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 .
Response to Preliminary Amendment
The preliminary amendment filed on 03/06/2024 have been acknowledged.
Claims 1-20 are new.
Drawings
The drawings are objected to under 37 CFR 1.83(a). The drawings must show every feature of the invention specified in the claims. Therefore, the application of “an axis rotation that includes one or values closest to a mean of an axis training set” and the application of “the axis rotation that includes one or values closest to a best fit to an axis training set.” from claims 15 and 16 respectively must be shown or the feature(s) canceled from the claims No new matter should be entered.
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
The drawings are objected to under 37 CFR 1.83(a) because they fail to show “the system is configured to apply the axis rotation that includes one or values closest to a mean of the sample set and or best fit to an AI training set.” as described in paragraph 107 of the specification. Any structural detail that is essential for a proper understanding of the disclosed invention should be shown in the drawing. MPEP § 608.02(d). Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 15 and 16 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention. Claim’s 15 recites “wherein the system is configured to apply an axis rotation that includes one or values closest to a mean of an axis training set.” Claim 16 recites “wherein the system is configured to apply the axis rotation that includes one or values closest to a best fit to an axis training set.” Examiner is unsure what “…one or values closest to a…” objectively means.” Paragraph 107 of the specification seems to be the only insight yet; this claim is merely a recitation of this passage. The paragraph also points to figure 42 which does not assist in clarification.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 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.
Claim 1-11 and 17 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Sabina et al (Sabina hereinafter US 10390913 B2).
As per claim 1
Sabina teaches A system comprising: one or more computers comprising one or more processors (Fig 1A and Fig 1B) and one or more non- transitory computer readable media comprising program instructions stored thereon that when executed cause the one or more computers to (Paragraph 30 “These apparatuses may include non-transitory, machine-readable tangible medium storing instructions for causing one or more machines to execute operations for performing any of the methods described herein”) import, by the one or more processors, an image set, where each image in the image set comprises 3D image data comprising voxel data, (Paragraph 30 “In particular, any of these methods and apparatuses may operate on a data set that includes both a 3D model of the patient's dental arch, or in some variations, both of the patient's dental arches. The 3D model may be, but is not limited to, a 3D volumetric model; in some variation the 3D model is a 3D surface model of the arch. This data set may also include a plurality of images of the dental arch, taken from different positions relative to the dental arch, such as different angles between the plane of the image and the dental arch and different sub-regions of the dental arch”) wherein the voxel data includes a voxel value representing properties of an object in 3D space (Paragraph 7 “The regions of the volumetric model may correspond to one or more voxels, including contiguous voxel regions. These regions may be referred to herein as volumetric regions.” Paragraph 7 “For example, described herein are methods of displaying images from a three-dimensional (3D) volumetric model of a patient's dental arch.”) execute, by the one or more processors, a defect analysis configured to identify outliers in the 3D image data by comparing a statistical representation of the voxel data to a predefined threshold (Paragraph 19 “Identifying the region may comprise automatically identifying using a processor. For example, automatically identifying may comprise identifying a region having a possible defects including: cracks and caries. Identifying the region having a possible defect may comprise comparing a near-IR transparency value of a region within the 3D model to a threshold value. Automatically identifying may comprise identifying a surface color value outside of a threshold range. Automatically identifying may comprise segmenting the 3D volumetric model to identify enamel regions and identifying regions having enamel thicknesses below a threshold value.”) execute, by the one or more processors, a defect analysis configured to identify outliers in the 3D image data by comparing a statistical representation of the voxel data to a predefined threshold; ( Paragraph 7 “These methods may include automatically, manually or semi-automatically (e.g., with user approval or input) identifying one or more regions from within the 3D volumetric model to mark (including surface features and/or internal features of the dental arch); these regions may be regions in which a caries, crack or other irregularity has developed or may develop. Marked regions may be analyzed in greater detail, and may be tracked over time.” Paragraph 19 “Automatically identifying may comprise segmenting the 3D volumetric model to identify enamel regions and identifying regions having enamel thicknesses below a threshold value” Paragraph 55 “determining a confidence score for the dental feature based on the identified regions corresponding to the dental feature in the one or more different records; and displaying the dental feature when the confidence score for the dental feature is above a threshold.”) generate, by the one or more processors, a graphical user interface (GUI) configured to display the identified outliers in the image set (Figure 10A, Figure 10B Figure 14A Figure 14C) enable a user to select one or more images in the image set based on the identified outliers from the statistical representation (paragraph 53 “The user may select the plane's location and/or orientation, and my do this in a continuous manner. For example, any of these methods may include selecting, by a user, a section though the 3D volumetric model to display, wherein selecting comprises continuously selecting sections through the 3D volumetric model as the user scans through the 3D model and continuously displaying the 2D views corresponding to each section. Generating the 2D view may comprises selecting, by a user, an orientation of the 2D view.”)
