20230360201 A1 (hereinafter Natanzon) in view of Avinash et al. U.S. Patent No. 8761479 B2-IDS REF (hereinafter Avinash) in further view of Min et al. U.S. Patent Application Publication No. 20220392065 A1 (hereinafter Min).
Regarding claim 14, Natanzon teaches a computed tomography (CT) system, comprising a processor and a non-transitory memory including instructions that when executed, cause the processor to: (Para. 0056)
reconstruct (Reconstruction System RECON, Para. 0054) a monochromatic virtual image (MVI) (Spectral Imagery, Para. 0069) and a basis material decomposition (MD) (Computerized System MD, Para. 0070-0073, Fig. 2-3 and 5) image based on scan data acquired during a CT scan (X-Ray Imaging Apparatus) performed on a patient injected with a contrast agent; (Para. 0052)
segment (Segmentation Algorithm Para. 0108 or Sub-dividing Spectral Imagery into Patches, Para. 0082) a plurality of anatomical regions (Regions of Interest) of the MVI and the MD image; (Para. 108)
assess an uptake of the contrast agent (Contrast Agent Quantitative Map, Para. 0069) at a respective plurality of anatomical reference points (Image location L, Para. 0070) of the plurality of segmented anatomical regions (Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) of the MVI;
based on the assessed uptake of the contrast agent (Contrast Agent Quantitative Map, Para. 0069) at the respective plurality of anatomical reference points (Image location L, Para. 0070), determine a first desired contrast (Amount of Contrast, Para. 0070 or Contrast Ranges, Para. 0065) of a first segmented anatomical region (Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) of the MVI, and a second desired contrast of a second segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) of the MVI;
generate a contrast-optimized MVI using a first set of display parameter settings (KeV Energy Window Para. 0066, Associated with the Image Location Para. 0015) of the CT system for the first segmented anatomical region (Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) of the MVI that show the first segmented anatomical region in the first desired contrast (Amount of Contrast, Para. 0070 or Contrast Ranges, Para. 0065), and a second set of display parameter settings (KeV Energy Window Para. 0066, Associated with the Image Location Para. 0015) of the CT system for the second segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) of the MVI that show the second segmented anatomical region in the second desire contrast(Amount of Contrast, Para. 0070 or Contrast Ranges, Para. 0065); As stated above, Natanzon teaches the spectral imagery can be a combination of energy images or a single energy image (Para. 0140, 0151 and 0153). Each image is segmented into regions of interests (Para. 0108) and L locations (Para. 0020-0021). The image L locations have several energies or energy ranges associated with them(Para. 0065-0067). Each energy value for a given image location L represents contrast for different energies/energy ranges (Para. 0065) and spectral imaging resolves image contrasts into a plural of energy windows (Para. 0066-0067). Depending on the interest/diagnosis/material for the image locations specific energies/contrast are sought (Para. 0005 and 0069-0070). The images are sub-divided into one or several patches (Para. 0082 and 0096) associated with L Locations. The L locations, regions of interest, and patches can be anatomical regions as each are portions of spectral images. The patches can be combined to create partial or global probability maps used to generate material decomposition images(Para. 0139-0147). The probability maps created are used to illustrate material decomposition and indicate several different contrasts, such as bone, tissue, iodine (Contrast Agent), fat, uric acid, and more in the images (Para. 0153). These probability maps can be overlayed on the entirety of the spectral imagery or on a patch with any suitable color or grey-value coloring(Para. 0151). Thus, portions of the material decomposition images can have different energy levels associated at each pixel/voxel of the spectral images(Para. 0036-0037) based on a display parameter (Energy KeV Value, Para. 0066). Since in dual-energy imaging a low and high energy is measured for the imaging (Para. 0036 and 0066) as well as contrast is modulated by the amount and concentration of a specific material (Para. 0005).
generate a visualization (Fig. 8) of the contrast-optimized MVI including one or more color overlays (Partial or Global Probability Map Overlay, Para. 0151) superimposed on the contrast-optimized MVI, the color overlays (Color or Grey-Value Coded, Para. 0083 and 0151) generated from the MD image, the color overlays applying color to portions of the segmented anatomical regions(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) ;
However, Natanzon fails to teach instructions that when executed, cause the processor to:
compare the visualization with a previous visualization of the patient generated from a previous scan to determine a progression of a disease of the patient;
generate an automated report describing the progression, the automated report including the visualization and the previous visualization;
and send the automated report to a user of the CT system and/or display the visualization on a display device of the CT system.
