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 .
Drawings
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(4) because reference character “2328” in Figure 23B has been used to designate “Outputting the image data to a display”; “Generate dental chart showing teeth and associated oral conditions” and “Output dental chart to the display”. 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. 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.
Specification
The lengthy specification has not been checked to the extent necessary to determine the presence of all possible minor errors. Applicant’s cooperation is requested in correcting any errors of which applicant may become aware in the specification.
The disclosure is objected to because of the following informalities:
Paragraphs 138, 146, 147, 202, 211, 212, “centoenamel junction (CEJ)” should be “cementoenamel junction (CEJ)”
Paragraphs 294 and 860, “a oral health diagnostics system” should be “an oral health diagnostics system”.
Paragraph 377, “may be be” should be “may be”.
Paragraph 443, “that may receives as inputs” should be “that may receive as inputs”
Paragraph 532, “cemento-enamel junction (CEJ)” should be “cementoenamel junction (CEJ)”
Paragraph 534, “apical lesion segementer” should be “apical lesion segmenter”
Paragraph 538, “restoration segementer” should be “restoration segmenter”
Paragraph 551, “Based on these bone loss values, periodontal bone loss postprocessor” should be “Based on these bone loss values, the periodontal bone loss postprocessor”
Paragraph 620, “the another image type” should be “another image type”. It seems to be the most fitting with the context of the sentence in this case.
Paragraph 620, “For example, severity level of caries may be base on a size of the caries” should be “For example, severity level of caries may be based on a size of the caries”
Paragraph 631, “In case the contraints” should be “In case the constraints”
Paragraph 631, “most likely arangement of tooth numbers” should be “most likely arrangement of tooth numbers”
Paragraphs 708, 717, “the a training dataset’ should be “the training dataset” or “a training data set”
Paragraph 714, “annotated versions o the image” should be “annotated versions of the image”
Paragraph 734, “may include at block 2327” should be “may include block 2327”
Paragraph 758, “then an a minor instance of the oral condition” should be “then a minor instance of the oral condition”
Paragraph 851, “a oral health condition” should be “an oral health condition”
Appropriate correction is required.
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.
Claim 22 is 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.
The term “approximately equal” in claim 22 is a relative term which renders the claim indefinite. The term “approximately equal” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. Approximately equal is a relative term that renders the claim indefinite. A person can view values such as 0.99 and 1 as approximately equal. A similar person of ordinary skill in the art can view the values of 0.9 and 1 as approximately equal. The term is not clearly defined within the specification, and as such, the term renders the claim indefinite.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-22 and 25 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite a mental process accomplished via generic computer elements. This judicial exception is not integrated into a practical application because the disclosed computer elements are not sufficiently more. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the recited computer elements do not amount to significantly more. The recited computing device is comprised of a memory which is used to store programs and information which is the standard use of such a device along with one or more processing devices which would be a more generic disclosure of processors or something equivalent in function to processors which execute the programs stored in memory. The disclosed machine learning model is a generic disclosure of machine learning capabilities.
In regards to claim 1, A system comprising: A computing device comprising a memory and one or more processing devices, wherein the computing device is configured to: receive a radiograph of a dental site (A person of ordinary skill in the art can receive an image or radiograph of a dental site); process the radiograph using a segmentation pipeline to segment the radiograph into a plurality of constituent dental objects, wherein processing the radiograph using the segmentation pipeline comprises: processing the radiograph using one or more first models that generate one or more first outputs comprising one or more regions of interest associated with the plurality of constituent dental objects, the one or more first models comprising one or more first trained machine learning models (A person of ordinary skill in the art can segment an image by simply using a pencil upon the image or covering sections of the image with their hand, further a person can mentally designate certain areas as areas of interest including a number of dental objects); and processing the one or more regions of interest of the radiograph using a first plurality of additional models to generate a first plurality of additional outputs each comprising at least one of first identifications or first locations of at least a first subset of the plurality of constituent dental objects, the first plurality of additional models comprising a first plurality of additional trained machine learning models (A person of ordinary skill in the art can mentally identify various regions of interest or locations where certain dental objects are located); and generate a dental chart comprising the plurality of constituent dental objects (A person of ordinary skill in the art can create using a pencil and paper a chart of the dental objects based on the image that they saw).
In regards to claim 2, wherein the one or more regions of interest comprises a region of a jaw, and wherein the first subset of the plurality of constituent dental objects comprises a plurality of teeth in the jaw (A person of ordinary skill in the art can have the region of interest comprise of a section of jaw with the associated teeth).
In regards to claim 3, wherein the one or more regions of interest comprises regions of one or more teeth, and wherein the first subset of the plurality of constituent dental objects comprises at least one of caries, a periapical radiolucency, a restoration, or a periodontal bone loss location associated with the one or more teeth (A person of ordinary skill in the art can make an observation of tooth decay or a cavity or a restoration such as a crown along with identifying areas of periapical radiolucency in a radiograph).