As per claim 2
Sabina teaches all claim limitations previously rejected in claim 1’s 102 rejection. See claim 1’s 102 rejection.
Sabina teaches wherein the system is configured to automatically use images within the image set that include one or more characteristics that fall within a specified range of a statistical value as training data for an artificial intelligence (AI) algorithm. (Paragraph 68 “Automatic (or semi-automatic, etc., automatic but with manual assistance to verify/confirm) may be performed by a microprocessor, including systems that have been trained (e.g., by machine learning) to identify regions of irregularities on the outside and/or internal volume of the teeth. For example, the apparatus may examine the digital model to identify possible defects in the patient's teeth such as…For example, regions of the surface of the teeth in which the tooth surface is rough (e.g., has a smoothness that is below a set threshold, where smoothness may be determined from the outer surface of the enamel)” Paragraph 140 “For example, one or more actionable dental features may be identified automatically; a system as described herein may review the record (including the one or more images of the patient's teeth) to flag or identify regions having a characteristic associated with an actionable dental feature. A system may be trained, using machine learning techniques such as supervised learning techniques (e.g., classification, regression, similarity, etc.), unsupervised learning techniques (e.g., density estimation, cluster analysis, etc.), reinforcement learning (e.g., Markov Decision Process techniques, etc.), representation learning techniques and/or principle component analysis, etc., to identify/flag a region of a particular scan in a specified modality that is associated (even loosely associated with) an actionable dental characteristic…The grade and/or degree may refer to the confidence level or score for the potential actionable dental feature, including the confidence level or score that the identified potential actionable dental features is likely ‘real’.)
As per claim 3
Sabina teaches all claim limitations previously rejected in claim 1’s 102 rejection. See claim 1’s 102 rejection.
Sabina teaches wherein the voxel data includes values representing tissue density (“Paragraph 118 “The 3D volumetric models of the teeth” Figure 1A, Figure 3, Figure 5A Figure 5B, Figure 8A etc.)
As per claim 4
Sabina teaches all claim limitations previously rejected in claim 1’s 102 rejection. See claim 1’s 102 rejection.
Sabina teaches where the 3D image data comprises segmented 3D image data (Paragraph 19 “Automatically identifying may comprise segmenting the 3D volumetric model “ Paragraph 26 “the method may also include segmenting the 3D volumetric model into a plurality of teeth,” Paragraph 38 “hereafter, the penetrative images may be segmented 1711. In this example, segmentation may be done in one of two ways. On the inner teeth structure images, the images may be segmented using contour finding 1713, 1713′. Machine learning methods may be applied to further automate this process.” Paragraph 56 “automatically segmenting the volumetric model to define the regions of interest, including either or both tooth features (enamel, dentin, etc.) and/or irregularities (e.g., caries, cracks, etc.). Any appropriate segmentation technique may be used, such as but not limited to: mesh segmentation (mesh decomposition), polyhedral segmentation, skeletonization, etc.”).
As per claim 5
Sabina teaches all claim limitations previously rejected in claim 4’s 102 rejection. See claim 4’s 102 rejection.
