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 .
Priority
Acknowledgment is made of applicant’s claim for domestic priority under 35 U.S.C. 119 (e)). For the purpose of examination, the priority date for claims 1-6, 10, 12, 17, 19-24 is 07/26/2022.
The “dental features” which correspond to the first and second sets of data as described in claims 13 and 15 are not supported by the disclosure of the provisional application (63392447), as only geometric features, intraoral and panoramic features are disclosed (refer to Paragraphs [0123], [0137]). For the purpose of examination, the priority date for claims 13 and 15 is 07/25/2023.
Specification
The specification is objected to as failing to provide proper antecedent basis for the claimed subject matter. See 37 CFR 1.75(d)(1) and MPEP § 608.01(o). Correction of the following is required:
The "dental features" which correspond to the first and second sets of data as described in claims 13 and 15 ; the disclosure references geometric features (702) (refer to Paragraph [0137]), intraoral and panoramic features (refer to Paragraph [0125]), but not dental features that correspond to the first and second sets of data from the 2D and 3D CNNs.
Claim Objections
Claim 13 is objected to because of the following informalities:
Line 3, "a first set of data" should be "the first set of data".
Appropriate correction is required.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-6, 10, 12-13, 15, 17, 19-23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kearney et al. (US 20210118132 A1), herein referred to as Kearney, in view of Sachdeva et al. (US 20080280247 A1), herein referred to as Sachdeva.
Regarding claim 1, Kearney discloses a method of generating a treatment plan for forming one or more dental appliances by determining coordinates of a tooth root apex of a tooth (refer to Abstract and Paragraphs [0466], [0483]; a machine learning model for taking orthodontic points, such as root apex points, to output a treatment plan and point clouds for retainers/appliances is disclosed), the method comprising:
obtaining patient data, wherein the patient data includes
obtaining a tooth number associated with the tooth (refer to Paragraphs [0082], [0468]; each tooth is assigned a tooth number, also referred to as a “mask”, which is received as input to generator (3902));
providing the patient data and the tooth number to a trained deep learning network (3900) (refer to Paragraphs [0199], [0209], [0468]; the generator (3902) takes an image (3910) with a corresponding tooth number mask as an input, wherein a variation of the deep learning system for forming a treatment protocol takes a plurality of labeled images from a plurality of 2D and 3D imaging modalities as inputs, concatenating them to form a single array representing the patient data), wherein the deep learning network is trained at least in part on cone beam computed tomography (CBCT) tooth data for a plurality of patients (refer to Paragraphs [0077], [0471]; each training data entry includes an image (3910) and data describing the features shown in the image (3910), masks, where each image is from a CBCT scan), wherein the CBCT tooth data includes segmented data with a label for each tooth number (refer to Paragraphs [0468], [0471]; the masks included with each image (3910) include tooth number), and tooth root apex coordinates associated with each tooth number (refer to Paragraphs [0471], [0476], [0483]; the training data entry includes target orthodontic points (3924), wherein the target orthodontic points include root apex points); and
determining, via a processor executing the trained deep learning network, the coordinates of [[a]] the tooth root apex based on the patient data and corresponding to the tooth number (refer to Paragraphs [0467], [0468], [0483]; the system (3900) generates orthodontic points (3932a-3932h) for each tooth number, based on the provided image (3910) and tooth number mask, wherein the orthodontic points (3932a-3932h) include a lower incisor root apex);
generating or modifying the treatment plan using the coordinates of the tooth root apex (refer to Paragraphs [0545], [0547]; an estimated treatment plan (4418) is generated based on the paired orthodontic points (4412)); and
forming one or more dental appliances according to the treatment plan (refer to Paragraph [0547]; each treatment plan (4418) comprises a point cloud defining a retainer).
Kearney does not disclose forming a physical dental appliance.
Sachdeva discloses a method of orthodontic treatment planning in the same field of endeavor (refer to Abstract), wherein the method includes forming one or more physical dental appliances according to the treatment plan for treating the patient (refer to Paragraph [0130]; the plan is transmitted to an appliance manufacturer for fabrication of the therapeutic devices).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Kearney with the step of forming a physical appliance as taught by Sachdeva to ultimately treat the patient based on the treatment plan (refer to Paragraph [0130]).