In regards to claim 4, wherein the computing device is further configured to: determine a radiograph type of the radiograph from a plurality of radiograph types (A person of ordinary skill in the art can make a judgement on what kind of radiograph they are currently seeing or observe what kind of radiograph and be able to select what type from the plurality that they already know ); and select the segmentation pipeline from a plurality of distinct segmentation pipelines based on the radiograph type, wherein each of the plurality of distinct segmentation pipelines comprises a different combination of trained machine learning models (A person of ordinary skill in the art can mentally choose how they wish to segment a specific type of radiograph and can choose to use different methods of segmentation for each type).
In regards to claim 5, wherein the computing device is further configured to: process the radiograph using one or more second models that generate one or more second outputs comprising identifications and locations of a plurality of teeth of the plurality of constituent dental objects, the one or more second models comprising one or more second trained machine learning models that comprise a first segmentation model that performs semantic segmentation of the plurality of teeth in the radiograph and a second segmentation model that performs instance segmentation of the plurality of teeth in the radiograph (A person of ordinary skill in the art can segment an image in a way that identifies the various objects in the image and providing a semantic label and can define what each object’s class is).
In regards to claim 6, wherein the computing device is further configured to: determine, based on an output of at least one of the first segmentation model or the second segmentation model, tooth numbering of the plurality of teeth in the radiograph (A person of ordinary skill in the art can number the teeth in a radiograph either mentally or physically with pen and paper); determine whether the tooth numbering satisfies one or more constraints (A person of ordinary skill in the art can make sure that their numbering scheme satisfies some kind of constraint); and update the tooth numbering using a statistical model responsive to determining that the tooth numbering fails to satisfy the one or more constraints (A person of ordinary skill can use some kind of statistical model after determining a failure in the tooth numbering that fails a constraint of some kind).
In regards to claim 7, wherein the computing device is further configured to: for each output of the first plurality of additional outputs, perform postprocessing of the output based on data from the one or more second outputs to at least one of augment, verify or correct at least one of the first identifications or the first locations of at least the first subset of the plurality of constituent dental objects (A person of ordinary skill in the art can augment, verify, or correct their identification or location of a grouping of dental objects by double-checking their identification or location mentally or by providing further information on the identification or location).
In regards to claim 8, wherein the computing device is further configured to: combine postprocessed outputs of two or more of the first plurality of additional outputs (A person of ordinary skill in the art can combine two outputs on a piece of paper); and perform additional postprocessing on the combined postprocessed outputs to resolve any discrepancies therebetween, wherein the additional postprocessing is performed using a rules-based engine, and wherein performing the additional postprocessing comprises: identify one or more teeth that were classified both as having caries and as restorations (A person of ordinary skill can observe that a tooth or teeth have been classified as having both tooth decay and a restoration); and remove caries classifications for the one or more teeth (Further, this person of ordinary skill can remove such a classification or choose to do so).
In regards to claim 9, wherein the one or more second outputs comprise an assignment of tooth numbers to a plurality of teeth in the radiograph, and wherein the computing device is further configured to: process the one or more second outputs using at least one of a statistical model or one or more rules to at least one of verify or correct the assignment of the tooth numbers to the plurality of teeth of the radiograph (A person of ordinary skill in the art can mentally or physically use some form of statistical model or equation to verify or correct the numbering of the teeth in the radiograph).
In regards to claim 10, wherein processing the one or more second outputs comprises at least one of: identifying and removing any duplicate tooth numbers (A person of ordinary skill can identify duplicate numbers for the teeth and remove and replace them); removing one or more tooth identifications responsive to determining that more than 32 teeth were identified (A person of ordinary skill in the art can further identify that more than 32 teeth were identified and remove any more than that number); or updating tooth numbering assigned to one or more teeth responsive to determining that assigned tooth numbers are not left to right sorted and ordered (A person of ordinary skill can determine whether the numbers are properly sorted and ordered and update the numbers to see that it is done properly).
In regards to claim 11, wherein the computing device is further configured to: wait for a first one of the first plurality of additional outputs to be generated by a first one of the first plurality of additional trained machine learning models before processing an input comprising the radiograph and data from the one or more first outputs using a second one of the first plurality of additional trained machine learning models (A person of ordinary skill can wait for the output of a process before starting another process or simply by doing two processes in order), wherein the input for the second one of the first plurality of additional trained machine learning models further comprises data output by the first one of the first plurality of additional trained machine learning models (A person of ordinary skill can perform a process by using the output of a previous step that they performed or use it as input).
In regards to claim 12, wherein the computing device is further configured to: receive an additional data item generated from a second oral state capture modality (A person of ordinary skill in the art can receives additional data items); process the additional data item using one or more further trained machine learning models to generate one or more further outputs each comprising at least one of second identifications or second locations of at least a second subset of the plurality of constituent dental objects (A person of ordinary skill in the art can perform some kind of process to create further identifications or locations of a different subset of dental objects); and combine the one or more further outputs with the first plurality of additional outputs (A person of ordinary skill can further combine these outputs).
In regards to claim 13, wherein the computing device is further configured to: process the radiograph using a second trained machine learning model that generates a second output comprising at least one of an identification or a location of a mandibular nerve canal (A person of ordinary skill can identify from a radiograph the location or identification of the mandibular canal); determine locations of roots of one or more teeth (A person can observe the roots of some of the teeth); determine a distance between the mandibular nerve canal and the roots of the one or more teeth (A person can determine a distance between the mandibular canal and the roots); and responsive to determining that the distance is below a distance threshold for a tooth of the one or more teeth, generate a notice that a root of the tooth is near the mandibular nerve canal (A person of ordinary skill can determine that the distance is below a threshold as this is a form of judgement and create a notice via pen and paper or create a notice by taking note of it mentally).