Sabina teaches where the one or more non-transitory computer readable media include further program instructions stored thereon that when executed cause the one or more computers to: enable, by the one or more processors, the user to assign attributes to the identified outliers for training of a defect identification artificial intelligence (AI) model. (Paragraph 140 A system may be trained, using machine learning techniques such as supervised learning techniques (e.g., classification, regression, similarity, etc.), unsupervised learning techniques (e.g., density estimation, cluster analysis, etc.), reinforcement learning (e.g., Markov Decision Process techniques, etc.), representation learning techniques and/or principle component analysis, etc., to identify/flag a region of a particular scan in a specified modality that is associated (even loosely associated with) an actionable dental characteristic…. additionally, a user (dental professional, technician, etc.) may manually review one or more records (each in a particular imaging modality) and may flag or identify regions suspected to show an actionable dental characteristic.” Paragraph 148 “The system may be trained to recognize the potential actionable dental feature in the imaging modality of the additional record and may provide a score indicating the likelihood that the potential actionable dental feature is present in this location…user (e.g., technician, dental professional, etc.) may be presented with an image from the additional record(s) and may manually indicate the likelihood (yes/no, graded scale, numeric scale, etc.) that the potential actionable dental feature is present in the one or more additional records.
As per claim 6
Sabina teaches all claim limitations previously rejected in claim 5’s 102 rejection. See claim 5’s 102 rejection.
Sabina teaches execute, by the one or more processors, the defect identification Al model to classify defects in segmented 3D images based on the assigned attributes. (Paragraph 140 “The initial identification of the one or more actionable dental features may be performed manually or automatically or semi-manually. For example, one or more actionable dental features may be identified automatically; a system as described herein may review the record (including the one or more images of the patient's teeth) to flag or identify regions having a characteristic associated with an actionable dental feature. A system may be trained, using machine learning techniques such as supervised learning techniques (e.g., classification, regression, similarity, etc.), unsupervised learning techniques (e.g., density estimation, cluster analysis, etc.), reinforcement learning (e.g., Markov Decision Process techniques, etc.), representation learning techniques and/or principle component analysis, etc., to identify/flag a region of a particular scan in a specified modality that is associated (even loosely associated with) an actionable dental characteristic.” Paragraph 164 “In any of the methods and systems described herein, tooth segmentation may be used on all or some of the records and/or the 3D model to enhance performance and usability. Tooth segmentation may be added prior to volumetric modeling to assist and improve volumetric results and model quality. For example, the volumetric 3D model may uses the information of segmentation to potentially enhance performance as additional surface 3D information is added. The segmentation information may also assist in segmenting enamel-dentin-lesions to improve auto detection and suspicious areas marking (e.g., including but not limited to when using an automatic agent to identify potential actionable dental features).”)
As per claim 7
Sabina teaches all claim limitations previously rejected in claim 6’s 102 rejection. See claim 6’s 102 rejection.
Sabina teaches the system is configured to assign one or more images that fall within a specified range as normal.( Paragraph 141 “The grade and/or degree may refer to the confidence level or score for the potential actionable dental feature, including the confidence level or score that the identified potential actionable dental features is likely ‘real’. Paragraph 165 “In any of the methods and apparatuses described herein the confidence level indicated may be a quantitative and/or qualitative index. For example, a quantitative confidence level “score” may be provided (e.g., using a number between, for example, 0-100, 0 to 1.0, -100 to 100, or scaled to any range of numeric values). Qualitative indexes may include “high, medium high, medium, medium low, low”, etc. Both qualitative and quantitative confidence levels may be used. A rating system for the confidence level based on the multiple records as described herein may be impactful for insurance claims and/or patient communication.” Sabina states the confidence scores are correlated to an “actionable dental feature” which may include “cracks, gum recess, tartar, enamel thickness, pits, caries, pits, fissures, evidence of grinding, and interproximal voids.” Because “the confidence level indicated may be a quantitative and/or qualitative index” the quantitative score index is the range and the qualitative indexes are what designates what is normal and what is an “actionable dental feature”. What is “normal” is analyzed on a case by case patient record/archive which can be automatic or semiautomatic.)