Regarding claim 2, Kearney and Sachdeva disclose the method of claim 1, with Kearney further disclosing wherein the patient data includes a first set of data (3912) and a second set of data (3914), wherein the first set of data (3912) is generated from using
Regarding claim 3, Kearney and Sachdeva disclose the method of claim 2, with Kearney further disclosing wherein the 2D convolutional neural network is trained based at least in part on the
Regarding claim 4, Kearney and Sachdeva disclose the method of claim 1, with Kearney further disclosing wherein the patient data includes a first set of data (3912) and a second set of data (3914), wherein the first set of data (3912) is generated from using
Regarding claim 5, Kearney and Sachdeva disclose the method of claim 4, with Kearney further disclosing wherein the 3D convolutional neural network is trained based at least in part on the CBCT tooth data (refer to Paragraphs [0077], [0147]; the training algorithm (702) inputs include an image (704), with patient images including CBCT scan images).
Regarding claim 6, Kearney and Sachdeva disclose the method of claim 1, with Kearney further disclosing wherein the tooth number selectively weights an output of the deep learning network (refer to Paragraphs [0413], [0415]; alternative machine learning model (3400), a GAN or deep-learning model, selectively places non-zero pixels at positions which represent the tooth number to output a synthetic image, thereby selectively weighing by tooth number).
Regarding claim 10, Kearney discloses a system (4400), the system comprising:
a treatment plan generator engine (4402; refer to Paragraph [0547]; the encoder (4402) of the system (4400) outputs an estimated treatment plan (4418)) configured to:
obtain, from a memory, patient data, wherein the patient data includes
provide the 2D panoramic radiographic data to a first learning model (700) that is trained at least in part on cone beam computed tomography (CBCT) tooth data for a plurality of patients to generate a first set of data (3912) (refer to Paragraphs [0077], [0146]-[0147], Fig. 7; the teeth labels are output according to a convolutional neural network system (700), which accepts an image input (704), wherein patient images include panoramic X-rays; the training algorithm (702) inputs also include an image (704), wherein patient images include CBCT scan images); and
provide the 3D intraoral scan data to a second learning model (800) that is trained at least in part on the CBCT tooth data to generate a second set of data (3914) (refer to Paragraphs [0077], [0162]-[0163], Fig. 8; the anatomical feature labels are output according to a convolutional neural network system (800), which accepts an image input (804a), wherein patient images include intraoral image capture; the training algorithm (802) inputs also include an image (804a), wherein patient images include CBCT scan images);
combine the first and second sets of data (refer to Paragraph [0468]; the image (3910) is concatenated with the masks (3912), (3914));
obtain, from the memory, a tooth number associated with a tooth (refer to Paragraphs [0082], [0468], [0544] ; the computing device memory (4504) is configured to be used with the disclosed methods and systems; a tooth mask (4406), which is defined according to the masks of other embodiments is received as input to the treatment plan generator (4400), wherein the embodiment of Fig. 39A defines a tooth mask as including the tooth number; therefore, the treatment plan generator (4400) is capable of receiving a tooth number from a memory based on the computer program executing this instruction); and
provide the combined first and second sets of wherein the trained deep learning network (3900) is trained on segmented data that includes segmented teeth with labels for each of the segmented teeth and tooth root apex coordinates associated with each of the segmented teeth (refer to Paragraphs [0471], [0476], [0483]; training entries include the masks (3912, 3914), which are labels for the individual teeth in the input image (3910), and target orthodontic points (3924), wherein the target orthodontic points include root apex points); [[and]]
a processor (4502) configured to determine, via the trained deep learning network, coordinates of a tooth root apex of the tooth based on the patient data and corresponding to the tooth number (refer to Paragraphs [0467], [0468], [0483]; the system (3900) generates lower incisor root apex orthodontic points (3932a-3932h) for each tooth number, based on the provided image (3910) and masks (3912, 3914), wherein the masks (3912), (3914) are based on the patient data),
wherein the treatment plan generator engine (4400) is configured to use the coordinates of the tooth root apex to generate or modify a treatment plan (refer to Paragraphs [0466], [0545]; the orthodontic points (3932a-3932h) are used to plan orthodontic tooth movement by the encoder (4402) of the treatment plan system (4400)).