In regards to claim 14, a system comprising: a computing device comprising a memory and one or more processing devices, wherein the computing device is configured to: receive a radiograph of a dental site (A person of ordinary skill in the art can receive an image or radiograph of a dental site); process the radiograph using a segmentation pipeline to identify a one or more oral conditions for the dental site, wherein processing the radiograph using the segmentation pipeline comprises: processing the radiograph using one or more first models that perform tooth segmentation, wherein the one or more first models generate a first output of tooth segmentation information comprising identifications and locations of a plurality of teeth in the radiograph (A person of ordinary skill can look at the received radiograph and identify and locate where the teeth are in the image); processing the radiograph using one or more second models that generate a second output comprising at least one of identifications or locations of the one or more oral conditions (A person of ordinary skill in the art can identify some oral condition or where the condition is inside of a radiograph); and performing postprocessing to combine the first output and the second output, wherein as a result of the postprocessing each of the one or more oral conditions is assigned to one or more teeth of the plurality of teeth in the radiograph (A person of ordinary skill in the art can further identify that there is an oral condition associated with certain teeth and assign them to the relevant teeth).
In regards to claim 15, wherein processing the radiograph using the one or more first models comprises: processing the radiograph using a first trained machine learning model that generates a first preliminary output comprising tooth numbers for the plurality of teeth according to physiological heuristics (A person of ordinary skill can use physiological heuristics or physiological rules to determine the numbering of the teeth); processing the radiograph using a second trained machine learning model that generates a second preliminary output comprising a jaw side associated with the radiograph (A person of ordinary skill can create an output comprising the jaw sides such as identifying if it is the left, right, upper, or lower jaw in the image); and processing an input comprising the radiograph, the first preliminary output and the second preliminary output using a third trained machine learning model to generate the first output (A person can further generate the first output, the numbering, based upon the prior numbering and the jaw side).
In regards to claim 16, it is similar to claim 4, and it is similarly rejected.
In regards to claim 17, wherein: the one or more oral conditions comprise caries and the one or more second models comprise a machine learning model trained to detect caries, wherein the machine learning model outputs caries segmentation information of one or more caries (A person of ordinary skill in the art can detect and identify tooth decay, cavities, or caries); the one or more oral conditions further comprise dentin and the one or more second models further comprise an additional machine learning model trained to detect dentin, wherein the additional machine learning model outputs dentin segmentation information (A person of ordinary skill in the art can identify or observe dentin in a radiograph); and performing the postprocessing further comprises: determining, for a tooth of the plurality of teeth, a distance between a caries on the tooth and the dentin of the tooth based on a comparison of the caries segmentation information and the dentin segmentation information (A person of ordinary skill can determine the distance between a cavity or tooth decay and the dentin by observing that the enamel has been pierced or worn down or not); and determining a severity of the caries for the tooth at least in part based on the distance (A person of ordinary skill make a judgement upon the severity of the tooth decay contingent on the state of the enamel or the position of the cavity in relation to the dentin).
In regards to claim 18, wherein performing the postprocessing further comprises: determining whether the caries penetrates the dentin for the tooth (A person of ordinary skill in the art can determine whether the dentin is penetrated by the cavities or caries); responsive to determining that the caries penetrates the dentin, classifying the caries for the tooth as a dentin caries (A person of ordinary skill in the art can identify if the dentin has been penetrated by the cavity and classify it as a dentin cavity); and responsive to determining that the caries does not penetrate the dentin, classifying the caries as an enamel caries (A person of ordinary skill in the art can identify if the dentin has not been penetrated by the cavity and classify it as an enamel cavity).
In regards to claim 19, wherein: the one or more oral conditions comprise caries and the one or more second models comprise a machine learning model trained to detect caries, wherein the machine learning model outputs caries segmentation information of one or more caries (A person of ordinary skill can identify caries or tooth decay); and the one or more second models further comprise an additional machine learning model trained to assign localization to caries, wherein the additional machine learning model is to receive as an input the caries segmentation information and to provide as an output one or more localization classes for one or more caries, wherein the one or more localization classes comprises at least one of tooth left surface, tooth right surface, tooth top surface, tooth mesial surface, tooth distal surface, tooth lingual surface, or tooth buccal surface (A person can further locate where the tooth decay is on the tooth and further identify which side of the tooth and classify it as such whether it be on the left, right, top, mesial, distal, lingual, or buccal sides).
In regards to claim 20, wherein the one or more oral conditions comprise one or more restorations and the one or more second models comprise a machine learning model trained to detect restorations (A person of ordinary skill can identify restorations to teeth), wherein the machine learning model outputs segmentation information of one or more restorations, wherein performing the postprocessing further comprises determining a restoration type for one or more of the detected restorations (A person of ordinary skill can further identify which kind of restoration is on the teeth).
