DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 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(s) 38 is/are 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 38 recites the limitation "the dictation device” in line 2. There is insufficient antecedent basis for this limitation in the claim. Appropriate clarification is requested for the proper interpretation of the claim limitations, as the ambiguity renders the metes and bounds of the claim unclear. For examination purposes, Examiner interprets “the dictation device” as: “a dictation device.”
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/process/file/efs/guidance/eTD-info-I.jsp.
Claims 21-40 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-17 of U.S. Patent No. 11,342,055. Although the claims at issue are not identical, they are not patentably distinct from each other because both sets of claims are directed toward a method for automatically generating an impression section of a radiology report, the method comprising: receiving, at a computing system: a string of text from the findings section of the radiology report, the string of text comprising a set of finding words; at the computing system and with a trained machine learning model, automatically: determining a radiologist style based on a radiologist identifier of a radiologist, wherein the radiologist style is determined based on a set of features of impression sections in a historical report previously generated by the radiologist: determining, with the trained machine learning model, a context based on the set of finding words; combining the context with the radiologist style; generating, with the trained machine learning model, the impression section, wherein the generated impression section is configured to mimic the radiologist style; and automatically inserting the impression section into the radiology report as a proposed impression section.
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.
Claim(s) 21-40 is/are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more. Based upon consideration of all of the relevant factors with respect to the claims as a whole, the claims are directed to non-statutory subject matter which do not include additional elements that are sufficient to amount to significantly more than the judicial exception because of the following analysis:
Claim 21 is drawn to a method which is within the four statutory categories (i.e., method). Claim 34 is drawn to a system which is within the four statutory categories (i.e., machine).
Independent claim 21 recites…receiving…a string of text from the findings section of the radiology report, the string of text comprising a set of finding words; …determining a radiologist style based on a radiologist identifier of a radiologist, wherein the radiologist style is determined based on a set of features of impression sections in a historical report previously generated by the radiologist: determining…a context based on the set of finding words; combining the context with the radiologist style; generating…the impression section, wherein the generated impression section is configured to mimic the radiologist style; and automatically inserting the impression section into the radiology report as a proposed impression section.
Independent claim 34 recites… receiving a string of text from the findings section of the radiology report, the string of text comprising a set of finding words; and…determining a radiologist style based on a radiologist identifier of a radiologist, wherein the radiologist style is determined based on features of impression sections in a historical report previously generated by the radiologist; and generating…the impression section based on the radiologist style, wherein the impression section is configured to mimic the radiologist style; and automatically inserting the impression section into the radiology report as a proposed impression section.
Under its broadest reasonable interpretation, the limitations noted above, as drafted, covers certain methods of organizing human activity (i.e., managing personal behavior or relationships or interactions between people…following rules or instructions), but for the recitation of generic computer components. That is, other than reciting a “computing system,” the claim encompasses rules or instructions to help a user (i.e., radiologist) write a report, which is described as human activity in ¶ 0003-0004 of the specification If a claim limitation, under its broadest reasonable interpretation, covers managing personal behavior or relationships or interactions between people, but for the recitation of generic computer components, then it falls within the “Certain Methods of Organizing Human Activity” grouping of abstract ideas. Accordingly, the claims recite an abstract idea.
Claim 21 recites additional elements (i.e., a computing system; a trained machine learning model). Claim 34 recites additional elements (i.e., a computing system; a trained machine learning model). Looking to the specifications, a computing system is described at a high level of generality (¶ 0026; ¶ 0042-0044), such that it amounts to no more than mere instructions to apply the exception using generic computer components. Also, a “trained machine learning model” is only used to generally apply the abstract idea without placing any limits on how the trained machine learning model functions and only recite the outcome of the abstract idea and does not include details about how “determining…a context based on the set of finding words” and “generating…the impression section, wherein the generated impression section is configured to mimic the radiologist style” is accomplished, and thus, provide nothing more than mere instructions to implement an abstract idea on a generic computer, and merely indicates a field of use or technological environment (i.e., machine learning) in which the judicial exception is performed. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements individually. The additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Accordingly, the claims are directed to an abstract idea.