As per claim 8
Sabina teaches all claim limitations previously rejected in claim 7’s 102 rejection. See claim 7’s 102 rejection.
Sabina teaches wherein the specified range includes one or more of a specified deviation of a mean value, a percent value, and a standard deviation. (Paragraph 165: For example, a quantitative confidence level “score” may be provided (e.g., using a number between, for example, 0-100, 0 to 1.0, -100 to 100, or scaled to any range of numeric values)” A person of ordinary skill in the art would consider “0-100” scale to be a percent value as it represents parts per 100. Furthermore, a person of ordinary skill in the art would see 0-1.0 decimal scale as an easily convertible scale as parts per 1 is proportional and convertible to parts per 100.)
As per claim 9
Sabina teaches all claim limitations previously rejected in claim 1’s 102 rejection. See claim 1’s 102 rejection.
Sabina teaches wherein the system is configured to automatically remove the identified outliers. (Paragraph 39 “In FIG. 3, the example image includes artifacts that are present outside of the teeth 1716; these may be removed or trimmed, based on the surface model 1718.” Paragraph 112 “For example, a method and/or apparatus that includes a 3D volumetric scan of the patient's teeth may be used to subtract out or remove from the 3D model of the teeth, any plaque, calculus and/or food debris that might be present at the time of the 3D scan. By digitally subtracting out any plaque, calculus, and/or food debris present, the volumetric information may be used with a virtual representation” Paragraph 149: “The user may set of adjust the threshold confidence level, including on the fly (e.g., making the threshold more or less stringent and showing the addition or removal of potential actionable dental features in response.” Artifacts, plaque, food debris, calculus, and or whatever doesn’t pass the confidence level of adjusted threshold are all outliers the system can automatically delete.)
As per claim 10
Sabina teaches all claim limitations previously rejected in claim 1’s 102 rejection. See claim 1’s 102 rejection.
Sabina teaches wherein the system is configured to enable the user to categorize the identified outliers (Paragraph 61 “) In general, the volumetric information may be annotated (e.g., marked, labeled, etc.) either automatically, manually, or semi-automatically, and this annotation may be displayed.” Paragraph 62 “As mentioned above any of these methods may include placing one or more markers on the volumetric model of the patient's teeth. Markers (e.g., flags, pins, etc.) may be manually placed by the user, or may be automatically placed by the apparatus, or may be semi-automatically placed (e.g., suggested by the system, configured by the user, etc.). This is described in greater detail below. As mentioned above any of these methods may include placing one or more markers on the volumetric model of the patient's teeth. Markers (e.g., flags, pins, etc.) may be manually placed by the user, or may be automatically placed by the apparatus, or may be semi-automatically placed (e.g., suggested by the system, configured by the user, etc.). This is described in greater detail below.” Paragraph 64 “For example, a user can mark a digital representation of the patient's teeth (or the patient's actual teeth) with a marker (e.g., a pin, flag, etc.) which can be annotated (e.g., can have notes associated with it).” User is able to manipulate an “annotate” outliers. Furthermore paragraphs 61-70 illustrate user being able to modify and annotate and label outliers that are presented to them automatically or semiautomatically.)
As per claim 11
Sabina teaches all claim limitations previously rejected in claim 1’s 102 rejection. See claim 1’s 103 rejection.
Sabina teaches wherein the system is configured to automatically correct an image (Paragraph 39: “Alternative views, sections, slices, projections or the like may be provided. In FIG. 3, the example image includes artifacts that are present outside of the teeth 1716; these may be removed or trimmed, based on the surface model 1718.” Deleting artifacts constitutes image correction. Furthermore, has stated that his system has the option of being automatic and or semiautomatic.)
As per claim 17
Sabina teaches all claim limitations previously rejected in claim 1’s 102 rejection. See claim 1’s 102 rejection.