In regards to claim 21, wherein determining the restoration type comprises: determining, based on the tooth segmentation information, a supporting tooth of the restoration (A person of ordinary skill can identify which teeth are supporting the restoration); determining that a size of the supporting tooth is greater than a size of the restoration (A person of ordinary skill can observe that the tooth is bigger than the restoration); and determining that the restoration is a crown (A person of ordinary skill can use the prior information to determine that the restoration is a crown).
In regards to claim 22, wherein determining the restoration type comprises: determining, based on the tooth segmentation information, that the restoration is associated with one or more teeth (A person of ordinary skill in the art can observe that the restoration is associated with one or more teeth); determining that a size of the restoration is approximately equal to a size of the one or more teeth (A person can determine if the restoration is roughly the same size as one or more teeth); and determining that the restoration is a bridge (A person of ordinary skill can use the prior information to determine that the restoration is a bridge).
In regards to claim 25, claim 25 acts as a linking claim for claims 1 and 14, it is rejected similarly to those claims.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-4, 7, 12, 14, 16, 23, and 25 are rejected under 35 U.S.C. 103 as being unpatentable over Golay et al. (US 20240212153 A1), hereinafter referred to as Golay, in view of Suri et al. (US 20240046456 A1), hereinafter referred to as Suri.
In regards to claim 1, Golay discloses a system comprising: A computing device comprising a memory and one or more processing devices, wherein the computing device is configured to: receive a radiograph of a dental site (Paragraphs 1, 48, and 82, Discloses that the invention is directed to a device that processes radiographs with paragraph 48 detailing the use of a processor and memory with paragraph 82 disclosing that the data is received which contains dental anatomy/teeth); process the radiograph using a segmentation pipeline to segment the radiograph into a plurality of constituent dental objects, wherein processing the radiograph using the segmentation pipeline comprises: processing the radiograph using one or more first models that generate one or more first outputs comprising one or more regions of interest associated with the plurality of constituent dental objects, the one or more first models comprising one or more first trained machine learning models (Paragraph 82 and the abstract, Paragraph 82 discloses that the process may entail segmentation of image to identify tooth structures, which would read upon constituent dental objects, which are then further sub-segmented to identify dentin/enamel/tissue saliva/ teeth spacing, and region of interest pixel data with the abstract detailing that one or more machine learning convolution neural networks detect specific dental conditions from sets of dental features or conditions); and processing the one or more regions of interest of the radiograph using a first plurality of additional models to generate a first plurality of additional outputs each comprising at least one of first identifications or first locations of at least a first subset of the plurality of constituent dental objects, the first plurality of additional models comprising a first plurality of additional trained machine learning models (Paragraph 82 and the abstract, Paragraph 82 discloses that “ML/AI convolution neural networks…. have been trained to identify specific dental anatomy conditions” such as caries, periodontal pocket depth, open diastema, stained teeth, inflamed gingivitis, along with other conditions with the abstract detailing that one or more machine learning convolution neural networks detect specific dental conditions from sets of dental features or conditions).
Golay does not explicitly disclose and generate a dental chart comprising the plurality of constituent dental objects.
However, Suri does explicitly disclose and generate a dental chart comprising the plurality of constituent dental objects (Abstract and paragraph 27, Suri discloses that the method contained can be used for automated dental charting of the system which attributes specific conditions to teeth within the chart).
It would be prima facie obvious to combine the teachings of Suri and Golay as it would be simple substitution. Golay discloses through prior art references in paragraphs 9 and 72 that it encompasses the charting systems disclosed in prior paragraphs as part of its own invention. However, Golay does not disclose their own unique charting system. As such, one could simply substitute the dental charting system of Suri with prior art references from Golay. As such, it would be prima facie obvious to combine.
In regards to claim 2, Golay discloses wherein the one or more regions of interest comprises a region of a jaw, and wherein the first subset of the plurality of constituent dental objects comprises a plurality of teeth in the jaw (Paragraph 92, Discloses that the regions of interest comprise various groupings of teeth which would be a region of the jaw).
In regards to claim 3, Golay discloses wherein the one or more regions of interest comprises regions of one or more teeth, and wherein the first subset of the plurality of constituent dental objects comprises at least one of caries, a periapical radiolucency, a restoration, or a periodontal bone loss location associated with the one or more teeth (Paragraph 92, Discloses that the teeth can have various restorations like fillings or crowns along with caries).
In regards to claim 4, Golay does not explicitly disclose wherein the computing device is further configured to: determine a radiograph type of the radiograph from a plurality of radiograph types; and select the segmentation pipeline from a plurality of distinct segmentation pipelines based on the radiograph type, wherein each of the plurality of distinct segmentation pipelines comprises a different combination of trained machine learning models.
However, Suri does disclose wherein the computing device is further configured to: determine a radiograph type of the radiograph from a plurality of radiograph types (Paragraph 108, Discloses that the specific type of radiograph is determined); and select the segmentation pipeline from a plurality of distinct segmentation pipelines based on the radiograph type, wherein each of the plurality of distinct segmentation pipelines comprises a different combination of trained machine learning models (Paragraph 109, Discloses that different models are used in the segmentation process based on each radiograph type).