Reevaluated under step 2B, the additional elements noted above do not provide “significantly more” when taken either individually or as an ordered combination. The use of a general purpose computer or computers (i.e., a computing system) amounts to no more than mere instructions to apply the exception using generic computer components and does not impose any meaningful limitation on the computer implementation of the abstract idea, so it does not amount to significantly more than the abstract idea. Also, a “trained machine learning model” is only used to generally apply the abstract idea without placing any limits on how the trained machine learning model functions and only recite the outcome of the abstract idea and does not include details about how “determining…a context based on the set of finding words” and “generating…the impression section, wherein the generated impression section is configured to mimic the radiologist style” is accomplished, and thus, provide nothing more than mere instructions to implement an abstract idea on a generic computer, and merely indicates a field of use or technological environment (i.e., machine learning) in which the judicial exception is performed. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements individually. The combination of elements does not indicate a significant improvement to the functioning of a computer or any other technology and their collective functions merely provide a conventional computer implementation of the abstract idea. Furthermore, the additional elements or combination of elements in the claims, other than the abstract idea per se, amount to no more than a recitation of generally linking the abstract idea to a particular technological environment or field of use, as the courts have found in Parker v. Flook; similarly, the current invention merely limits the claimed calculations to the healthcare industry which does not impose meaningful limits on the scope of the claim. Therefore, there are no limitations in the claims that transform the judicial exception into a patent eligible application such that the claims amount to significantly more than the judicial exception.
Dependent claims 22-33, 35-40 include all the limitations of the parent claims and further elaborate on the abstract idea discussed above and incorporated herein.
Claims 22, 28-33, 39 further define the analysis and organization of data for the performance of the abstract idea and do not recite any additional elements. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements individually. Thus, the claims do not integrate the abstract idea into a practical application and do not provide “significantly more.”
Claims 23, 38 further recite the additional elements of a “dictation device,” which only invokes the dictation device merely as a tool in its ordinary capacity to perform an existing process (i.e., generating text), which does not impose meaningful limits on the scope of the claim and amounts to no more than a recitation of the words "apply it" (or an equivalent), and only generally links the claimed invention to a particular technological environment or field of use, which does not impose meaningful limits on the scope of the claim. Also, functional limitations further define the analysis and organization of data for the performance of the abstract idea. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements individually. Thus, the claims as a whole do not integrate the abstract idea into a practical application and do not provide “significantly more.”
Claims 24, 36 further recite the additional elements of “wherein the trained machine learning model comprises a decoder.” Claim 25 further recites the additional elements of “wherein the trained machine learning model comprises a multi-transformer model.” Claims 26, 35 further recites the additional elements of “wherein the trained machine learning model comprises a natural language processing (NLP) model.” However, a “decoder,” “multi-transformer model,” and “natural language processing (NLP) model” is only used to generally apply the abstract idea without placing any limits on how the trained machine learning model functions and only recite the outcome of the abstract idea and does not further include details about how “determining…a context based on the set of finding words” and “generating…the impression section, wherein the generated impression section is configured to mimic the radiologist style” is accomplished, and thus, provide nothing more than mere instructions to implement an abstract idea on a generic computer, and merely indicates a field of use or technological environment (i.e., machine learning) in which the judicial exception is performed. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements individually. Thus, the claims as a whole do not integrate the abstract idea into a practical application and do not provide “significantly more.”
Claims 27, 40 further recite the additional elements of a “a user interface, wherein the user interface comprises a navigation device,” which only invokes the user interface and navigation device merely as a tool in its ordinary capacity to perform an existing process (i.e., presenting output and receiving input), which does not impose meaningful limits on the scope of the claim and amounts to no more than a recitation of the words "apply it" (or an equivalent), and only generally links the claimed invention to a particular technological environment or field of use, which does not impose meaningful limits on the scope of the claim. Also, functional limitations further define the analysis and organization of data for the performance of the abstract idea. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements individually. Thus, the claims as a whole do not integrate the abstract idea into a practical application and do not provide “significantly more.”