Kearney does not disclose an appliance fabrication subsystem configured to fabricate one or more physical appliances from the treatment plan.
Sachdeva discloses a system of orthodontic treatment planning in the same field of endeavor (Fig. 20), wherein the system (Fig. 20) includes an appliance fabrication subsystem configured to fabricate one or more physical appliances from the treatment plan (refer to Paragraph [0134]; the appliance design data sets are furnished over the internet to a vendor for manufacture of a custom appliance).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified the system of Kearney with the appliance fabrication subsystem as taught by Sachdeva to manufacture the custom appliances to treat the patient (refer to Paragraph [0134]).
Regarding claim 12, Kearney discloses a non-transitory computer-readable storage medium (4508) comprising instructions that, when executed by one or more processors (4502) of a system (4500), cause the system (4500) to perform operations comprising (refer to Paragraphs [0552]- [0553]; the computer-readable mediums stores the program instructions for any of the disclosed inventions, which are then executed by one or more processors (4502)) :
obtaining patient data, wherein the patient data includes
providing the 2D panoramic radiographic data to a first learning model (700) that is trained at least in part on cone beam computed tomography (CBCT) tooth data for a plurality of patients to generate a first set of data (3912) (refer to Paragraphs [0077], [0146]-[0147], Fig. 7; the teeth labels are output according to a convolutional neural network system (700), which accepts an image input (704), wherein patient images include panoramic X-rays; the training algorithm (702) inputs also include an image (704), wherein patient images include CBCT scan images); and
providing the 3D intraoral scan data to a second learning model (800) that is trained at least in part on the CBCT tooth data to generate a second set of data (3914) (refer to Paragraphs [0077], [0162]-[0163], Fig. 8; the anatomical feature labels are output according to a convolutional neural network system (800), which accepts an image input (804a), wherein patient images include intraoral image capture; the training algorithm (802) inputs also include an image (804a), wherein patient images include CBCT scan images);
combining the first and second sets of data (refer to Paragraph [0468]; the image (3910) is concatenated with the masks (3912), (3914));
obtaining a tooth number associated with a tooth (refer to Paragraphs [0082], [0468]; a mask, which includes a labeled image for each tooth number, is received as input to generator (3902));
providing the combined first and second sets of wherein the trained deep learning network (3900) is trained on segmented data that includes segmented teeth with labels for each of the segmented teeth and tooth root apex coordinates associated with each of the segmented teeth (refer to Paragraphs [0471], [0476], [0483]; training entries include the masks (3912, 3914), which are labels for the individual teeth in the input image (3910), and target orthodontic points (3924), wherein the target orthodontic points include root apex points); and
determining, via a processor executing the trained deep learning network, [[the]] coordinates of a tooth root apex of the tooth based on the combined first and second sets of
generating or modifying [[the]] a treatment plan using the coordinates of the tooth root apex (refer to Paragraphs [0545], [0547]; an estimated treatment plan (4418) is generated based on the paired orthodontic points (4412) from the system in Fig. 39A (3900));
and
forming one or more dental appliances according to the treatment plan (refer to Paragraph [0547]; each treatment plan (4418) comprises a point cloud defining a retainer).
Kearney does not disclose forming a physical dental appliance.
Sachdeva discloses a method of orthodontic treatment planning executed by a system (100) with a computer storage medium (22) in the same field of endeavor (refer to Abstract, Paragraph [0057]), wherein the method includes forming one or more physical dental appliances according to the treatment plan for treating the patient (refer to Paragraph [0130]; the plan is transmitted to an appliance manufacturer for fabrication of the therapeutic devices).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Kearney with the step of forming a physical appliance as taught by Sachdeva to ultimately treat the patient based on the treatment plan (refer to Paragraph [0130]).