It would be prima facie obvious to combine the disclosures of Suri and Golay as combining the two reference would allow for a predictable increase in accuracy. Suri’s method allows for the segmentation pipelines to compensate for the different varieties of radiograph. This allows the system to be able to handle and process different kinds of radiographs more accurately as the other methods of segmentation would allow for specific pipelines to be optimized for specific kinds of radiographs. As such, this would lead to a predictable increase in accuracy.
In regards to claim 7, Suri discloses wherein the computing device is further configured to: for each output of the first plurality of additional outputs, perform postprocessing of the output based on data from the one or more second outputs to at least one of augment, verify or correct at least one of the first identifications or the first locations of at least the first subset of the plurality of constituent dental objects (Paragraphs 69-75, The disclosed training process for the model functions as a way to verify the identifications of the conditions of the constituent dental objects).
In regards to claim 12, Suri discloses wherein the computing device is further configured to: receive an additional data item generated from a second oral state capture modality (Paragraphs 8-11, Discloses that additional data items along additional pipelines are generated); process the additional data item using one or more further trained machine learning models to generate one or more further outputs each comprising at least one of second identifications or second locations of at least a second subset of the plurality of constituent dental objects (Paragraphs 8-11, Discloses the use of multiple models which are used for identification and the location of various oral conditions); and combine the one or more further outputs with the first plurality of additional outputs (Paragraphs 8-11, Discloses that the first and second outputs are merged where the labeled teeth with conditions are identified and located on specific teeth).
In regards to claim 14, Golay discloses a system comprising: a computing device comprising a memory and one or more processing devices, wherein the computing device is configured to: receive a radiograph of a dental site (Paragraphs 1 and 48, Discloses that the invention is directed to a device that processes radiographs with paragraph 48 detailing the use of a processor and memory); process the radiograph using a segmentation pipeline to identify a one or more oral conditions for the dental site, wherein processing the radiograph using the segmentation pipeline comprises: processing the radiograph using one or more first models that perform tooth segmentation, wherein the one or more first models generate a first output of tooth segmentation information comprising identifications and locations of a plurality of teeth in the radiograph (Paragraph 82 and the abstract, Discloses that the image may be segmented to identify various dental structures such as teeth or their condition and regions of interest with the abstract disclosing the usage of machine learning models in this process).
Golay does not explicitly disclose processing the radiograph using one or more second models that generate a second output comprising at least one of identifications or locations of the one or more oral conditions; and performing postprocessing to combine the first output and the second output, wherein as a result of the postprocessing each of the one or more oral conditions is assigned to one or more teeth of the plurality of teeth in the radiograph.
Suri does disclose processing the radiograph using one or more second models that generate a second output comprising at least one of identifications or locations of the one or more oral conditions (Paragraphs 8-11, Discloses the use of multiple models which are used for identification and the location of various oral conditions); and performing postprocessing to combine the first output and the second output, wherein as a result of the postprocessing each of the one or more oral conditions is assigned to one or more teeth of the plurality of teeth in the radiograph (Paragraphs 8-11, Discloses that the first and second outputs are merged where the labeled teeth with conditions are identified and located on specific teeth).
It would be prima facie obvious to combine the disclosures of Suri and Golay as combining the two reference would allow for a predictable increase in accuracy. Suri’s method allows for the various oral conditions identified by Golay to be assigned to specific teeth. This allows the system to be able to accurately catalogue and sort the conditions out for each teeth aiding in the process of diagnosis and treatment. As such, this would lead to a predictable increase in accuracy.
In regards to claim 16, it is similar to claim 4, and it is similarly rejected.
In regards to claim 23, Golay discloses wherein the one or more second models comprise at least two of a first trained machine learning model trained to detect caries, a second trained machine learning model trained to detect calculus, or a third trained machine learning model trained to detect restorations (Paragraph 36, Discloses that sperate models may find caries, restorations, and calculus).
Golay does not explicitly disclose and wherein the computing device is further configured to: combine postprocessed outputs of the one or more second models; and perform additional postprocessing on the combined postprocessed outputs to resolve any discrepancies therebetween.
Suri does disclose and wherein the computing device is further configured to: combine postprocessed outputs of the one or more second models; and perform additional postprocessing on the combined postprocessed outputs to resolve any discrepancies therebetween (Paragraphs 8-11, Discloses that the first and second outputs are merged where the labeled teeth with conditions are identified and located on specific teeth).
In regards to claim 25, Golay does disclose a non-transitory computer readable medium comprises instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising: receiving a radiograph of a dental site (Paragraphs 1 and 48, Discloses that the invention is directed to a device that processes radiographs with paragraph 48 detailing the use of a processor and memory); processing the radiograph using a segmentation pipeline to identify a plurality of oral conditions for the dental site, wherein processing the radiograph using the segmentation pipeline comprises: processing the radiograph using one or more first models that perform tooth segmentation, wherein the one or more first models generate a first output of tooth segmentation information comprising identifications and locations of a plurality of teeth in the radiograph (Paragraph 82 and the abstract, Discloses that the image may be segmented to identify various dental structures such as teeth or the conditions of the teeth and regions of interest with the abstract disclosing the usage of machine learning models in this process)..