Natanzon and Avinash are analogous to the claimed invention because both of them are in the field of analyzing and visualizing spectral CT data
However, Avinash teaches instructions that when executed, cause the processor to:
send the automated report to a user of the CT system and/or display the visualization on a display device of the CT system. (Col. 8 Lines 18-25, Fig.
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Contrast-Optimized images to incorporate Avinash’s Automated Report that Displays Multiple Spectral Images and Sends it to the User of the CT. Since doing so would provide the benefit of increasing the visual readability of the images which are desirable in analyzing and visualizing spectral CT data. (Avinash, Col. 2 Para. 23-25)
Natanzon and Avinash fails to teach instructions that when executed, cause the processor to:
compare the visualization with a previous visualization of the patient generated from a previous scan to determine a progression of a disease of the patient;
generate an automated report describing the progression, the automated report including the visualization and the previous visualization;
Natanzon, Avinash, and Min are analogous to the claimed invention because all of them are in the field of analyzing medical images.
However, Min teaches instructions that when executed, cause the processor to:
compare the visualization (Current Scan) with a previous visualization (Previous Scan) of the patient generated from a previous scan to determine a progression of a disease (Track Disease Progression) of the patient; (Para. 0186-0187, 0198 and 0201)
generate an automated report (Patient-Specific Medical Report) describing the progression, the automated report including the visualization and the previous visualization; (Para. 0186-0187, 0198 and 0201)
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Contrast-Optimized images Altered by Avinash’s Automated Report that Displays Multiple Spectral Images and Sends it to the User of the CT to incorporate Min’s Automated Report that Tracks Disease Progression. Since doing so would provide the benefit of increasing the visual readability of the progression of disease through colored images by comparing them in a visual report.
Regarding claim 17, Natanzon teaches the CT system of claim 14, wherein further instructions are stored in the non-transitory memory that when executed, (Para. 0056) cause the processor to generate the previous visualization from a prior study of the patient stored in a picture archiving and communications system (PACS) (Para. 0074) coupled to the CT system, the previous visualization generated by following a same procedure used to generate the visualization from the MVI and the MD image. (Para. 0061 and 0065)
Claims 15 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Natanzon et al U.S. Patent Application Publication No. 20230360201 A1 (hereinafter Natanzon) in view of Avinash et al. U.S. Patent No. 8761479 B2-IDS REF (hereinafter Avinash) in further view of Min et al. U.S. Patent Application Publication No. 20220392065 A1 (hereinafter Min) and Hoffmann et al German Patent Application No. 102019210473 A1 (hereinafter Hoffmann).
Regarding claim 15, Natanzon, Avinash, and Min fail to teach the CT system of claim 14, wherein the one or more color overlays show healthy tissues in a first color, and diseased tissues in a second color, the diseased tissues distinguished from the healthy tissues using a tissue assessment deep learning (DL) model.
Natanzon, Avinash, Min, and Hoffman are analogous to the claimed invention because all of them are in the same field of imaging in computed tomography.
However, Hoffman teaches the CT system of claim 14, wherein the one or more color overlays show healthy tissues in a first color, and diseased tissues in a second color (Tissues Displayed Differently with Color or Textures, Page 7, Para. 4), the diseased tissues distinguished (Detects change in tissue types) from the healthy tissues using a tissue assessment deep learning (DL) model. (Machine Learning Algorithm, Page 5 Para. 3) Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s, Avinash’s, or Min’s spectral images to incorporate Hoffman’s machine learning model that detects changes in tissues and displays them based on color/texture. Since doing so would provide the benefit of leveraging AI to detect changes in tissues to contribute to diagnosis and treatment reliability. (Hoffman, Page 5, Para. 4) Then color-coding such detections has the advantage of increasing the visual readability of the changes in the tissue.