Claim 37 further recites the additional elements of “a database, wherein the database comprises at least one of: a Picture Archiving and Communication System (PACS), an electronic medical record (EMR) database, an electronic health record (EHR) database, or a Radiology Information System (RIS),” which only invokes the database merely as a tool in its ordinary capacity to perform an existing process (i.e., interface with a computing system), which does not impose meaningful limits on the scope of the claim and amounts to no more than a recitation of the words "apply it" (or an equivalent), and only generally links the claimed invention to a particular technological environment or field of use, which does not impose meaningful limits on the scope of the claim. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements individually. Thus, the claims as a whole do not integrate the abstract idea into a practical application and do not provide “significantly more.”
Although the dependent claims add additional limitations, they only serve to further limit the abstract idea by reciting limitations on what the information is and how it is received and used. These information characteristics do not change the fundamental analogy to the abstract idea grouping of “Certain Methods of Organizing Human Activity,” and, when viewed individually or as a whole, they do not add anything substantial beyond the abstract idea. Furthermore, the combination of elements does not indicate a significant improvement to the functioning of a computer or any other technology. Therefore, the claims when taken as a whole are ineligible for the same reasons as the independent 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.
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.
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.
Claim(s) 21-40 is/are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent App. Pub. No. US 2013/0290031 A1 (hereinafter referred to as "Kay") in view of “Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation” (hereinafter referred to as "Dai").
Regarding (new) claim 21, Kay teaches a method for automatically generating an impression section of a radiology report, the method comprising:
receiving, at a computing system (Kay: ¶ 0097):
a string of text from the findings section of the radiology report, the string of text comprising a set of finding words (Kay: ¶ 0056-0057);
at the computing system and with a trained…model (Kay: ¶ 0032, i.e., Examiner interprets the association of the template “based on the institution, the reading radiologist, and the study description” as the claimed trained model), automatically:
determining a radiologist style based on a radiologist identifier of a radiologist (Kay: ¶ 0049, i.e., “different macros are available to the radiologist based on the template being used to create the report”; ¶ 0067-0068), wherein the radiologist style is determined based on a set of features of impression sections in a historical report previously generated by the radiologist (Kay: ¶ 0067, i.e., “the entries that the radiologist has dictated for each field are recorded in a database. When that same template is later used by that same radiologist, those previous entries are accessed. When a particular field is selected, not only are the macro choices for that field made available to the radiologist, but also the text that the radiologist has previously dictated in that field in connection with other previous studies”; ¶ 0068, i.e., “the phrases are sorted to provide the radiologist with the most recently used phrases at the top of the list and the least recently used phrases towards the bottom”):
generating, with the trained…model, the impression section, wherein the generated impression section is configured to mimic the radiologist style (Kay: abstract, i.e., “entry of text in one field of the report may cause related text to be propagated to other fields, such as from the findings to the impression, automatically as specified by the radiologist”; ¶ 0065, i.e., “propagate part of the findings to the Impression, by causing some of the text included in the Findings to also be included in the Impression”); and
automatically inserting the impression section into the radiology report as a proposed impression section (Kay: abstract, i.e., “entry of text in one field of the report may cause related text to be propagated to other fields, such as from the findings to the impression, automatically as specified by the radiologist”; ¶ 0065, i.e., “propagate part of the findings to the Impression, by causing some of the text included in the Findings to also be included in the Impression”).