Golay does not explicitly disclose processing the radiograph using one or more second models that generate a second output comprising at least one of identifications or locations of the plurality of oral conditions; and performing postprocessing to combine the first output and the second output, wherein as a result of the postprocessing each of the plurality of oral conditions is assigned to one or more teeth of the plurality of teeth in the radiograph and generating a dental chart comprising the plurality of teeth and the plurality of oral conditions.
However, Suri does disclose processing the radiograph using one or more second models that generate a second output comprising at least one of identifications or locations of the plurality of oral conditions (Paragraphs 8-11, Discloses the use of multiple models which are used for identification and the location of various oral conditions); and performing postprocessing to combine the first output and the second output, wherein as a result of the postprocessing each of the plurality of oral conditions is assigned to one or more teeth of the plurality of teeth in the radiograph (Paragraphs 8-11, Discloses that the first and second outputs are merged where the labeled teeth with conditions are identified and located on specific teeth) and generating a dental chart comprising the plurality of teeth and the plurality of oral conditions (Abstract and paragraph 27, Suri discloses that the method contained can be used for automated dental charting of the system which attributes specific conditions to teeth within the chart).
It would be prima facie obvious to combine the disclosures of Suri and Golay as combining the two reference would allow for a predictable increase in accuracy. Suri’s method allows for the various oral conditions identified by Golay to be assigned to specific teeth. This allows the system to be able to accurately catalogue and sort the conditions out for each teeth aiding in the process of diagnosis and treatment. As such, this would lead to a predictable increase in accuracy.
Claims 5-6, 9-10, and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Golay et al. (US 20240212153 A1), hereinafter referred to as Golay, in view of Suri et al. (US 20240046456 A1), hereinafter referred to as Suri, as applied to claims 1-4, 7, 12, 14, 16, 23, and 25 above, and further in view of Ezhov et al. (US 20240029901 A1), hereinafter referred to as Ezhov.
In regards to claim 5, neither Golay nor Suri explicitly disclose the elements of this claim.
Ezhov does disclose wherein the computing device is further configured to: process the radiograph using one or more second models that generate one or more second outputs comprising identifications and locations of a plurality of teeth of the plurality of constituent dental objects, the one or more second models comprising one or more second trained machine learning models that comprise a first segmentation model that performs semantic segmentation of the plurality of teeth in the radiograph and a second segmentation model that performs instance segmentation of the plurality of teeth in the radiograph (Paragraph 123-125, Paragraphs 123-124 detail the use of semantic segmentation to locate and localize the teeth positions while paragraph 125 details a semantic segmentation module detailing the condition).
It would be prima facie obvious to combine the teachings of these prior arts. It would be simple substitution to implement the semantic segmentation and instance segmentation as Suri already teaches different segmentation pipelines. As such, one can simply substitute one of the pipelines of Suri with the instance segmentation, semantic segmentation, or both. As such, it would be prima facie obvious.
In regards to claim 6, Suri discloses wherein the computing device is further configured to: determine, based on an output of at least one of the first segmentation model or the second segmentation model, tooth numbering of the plurality of teeth in the radiograph (Paragraph 53, Discloses the usage of a tooth numbering system).
Ezhov discloses determine whether the tooth numbering satisfies one or more constraints (Paragraph 158, Discloses that if the teeth are not in the proper order, then they are resorted and ordered); and update the tooth numbering using a statistical model responsive to determining that the tooth numbering fails to satisfy the one or more constraints (Paragraph 158, Discloses that if the teeth are not in the proper order, then they are resorted and ordered).
In regards to claim 9, Ezhov discloses wherein the one or more second outputs comprise an assignment of tooth numbers to a plurality of teeth in the radiograph, and wherein the computing device is further configured to: process the one or more second outputs using at least one of a statistical model or one or more rules to at least one of verify or correct the assignment of the tooth numbers to the plurality of teeth of the radiograph (Paragraph 158, Discloses that if the teeth are not in the proper order, then they are resorted and ordered).
In regards to claim 10, Ezhov discloses or updating tooth numbering assigned to one or more teeth responsive to determining that assigned tooth numbers are not left to right sorted and ordered (Paragraph 158, Discloses that if the teeth are not in the proper order, then they are resorted and ordered).
In regards to claim 15, Suri discloses wherein processing the radiograph using the one or more first models comprises: processing the radiograph using a first trained machine learning model that generates a first preliminary output comprising tooth numbers for the plurality of teeth according to physiological heuristics (Paragraph 53, Discloses the usage of a tooth numbering system); and processing an input comprising the radiograph, the first preliminary output and the second preliminary output using a third trained machine learning model to generate the first output (Paragraph 53, This claim requires that the third model merely generates the first output which corresponds to the teeth numbers by the language of the claim as such, Suri discloses this).
Suri does not explicitly disclose processing the radiograph using a second trained machine learning model that generates a second preliminary output comprising a jaw side associated with the radiograph.
However, Ezhov does disclose processing the radiograph using a second trained machine learning model that generates a second preliminary output comprising a jaw side associated with the radiograph (Paragraph 149, The reference of Ezhov discloses that it identifies the upper and lower jaw bones which is within a BRI of the term jaw side).
It would be prima facie obvious to combine the teachings of the two arts as it would lead to a predictable increase in accuracy. Ezhov’s disclosure of keeping track of the jaw sides helps to prevent miscounting or misnumbering the various teeth. There are only so many teeth per side, and if the counting program misidentifies an object as a tooth, then the additional information from Ezhov allows for the program to recognize that the object was misnumbered or miscounted.