Regarding claim 16, Natanzon teaches the CT system of claim 14, wherein the one or more color overlays (Color Coding, Para. 0151) show harder bone tissues in a first color, and softer bone tissues in a second color (Para. 0153), the harder bone tissues distinguished from the softer bone tissues based on relative water densities (Amount of Concentration, Para. 0070) of the harder bone tissues and the softer bone tissues.
However, Natanzon, Avinash, and Min fail to teach the CT system of claim 14, wherein the one or more color overlays show harder bone tissues in a first color, and softer bone tissues in a second color, the harder bone tissues distinguished from the softer bone tissues based on relative water densities of the harder bone tissues and the softer bone tissues.
Natanzon, Avinash, Min, and Hoffman are analogous to the claimed invention because all of them are in the same field of imaging in computed tomography.
Hoffman teaches the CT system of claim 14, wherein the one or more color overlays show harder bone tissues in a first color, and softer bone tissues in a second color (Tissue Areas Visualized, Page 4 Para. 7), the harder bone tissues distinguished from the softer bone tissues based on relative water densities (Water Content) of the harder bone tissues and the softer bone tissues. (Page 12, Para. 4) Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon colored overlays that can be used for bones to incorporate Hoffman’s distinguishing of tissues based on water content. Since integrating color into distinguishing tissues reduces the difficulty of recognizing changes in tissues that use gray-white contrast overlays. (Hoffman, Page 4 Para. 8 and Page 5 Para. 1)
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Natanzon et al. U.S. Patent Application Publication No. 20230360201 A1 (hereinafter Natanzon) in view of Avinash et al. U.S. Patent No. 8761479 B2 IDS REF (hereinafter Avinash).
Regarding Claim 18, Natanzon teaches method for a computed tomography (CT) system, the method comprising:
injecting a contrast agent into a patient; (Para. 0069)
performing a CT scan on the patient; (Para. 0052)
reconstructing (Reconstruction System RECON) a monochromatic virtual image (MVI) and a basis material decomposition (MD) image based on scan data acquired during the CT scan; (Para. 0069 and 0070)
segmenting (Segmentation Algorithm Para. 0108 or Sub-dividing Spectral Imagery into Patches, Para. 0082) a plurality of anatomical regions (Regions of Interest) of the reconstructed MVI and the reconstructed MD image; (Para. 0108)
performing an assessment of an absorption of the contrast agent (Contrast Agent Quantitate Map Para. 0069 or Amount of Contrast in Materials, Para. 0070) at each segmented(Segmentation Algorithm Para. 0108 or Sub-dividing Spectral Imagery into Patches, Para. 0082) anatomical region (Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) of the plurality of anatomical regions (Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) , based on the reconstructed MVI; (Fig. 8)
based on the assessed absorption of the contrast agent (Contrast Agent Quantitate Map Para. 0069 or Amount of Contrast in Materials, Para. 0070) at each segmented anatomical region (Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) of the plurality of anatomical regions (Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) , determining a first desired contrast of a first segmented anatomical region (Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) of the reconstructed MVI, and a second desired contrast of a second anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) of the reconstructed MVI;
adjusting a first set of display (Display Device DD) parameter settings (KeV Energy Window Para. 0066, Associated with the Image Location Para. 0015) of the CT system separately for the first segmented anatomical region to achieve the first desired contrast(Amount of Contrast, Para. 0070 or Contrast Ranges, Para. 0065) for the first segmented anatomical region (Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) , and adjusting a second, different set of display parameter settings (KeV Energy Window Para. 0066, Associated with the Image Location Para. 0015) of the CT system for the second segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) to achieve the second desired contrast(Amount of Contrast, Para. 0070 or Contrast Ranges, Para. 0065) for the second segmented anatomical region;
generating a visualization of the reconstructed MVI (Spectral Image) showing the first segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) in the first desired contrast(Amount of Contrast, Para. 0070 or Contrast Ranges, Para. 0065) and the second segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) in the second desired contrast(Amount of Contrast, Para. 0070 or Contrast Ranges, Para. 0065);
superimposing one or more colorized overlays (Partial or Global Probability Map Overlay, Para. 0151) on the visualization, the colorized overlays generated from the MD image (Fig.8), the colorized overlays applying color(Color or Grey-Value Coded, Para. 0083 and 0151) to portions of the segmented anatomical regions(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) ;
However, Natanzon fails to teach method for a computed tomography (CT) system, the method comprising:
comparing the visualization with a previous visualization of the patient generated from a previous scan to determine a progression of a disease of the patient;
generating an automated report describing the progression, the automated report including the visualization and the previous visualization;
sending the automated report to a user of the CT system.