Sabina teaches wherein the system is configured to automatically correct defective image (Paragraph 39: “Alternative views, sections, slices, projections or the like may be provided. In FIG. 3, the example image includes artifacts that are present outside of the teeth 1716; these may be removed or trimmed, based on the surface model 1718.” Deleting artifacts constitutes image correction. Furthermore, Sabina has stated that his system has the option of being automatic and or semiautomatic. An image with artefacts is essentially a defective image. )
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 12, 13, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Sabina et al (Sabina hereinafter US 10390913 B2) in view of Claessen et al (Claessen hereinafter US 11379975 B2)
As per claim 12
Sabina teaches all claim limitations previously rejected in claim 11’s 102 rejection. See claim 11’s 102 rejection
Claessen teaches correcting an image includes rotating and/or reflecting the image about one or more axes. (“Paragraph 42 “information about the position of the teeth and/or jaw and the orientation (e.g. a rotational angle) in the image volume may be determined by the computer. If the feature analysis function determines that the rotation angle is larger than a predetermined amount (e.g. larger than 15 degrees), the function may correct the rotation angle to zero as this is more beneficial for accurate results.” If an image has its rotational angle adjusted it is rotated. Furthermore, all rotations ins 3D space involve being rotated about an axis)
Accordingly, a person of ordinary skill in the art at the time this invention was effectively filed would have found it obvious to modify Sabina’s workflow with Claessen’s use of automatic image correction. A person of ordinary skill in the art understands that correcting an image of pose in both Claessen’s and Sabina’s 3D workflow is needed to register, realign and cement updates of anatomical images through time as well as correct the first iteration of said image in order to keep a consistent archive and pipeline of adjustment/updates.
As per claim 13
Sabina teaches all claim limitations previously rejected in claim 11’s 102 rejection. See claim 11’s 102 rejection.
Claessen teaches the system is configured to execute an axis evaluation using an axis artificial intelligence (AI) model. (Paragraph 21 “The 3D positional features may be determined using (manually) engineered features and/or using (trained) machine learning methods such as a 3D deep learning network configured to derive such information from the entire received 3D data set or a substantial part thereof.” Paragraph 40 “In an embodiment, the one or more 3D positional features may include a first 3D positional feature defining a relative distance in a plane in the image volume, preferably an axial plane in the image volume” Claessen states that 3D positional features may be determined using deep learning networks. The distance in an axial plane in the image volume between voxels is evaluated. The axis is therefore evaluated by the 3D deep learning network.)
As per claim 20
Sabina teaches all claim limitations previously rejected in claim 17’s 102 rejection. See claim 17’s 102 rejection.
Claessen teaches wherein the system is configured to display an indication that one or more images have been automatically corrected. (Figure 11A and 11B paragraph 73 “FIG. 11B depicts the result of the post-processing according the process as described with reference to FIGS. 9 and 10. As shown in this figure the post-processing deep learning neural network successfully removes artefacts that were present in the input data” the neural networks postprocessing is an automatic function and a generated display of artifact removal is a displayed indication of the correction which would be displayed on output device 1214 (see figure 12))
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Sabina et al (Sabina hereinafter US 10390913 B2) in view of Claessen et al (Claessen hereinafter US 11379975 B2) in further view of Kanezaki et al (Kanezaki hereinafter “RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints”)
As per claim 14
Sabina and Claessen teach all claim limitations previously rejected in claim 13’s 103 rejection. See claim 13’s 103 rejection
Sabina nor Claessen teach the axis Al model is configured to execute the axis evaluation by comparing a plurality of rotations of the image to an axis training set
Kanezaki teaches the axis Al model (Figure 1. “RotationNet”) is configured to execute the axis evaluation (Introduction “Our method automatically determines the basis axes of objects based on their appearance during the training and achieves not only intra-class but also inter-class object pose alignment.”) by comparing a plurality of rotations of the image to an axis training set (Figure 1-3, Section :”Viewpoint setups for training “ : “Note that the view obtained by rotating “view M” by the angle θ about the z-axis corresponds to “view 1.” We assume the sequence of input images is consistent with respect to a certain direction of rotation in the training phase.”)