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Golay et al. (US 20240212153 A1), hereinafter referred to as Golay, in view of Suri et al. (US 20240046456 A1), hereinafter referred to as Suri, and Ezhov et al. (US 20240029901 A1), hereinafter referred to as Ezhov as applied to claims 5-6, 9-10, and 15 above, and further in view of Mathur et al. (US 20210174941 A1), hereinafter referred to Mathur.
In regards to claim 11, Golay, Suri, and Ezhov fail to explicitly disclose the elements of this claim.
However, Mathur does explicitly disclose wherein the computing device is further configured to: wait for a first one of the first plurality of additional outputs to be generated by a first one of the first plurality of additional trained machine learning models before processing an input comprising the radiograph and data from the one or more first outputs using a second one of the first plurality of additional trained machine learning models (Paragraphs 58, 64, 120, and 207, Discloses that the algorithms can wait for a response), wherein the input for the second one of the first plurality of additional trained machine learning models further comprises data output by the first one of the first plurality of additional trained machine learning models (Paragraphs 58, 64, 120, and 207, Discloses that the output of a task can then be further processed by as input for a further task).
It would be prima facie obvious to combine the teachings of the two arts as it is a known method applied to predictable results. Further processing or refining an output before inputting it into a further method is a well-understood concept in the art and beyond. As such, waiting for an output to be fully completed before trying to process that information is a known method being applied that leads to predictable results.
Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over Golay et al. (US 20240212153 A1), hereinafter referred to as Golay, in view of Suri et al. (US 20240046456 A1), hereinafter referred to as Suri as applied to claims 1-4, 7, 12, 14, 16, 23, and 25 above, and further in view of Elbaz et al. (US 20220202295 A1), hereinafter referred to as Elbaz.
In regards to claim 17, Golay discloses the one or more oral conditions further comprise dentin and the one or more second models further comprise an additional machine learning model trained to detect dentin, wherein the additional machine learning model outputs dentin segmentation information (Paragraph 82, Discloses that the dentin is identified).
Golay does not disclose any other elements of Claim 17.
Suri discloses wherein: the one or more oral conditions comprise caries and the one or more second models comprise a machine learning model trained to detect caries, wherein the machine learning model outputs caries segmentation information of one or more caries (Paragraph 49, Discloses the identification of caries).
Suri does not disclose any other elements of the claim.
However, Elbaz does disclose and performing the postprocessing further comprises: determining, for a tooth of the plurality of teeth, a distance between a caries on the tooth and the dentin of the tooth based on a comparison of the caries segmentation information and the dentin segmentation information (Paragraph 67, Discloses that the distance between the caries and dentin can be determined); and determining a severity of the caries for the tooth at least in part based on the distance (Paragraph 112, Discloses that the severity level may be based on the distance between the caries and the dentin).
It would be prima facie obvious to combine the prior arts as it would lead to predictable results via an improvement that was used in similar devices. Elbaz is a related art in the field of dental diagnosis, and as such, the system that Elbaz utilizes where there are levels of severity levels for the state of tooth decay allows for better diagnosis. Without the inclusion of this improvement, it would be up to individual dentists to visually identify the depth of the caries themselves and determine how severe it is. With this improvement, that process is automated. As such, it would be prima facie obvious to combine.
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Golay et al. (US 20240212153 A1), hereinafter referred to as Golay, in view of Suri et al. (US 20240046456 A1), hereinafter referred to as Suri, and in view of Elbaz et al. (US 20220202295 A1), hereinafter referred to as Elbaz as applied to claim 17 above, and further in view of Kim et al. (US 20250371702 A1), hereinafter referred to as Kim.
In regards to claim 18, Golay, Suri, and Elbaz do not explicitly disclose any part of the claim.
Kim discloses wherein performing the postprocessing further comprises: determining whether the caries penetrates the dentin for the tooth (Paragraph 121, Kim discloses classifying the severity of caries depending upon the depth); responsive to determining that the caries penetrates the dentin, classifying the caries for the tooth as a dentin caries (Paragraph 121, Kim determines if the caries extended to the dentin and it is classified as C2 in Kim’s disclosure); and responsive to determining that the caries does not penetrate the dentin, classifying the caries as an enamel caries (Paragraph 121, Kim determines if the cavity does not reach the dentin which is classified separately as C1).
It would be prima facie obvious to combine the prior arts as it would lead to predictable results via an improvement that was used in similar devices. Kim is a related art in the field of dental diagnosis, and as such, the system that Kim utilizes where there are levels of severity levels for the state of tooth decay allows for better diagnosis. Without the inclusion of this improvement, it would be up to individual dentists to visually identify the depth of the caries themselves and determine whether it had pierced the enamel or not. With this improvement, that process is automated. As such, it would be prima facie obvious to combine.
Claim 19 is rejected under 35 U.S.C. 103 as being unpatentable over Golay et al. (US 20240212153 A1), hereinafter referred to as Golay, in view of Suri et al. (US 20240046456 A1), hereinafter referred to as Suri, as applied to claims 1-4, 7, 12, 14, 16, 23, and 25 above, and further in view of Watson et al. (US 20240050193 A1), hereinafter referred to as Watson.