Natanzon and Avinash are analogous to the claimed invention because both of them are in the field of analyzing medical images.
Avinash teaches method for a computed tomography (CT) system, the method comprising:
comparing the visualization (First Image Region 194, Col. 8 Lines 37-43) with a previous visualization (Second Image Region 212, Col. 8 Lines 59-66); of the patient generated from a previous scan to determine a progression of a disease of the patient; (Col. 5 Lines 21-40)
generating an automated report describing the progression, the automated report including the visualization and the previous visualization; (Fig. 10)
sending the automated report to a user of the CT system. (Col. 8 Lines 18-25)
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Spectral-Image Based Material Decomposition to incorporate Avinash’s Automated Report that Displays Multiple Spectral Images, Compares Regions of the Image, and Sends it to the User of the CT. Since doing so would provide the benefit of increasing the visual readability of spectral images which are desirable in analyzing and visualizing spectral CT data. (Avinash, Col. 2 Para. 23-25)
Claims 19 is rejected under 35 U.S.C. 103 as being unpatentable over Natanzon et al. U.S. Patent Application Publication No. 20230360201 A1 (hereinafter Natanzon) in view of Avinash et al. U.S. Patent No. 8761479 B2 IDS REF (hereinafter Avinash) in further view of Profio et al. U.S. Patent Application Publication No. 20180061045 A1 (hereinafter Profio).
Regarding claim 19, Natanzon teaches the method of claim 18, wherein adjusting the first set of display parameter settings(KeV Energy Window Para. 0066, Associated with the Image Location Para. 0015) of the CT system for the first segmented(Segmentation Algorithm Para. 0108 or Sub-dividing Spectral Imagery into Patches, Para. 0082) anatomical region and adjusting the second set of display parameter settings(KeV Energy Window Para. 0066, Associated with the Image Location Para. 0015) of the CT system for the second segmented anatomical region further comprises: (Para. 0061 and 0065)
using a (Reconstruction Algorithms Para. 0062) of the CT system for the first segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097), and using a second, different (Reconstruction Algorithms Para. 0062 of the CT system for the second segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097); The spectral imagery can be a combination of energy images or a single energy image (Para. 0140, 0151 and 0153). Each image L Location has several energies or energy ranges associated with them based on the energy image(Para. 0065-0067). Depending on the interest/diagnosis/material for the image locations specific energies/contrast are sought (Para. 0005 and 0069-0070). Each image L location is made up of one or several patches (Para. 0096). The patches can be combined to create partial or probability maps used to generate material decomposition images(Para. 0139-0147). Thus, the image L Locations can have different energy and contrast levels.
using a first keV setting(KeV Energy Window Para. 0066, Associated with the Image Location Para. 0015) of the CT system for displaying the first segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) , and using a second, different keV setting (KeV Energy Window Para. 0066, Associated with the Image Location Para. 0015) of the CT system for displaying the second anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) ;
selecting a first kernel(Reconstruction Algorithms Para. 0062 or Kernel Function Para. 0017 and 0087) to apply to the first segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) to adjust frequency contents of projection data of the first segmented anatomical region, and selecting a second, different kernel(Different Reconstruction Algorithms Para. 0062 or Kernel Function Para. 0017 and 0087) to apply the second segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) to adjust frequency contents of projection data of the second segmented anatomical region; Natanzon teaches that one or more different reconstruction algorithms can be implemented (Para. 0062).