Regarding claim 13, Kearney and Sachdeva disclose the non-transitory computer-readable storage medium of claim 12, with Kearney further disclosing wherein the first learning model (700) is a 2D convolutional neural network configured to determine a first set of data (3912) from the 2D panoramic radiograph data of the patient (704), wherein the first set of data (3912) corresponds to a first set of dental features (tooth number) (refer to Paragraphs [0077], [0147], Fig. 7; the tooth labels (706a) are output according to a convolutional neural network system (700), which accepts panoramic X-rays as the image input (704)).
Regarding claim 15, Kearney and Sachdeva disclose the non-transitory computer-readable storage medium of claim 12, with Kearney further disclosing wherein the second learning model (800) is a 3D convolutional neural network configured to determine the second set of data (3914) from the 3D intraoral scan data of the patient (804a), wherein the second set of data (3914) corresponds to a second set of dental features (anatomical feature of interest) (refer to Paragraphs [0077], [0162]-[0163], [0175], Fig. 8; the anatomical feature labels are output according to a convolutional neural network system (800), which operates on three-dimensional images (804a), with intraoral image capture being one of the 3D image inputs (804a))
Regarding claim 17, Kearney and Sachdeva disclose the non-transitory computer-readable storage medium of claim 12, with Kearney further disclosing wherein the tooth number selectively weights an output of the deep learning network (refer to Paragraphs [0413], [0415]; alternative machine learning model (3400), a GAN or deep-learning model, selectively places non-zero pixels at positions which represent the tooth number to output a synthetic image, thereby selectively weighing by tooth number).
Regarding claim 19, Kearney and Sachdeva disclose the non-transitory computer-readable storage medium of claim 12, with Kearney further disclosing wherein the deep learning network is trained based at least in part on the cone beam computed tomography (CBCT) tooth data and 2D panoramic radiograph data corresponding to the CBCT tooth data (refer to Paragraphs [0077], [0125], [0128]; embodiments of training algorithm (602) are alternatively trained by paired images (604, 606) from two different imaging modalities, wherein the different imaging modalities include CBCT and panoramic X-ray; as the generator (3902) used to generate orthodontic points can also be configured according to any attribute of other disclosed generators, the alternative training algorithm (602) can be configured in the generator (3902)).
Regarding claim 20, Kearney and Sachdeva disclose the non-transitory computer-readable storage medium of claim 12, wherein the deep learning network is trained based at least in part on the CBCT tooth data and 3D intraoral scan data corresponding to the CBCT tooth data (refer to Paragraph [0077], [0125], [0128]; some embodiments of training algorithm (602) are alternatively trained by paired images (604, 606) from two different imaging modalities, wherein the different imaging modalities include CBCT and three-dimensional optical imaging, wherein an optical camera is disclosed as performing intra-oral capture; as the generator (3902) used to generate orthodontic points can also be configured according to any attribute of other disclosed generators, the alternative training algorithm (602) can be configured in the generator (3902)).