In regards to claim 19, Suri discloses wherein: the one or more oral conditions comprise caries and the one or more second models comprise a machine learning model trained to detect caries, wherein the machine learning model outputs caries segmentation information of one or more caries (Paragraph 49, Discloses the identification of caries).
Suri does not explicitly disclose and the one or more second models further comprise an additional machine learning model trained to assign localization to caries, wherein the additional machine learning model is to receive as an input the caries segmentation information and to provide as an output one or more localization classes for one or more caries, wherein the one or more localization classes comprises at least one of tooth left surface, tooth right surface, tooth top surface, tooth mesial surface, tooth distal surface, tooth lingual surface, or tooth buccal surface.
However, Watson does disclose and the one or more second models further comprise an additional machine learning model trained to assign localization to caries, wherein the additional machine learning model is to receive as an input the caries segmentation information and to provide as an output one or more localization classes for one or more caries, wherein the one or more localization classes comprises at least one of tooth left surface, tooth right surface, tooth top surface, tooth mesial surface, tooth distal surface, tooth lingual surface, or tooth buccal surface (Paragraph 9, Discloses that cavities or caries can be identified and classified as belonging to the buccal, lingual, or occlusal tooth surfaces).
It would be prima facie obvious to combine the teachings of the two arts as it would lead to a predictable increase in accuracy. Watson’s method allows for the location and localization of the caries/cavities/tooth decay to be more accurately categorized onto the various sides of a tooth’s surface which would more accurately reflect the position of the tooth decay over being broadly assigned to the whole tooth. As such, it would be prima facie obvious to combine.
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Golay et al. (US 20240212153 A1), hereinafter referred to as Golay, in view of Suri et al. (US 20240046456 A1), hereinafter referred to as Suri, as applied to claims 1-4, 7, 12, 14, 16, 23, and 25 above, and further in view of Farkash et al. ( US 20220189611 A1), hereinafter referred to as Farkash.
In regards to claim 20, Suri discloses wherein the one or more oral conditions comprise one or more restorations and the one or more second models comprise a machine learning model trained to detect restorations (Paragraph 49, Discloses the detection of restorations).
Suri does not explicitly disclose wherein the machine learning model outputs segmentation information of one or more restorations, wherein performing the postprocessing further comprises determining a restoration type for one or more of the detected restorations.
However, Farkash does disclose wherein the machine learning model outputs segmentation information of one or more restorations, wherein performing the postprocessing further comprises determining a restoration type for one or more of the detected restorations (Paragraph 67, Discloses that the model can identify the type of restoration out of a set amount of types).
It would be prima facie obvious to combine the teachings of the two arts as it would lead to a predictable increase in accuracy. Suri discloses the identification of restorations, but does not go so far as to individually classify them as specific kinds of restorations. Farkash does, and this provides increased accuracy as it allows for the specific restorations to be more easily categorized and to be more accurately reflected which would prevent errors from mislabeling the various forms of restoration. As such, it would be prima facie obvious to combine.
Claim 24 is rejected under 35 U.S.C. 103 as being unpatentable over Golay et al. (US 20240212153 A1), hereinafter referred to as Golay, in view of Suri et al. (US 20240046456 A1), hereinafter referred to as Suri, as applied to claims 1-4, 7, 12, 14, 16, 23, and 25 above, and further in view of Vandenberghe (US 2013094740 A1).
In regards to claim 24, Neither Golay nor Suri disclose the elements of this claim.
However, Vandenberghe does disclose wherein the one or more oral conditions comprise periapical radiolucency and the one or more second models comprise a machine learning model trained to detect periapical radiolucency, wherein the machine learning model outputs periapical radiolucency information, wherein performing the postprocessing further comprises: determining inflammation at apexes of a plurality of neighboring teeth based on the periapical radiolucency at the one or more teeth (Paragraphs 6 and 30, Discloses the identification of lesions at the root end or apex of the teeth with paragraph 30 identifying that these can be radiolucent lesions); and assigning a lesion to the plurality of teeth based on the determined inflammation and segmentation information of the plurality of teeth output by the one or more second models (Paragraph 46, Discloses that this inflammation/lesions can be associated with teeth).
It would be prima facie obvious to combine the teachings of the two arts as it would lead to a predictable increase in accuracy. The disclosure of tracking specific inflammation/lesions to specific teeth allows for it to be more accurately located by the specific teeth that are most relevant. As such, it would be prima facie obvious to combine.
Allowable Subject Matter
Claims 8, 13, and 21-22 are not rejected under 35 U.S.C. 102 or 25 U.S.C. 103.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Fischli et al. (US 20260183090 A1) is pertinent prior art that involves a similar system for dental diagnostics.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CONOR AIDAN O'MALLEY whose telephone number is (571)272-0226. The examiner can normally be reached Monday - Friday 9:00 am. - 5:00 pm. 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, Andrew Moyer can be reached at 5722729523. 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.
/CONOR A O'MALLEY/ Examiner, Art Unit 2675
/GREGORY A MORSE/ Supervisory Patent Examiner, Art Unit 2698
Prosecution Insights