Accordingly, a person of ordinary skill in the art at the time this invention was effectively filed would have found it obvious to further modify the Sabina/Claessen workflow to include an axis AI model that evaluates an axis by comparing a plurality of rotations of the image to an axis training set as taught by Kanezaki’s use of RotationNet. Claessen states “The 3D positional features may be determined using (manually) engineered features and/or using (trained) machine learning methods such as a 3D deep learning network configured to derive such information from the entire received 3D data set or a substantial part thereof”. A person of ordinary skill in the art understands that Kanezaki’s implementation of RotationalNet can be used as the machine learning method used to determine Claessen’s 3D positional features. A person of ordinary skill in the art would have been motivated to Kanezaki’s use of RotationNet to perform an axis evaluation because RotationNet teaches that object orientation can be determined by evaluating an input image against representations learned from a plurality of rotational viewpoints. An “axis evaluation” requires distinguishing among different orientations of an object or tissue, using multiple rotated examples in an axis training set would improve the accuracy and robustness of determining the appropriate axis despite variations in image acquisition modality and orientation.
Claim 18 and 19 is rejected under 35 U.S.C. 103 as being unpatentable over Sabina et al (Sabina hereinafter US 10390913 B2) in view of Claessen et al (Claessen hereinafter US 11379975 B2) in further view of Hein et al (Hein hereinafter US 20210012543 A1)
As per claim 18
Sabina teaches all limitations previously rejected in claim 17’s 102 rejection. See claim 17’s 102 rejection.
Sabina nor Claessen teach wherein the system is configured to execute an iteration of the defect analysis after the defective image is corrected.
Hein teaches wherein the system is configured to execute an iteration of the defect analysis after the defective image is corrected. (Fig 2, Paragraph [0072] “Multiple steps in methods 100 and 200 can be performed using DL networks, including steps 110 and 160 in method 100 and steps 214, 226, 254, and 266 in method 200” Paragraph [0071] “In step 280, a final check is performed on the image 272 to determine whether or not the artifact detection and correction processes have been successful in generating a clinically relevant image, or if the resultant image 272 still has artifacts and/or noise that might reasonably lead to a misdiagnosis” An iteration of the defect analysis is the detection of the defect itself. Hein’s final check step in 280 fulfills this.)
Accordingly, a person of ordinary skill in the art at the time this invention was effectively filed would have found it obvious to further modify the Sabina/Claessen pipeline to include a final check or a reanalysis of the defect analysis. Claessen states in paragraph 72 that “noise and other artefacts in the input data result in irregularities and artefacts in the voxel classification and hence 3D surface structures that include gaps in sets of voxels that represent a tooth structure”. A person of ordinary skill in the art can see that Hein’s artifact detection pipeline works in voxel space analysis just as the Sabina/Claessen pipeline does (See paragraphs [0088]-[0095] in Hein et al) and that a second iteration should be done for the advantage of refinement of subtle residual errors to eliminate secondary distortions possibly missed or even caused by the initial correction. A person of ordinary skill in the art would see this as being necessary when Sabina removes artifacts (Label 1716 in fig 3.) in their methodology to support Sabina’s accurate continuous updating of a dental tissue record and stitching of differing imaging modalities to ensure the best composite.
As per claim 19
Sabina teaches all limitations previously rejected in claim 17’s 102 rejection. See claim 17’s 102 rejection.
Hein teaches wherein the system is configured to remove the defective image and/or isolate the defective image if the defective image continues to be an outlier after the iteration. (Figure 2, the logic path of 280, 282 284 and 286 shows that after a final check, if the artifact is again found the image is diverted from storage (isolated) and presented to a user with an error)
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHANE WRENSFORD CODRINGTON whose telephone number is (571)272-8130. The examiner can normally be reached 8:00am-5pm.
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, Matthew Bella can be reached at (571) 272-7778. 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.
/SHANE WRENSFORD CODRINGTON/Examiner, Art Unit 2667
/MATTHEW C BELLA/Supervisory Patent Examiner, Art Unit 2667
Prosecution Insights