Regarding claim 21, Kearney and Sachdeva disclose the method of claim 1, with Kearney further disclosing wherein the deep learning network (3900) is trained by;
provide the 2D panoramic radiographic data to a first learning model (700) that is trained at least in part on cone beam computed tomography (CBCT) tooth data for a plurality of patients to generate a first set of data (3912) (refer to Paragraphs [0077], [0146]-[0147], Fig. 7; the teeth labels are output according to a convolutional neural network system (700), which accepts an image input (704), wherein patient images include panoramic X-rays; the training algorithm (702) inputs also include an image (704), wherein patient images include CBCT scan images); and
provide the 3D intraoral scan data to a second learning model (800) that is trained at least in part on the CBCT tooth data to generate a second set of data (3914) (refer to Paragraphs [0077], [0162]-[0163], Fig. 8; the anatomical feature labels are output according to a convolutional neural network system (800), which accepts an image input (804a), wherein patient images include intraoral image capture; the training algorithm (802) inputs also include an image (804a), wherein patient images include CBCT scan images);
combine the first and second sets of data (refer to Paragraph [0468]; the image (3910) is concatenated with the masks (3912), (3914));
wherein providing the patient data and the tooth number to the trained deep learning network comprises providing the combined first (3912) and second sets of a data (3914) and the tooth number to the trained deep learning network (3900; refer to Paragraphs [0147], [0468]; the resulting concatenated image (3910) is provided to the generator (3902), where the concatenated image includes a tooth number mask)
Regarding claims 22-23, Kearney and Sachdeva disclose the non-transitory computer-readable storage medium of claim 12, with Kearney further disclosing wherein the operations further comprise comparing the 2D panoramic radiographic data or 3D intraoral scan data to the CBCT tooth data to ensure both data sets share a common coordinate system (refer to Paragraphs [0077], [0125], [0395]; one of the two images used for comparison (3204b) is obtained by transforming the image (3204b); a disclosed image transformation machine learning system (600) transforms between any two-dimensional imaging modality and any one of the three-dimensional modalities (panoramic X-ray and CBCT) or between two different three-dimensional modalities (CBCT and 3D intra-oral imaging); transforming the image ensures a common coordinate system is shared between the two images) and that the data sets match each other within a tolerance amount (refer to Paragraph [0392], Fig. 32; labeled images (3204a, 3204b) are input into a machine learning model (3200), with the image values (3222a, 3222b) being compared to obtain a comparison value (3224); a zero comparison value is the threshold value that indicates the images are not a match).
Claim(s) 24 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kearney et al. (US 20210118132 A1), herein referred to as Kearney, in view of Sachdeva et al. (US 20080280247 A1), herein referred to as Sachdeva as applied to claim 12 above, and further in view of Kitching et al. (US 20080294405 A1), herein referred to as Kitching.
Regarding claim 24, Kearney and Sachdeva disclose the non-transitory computer-readable storage medium of claim 12, with Kearney further disclosing wherein the first learning model (700) minimizes a loss function between a tooth apex from the CBCT data and a predicted tooth apex based on the 2D panoramic data (refer to Paragraph [0156]; a loss function (LF3) is evaluated based on the synthetic label output by the classifier (718) and the tooth label (706a) paired with the image (704) processed at Step 1, where the output of the loss function (LF3) decreases, or is minimized, with increasing similarity of the synthetic label output and the tooth label (706a); the labels (706a) correspond to a predicted tooth label based on the input panoramic X-ray data; the synthetic labels are generated by the classifier (718) based on the CBCT data used for training the model (700)).
Kearney discloses that the tooth labels indicate the portion of an image estimated to include a tooth for diagnostic and treatment purposes (refer to Paragraphs [0146], [0149]); but does not disclose the tooth labels including a tooth apex.
Kitching discloses a method executed by a computing device readable medium for tooth modeling in the same field of endeavor (refer to Paragraphs [0031]-[0032]), wherein the method includes labeling the tooth apex as a reference point (370-9, 370-10) (refer to Paragraph [0058], Fig. 3A), which allows the user to identify missing or partially erupted teeth for treatment purposes (refer to Paragraphs [0033], [0035]).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified the method executed by the computer readable medium as taught by Kearney with the tooth apex labels as taught by Kitching in order to identify missing or partially erupted teeth for treatment purposes (refer to Paragraphs [0033], [0035]).
Response to Arguments
The outstanding 35 U.S.C. 101 rejection is withdrawn in view of the newly submitted claim amendments to include forming a physical dental appliance.
Applicant's arguments filed 11/17/2025 have been fully considered but they are not persuasive.
As described in the above rejection, Kearney teaches the amended claim language, with the exception of the forming of the physical dental appliances, for which Sachdeva is referenced, and the loss function between a tooth apex, which relies on the combination of Kearney and Kitching.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Adriena J Webb Lyttle whose telephone number is (571)270-7639. The examiner can normally be reached Mon - Fri 8:00-5:00 EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Eric Rosen can be reached at (571) 270-7855. 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.
/ADRIENA J WEBB LYTTLE/Examiner, Art Unit 3772
/THOMAS C BARRETT/SPE, Art Unit 3799
Prosecution Insights