adjusting a contrast(Amount of Contrast, Para. 0070 or Contrast Ranges, Para. 0065) of the first segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) based on spectral information(Spatial Energy Images) associated with the first segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097), and adjusting a contrast(Amount of Contrast, Para. 0070 or Contrast Ranges, Para. 0065) of the second segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) based on spectral information associated with the second segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097);
and digitally adjusting the contrast(Amount of Contrast, Para. 0070 or Contrast Ranges, Para. 0065) of the first segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) as a function of image data of each voxel (Pixel/Voxel/Patch, Para. 0036-0037 and 0079) of the first segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097), and digitally adjusting the contrast(Amount of Contrast, Para. 0070 or Contrast Ranges, Para. 0065) of the second segmented anatomical region(Region of Interest Para. 0061 which contain L Locations in the Energy Images, Para. 0020, 0034, 0065, 0070 and 0096-0097) as a function of image data of each voxel(Pixel/Voxel/Patch, Para. 0036-0037 and 0079) of the second segmented anatomical region.
However, Natanzon and Avinash fail to teach:
a first window width setting and/or a first window level setting different window width setting and/or a second, different window level setting.
Natanzon, Avinash, and Profio are analogous to the claimed invention because all of them are in the field of analyzing scanned medical images.
Profio teaches:
first window width setting and/or a first window level setting(Reconstruction Parameters and Settings Para. 0038) of the CT system and using a second, different window width setting and/or a second, different window level setting(Reconstruction Parameters and Settings Para. 0038)
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Spectral-Image Based Material Decomposition to incorporate Avinash’s Automated Report that Displays Multiple Spectral Images, Compares Regions of the Image, and Sends it to the User of the CT to incorporate Profio’s Reconstruction Parameters. Since doing so would provide the benefit of adjusting settings when acquiring CT images for better performance, quality, and optimizations. Considering selecting effective combinations of settings of different parameters is difficult with conventional imaging systems. (Profio, Para. 0002)
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Natanzon et al U.S. Patent Application Publication No. 20230360201 A1 (hereinafter Natanzon) in view of Avinash et al. U.S. Patent No. 8761479 B2-IDS REF (hereinafter Avinash) in further view of Min et al. U.S. Patent Application Publication No. 20220392065 A1 (hereinafter Min).
Regarding claim 20, Natanzon fails to teach the method of claim 18, wherein the automated report shows the visualization and the previous visualization side by side, and includes a textual description of a measured difference between a first area of diseased tissue of the visualization and a second area of diseased tissue of the previous visualization.
However, Avinash teaches the method of claim 18, wherein the automated report (Textual Data, Col. 8 Para. 26-36) shows the visualization (First Image Region 194, Col. 8 Lines 37-43) and the previous visualization (Second Image Region 212, Col. 8 Lines 59-66) side by side (Fig. 10). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s spectral image overlay to incorporate displaying multiple spectral images side-by-side. Since doing so would provide the benefit of increasing the visual readability of the images which are desirable in analyzing and visualizing spectral CT data. (Avinash, Col. 2 Para. 23-25)
Natanzon and Avinash fail to teach the method of claim 18, wherein the automated report includes a textual description of a measured difference between a first area of diseased tissue of the visualization and a second area of diseased tissue of the previous visualization.
Natanzon, Avinash, and Min are analogous to the claimed invention because all of them are in the field of analyzing medical images.
However, Min teaches the method of claim 18, wherein the automated report (Patient-Specific Medical Report) includes a textual description of a measured difference (Quantified Parameters) between a first area of diseased tissue (Previous Scan) of the visualization and a second area of diseased tissue (Current Scan) of the previous visualization. (Para. 0198 and 0201) Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Natanzon’s Generation of Contrast-Optimized images Altered by Avinash’s Automated Report that Displays Multiple Spectral Images and Sends it to the User of the CT to incorporate Min’s Automated Report that Tracks Disease Progression and Provides a Textual Description. Since doing so would provide the benefit of increasing the visual readability of the progression of disease through colored images by comparing them in a visual report.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BRIANNA R COCHRAN whose telephone number is (571)272-4671. The examiner can normally be reached Mon-Fri. 7:30am - 5:00pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Alicia Harrington can be reached at (571) 272-2330. 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.
/BRIANNA RENAE COCHRAN/Examiner, Art Unit 2615
/ALICIA M HARRINGTON/Supervisory Patent Examiner, Art Unit 2615
Prosecution Insights