Yet, Kay does not explicitly teach, but Dai teaches, in the same field of endeavor,
at the computing system and with a trained machine learning model (Dai: page 5999, under broadest reasonable interpretation, a person having ordinary skill in the art would have understood the trained “style transfer system” of Dai as the association of the template “based on the institution, the reading radiologist, and the study description” of Kay, which is the claimed trained machine learning model), automatically:
determining, with the trained machine learning model, a context (Dai: page 5999, section 3.3, “for a input sentence x = (x1; x2; :::; xn), the Transformer encoder Enc(x; _E) maps inputs to a sequence of continuous representations z = (z1; z2; :::; zn)”) based on the set of finding words (Dai: page 5999, section 3.3, under broadest reasonable interpretation, a person having ordinary skill in the art would have understood the “input sentence x = (x1; x2; :::; xn)” of Dai as “the text that is populated into the report” of Kay, which is the claimed set of finding words);
combining the context (Dai: page 5999, section 3.3, “add an extra style embedding as input to the Transformer encoder Enc(x; s; _E). Therefore the network can compute the probability of the output condition both on the input sentence x and the style control variable s”) with the radiologist style (Dai: page 5999, section 3.3, under broadest reasonable interpretation, a person having ordinary skill in the art would have understood the “style control variable s” of Dai as “the template” of Kay, which is the claimed radiologist style);
generating, with the trained machine learning model, the impression section (Dai: page 5999, section 3.2, under broadest reasonable interpretation, a person having ordinary skill in the art would have understood “the output of this function…the transferred sentence bx” of Dai as the “impression” of Kay, which is the claimed impression section; page 5999, section 3.3, “the Transformer decoder Dec(z; _D) estimates the conditional probability for the output sentence y… the probability of the next token is computed by a softmax classifier...softmax(ot), where ot is logit vector outputted by decoder network…we denote the predicted output sentence of this network by f_(x; s)”; page 6002, column 1, i.e., “we view the softmax distribution generated by f_ as a “soft” generated sentence”), wherein the generated impression section is configured to mimic the radiologist style (Dai: page 5999, section 3.1, “rewrite this sentence to a new one x which has the style s”); and
Therefore, it would have been obvious to one having ordinary skill in the art, before the effective filing date of the claimed invention, to include determining, with the trained machine learning model, a context based on the set of finding words; combining the context with the radiologist style; generating, with the trained machine learning model, the impression section, wherein the generated impression section is configured to mimic the radiologist style, as taught by Dai, within the system of Kay, with the motivation to “achieve better style transfer and better content preservation” (Dai: abstract).
Regarding (new) claim 22, Kay and Dai teach the method of claim 21, further comprising: receiving, from the radiologist, an input indicating an action selected from the group consisting of:
accepting the proposed impression section (Kay: ¶ 0033, i.e., “When the report is complete, the radiologist, through either voice command or button click, signs and sends the report”),
editing the proposed impression section, and
rejecting the proposed impression section.
Regarding (new) claim 23, Kay and Dai teach the method of claim 21, wherein the string of text is generated using a dictation device (Kay: ¶ 0056, i.e., “the radiologist were to then select that entry, e.g. by…audibly dictating the name of the macro”; ¶ 0066, i.e., “radiologists are also able to access macros through…dictation software”).
Regarding (new) claim 24, Kay and Dai teach the method of claim 21, wherein the trained machine learning model comprises a decoder (Dai: page 5999, section 3.3, “Transformer follows the standard encoder-decoder architecture”).
The obviousness of combining the teachings of Kay and Dai are discussed in the rejection of claim 21, and incorporated herein.
Regarding (new) claim 25, Kay and Dai teach the method of claim 21, wherein the trained machine learning model comprises a multi-transformer model (Dai: page 5999, section 3.3, “Transformer follows the standard encoder-decoder architecture”).
The obviousness of combining the teachings of Kay and Dai are discussed in the rejection of claim 21, and incorporated herein.
Regarding (new) claim 26, Kay and Dai teach the method of claim 21, wherein the trained machine learning model comprises a natural language processing (NLP) model (Dai: page 5998, “Transformer is a fully-connected self-attention neural architecture, which has achieved many exciting results on natural language processing (NLP) tasks”).
The obviousness of combining the teachings of Kay and Dai are discussed in the rejection of claim 21, and incorporated herein.
Regarding (new) claim 27, Kay and Dai teach the method of claim 21, further comprising presenting the proposed impression section to the radiologist via a user interface, wherein the user interface comprises a navigation device (Kay: figure 5, i.e., user interface includes populated “Impression” field, macro 500, and menu element 506).
Regarding (new) claim 28, Kay and Dai teach the method of claim 21, wherein the set of features comprises an impression section length, a word choice, and a recommendation type (Kay: ¶ 0067, i.e., “When a particular field is selected, not only are the macro choices for that field made available to the radiologist, but also the text that the radiologist has previously dictated in that field in connection with other previous studies (e.g. in connection with reviewing studies of other patients which are similar to this study in terms of type of study and modality). Since the previously dictated entries are selected for presentation to the radiologist based on the particular field of the report”).
Regarding (new) claim 29, Kay and Dai teach the method of claim 21, wherein the radiologist style is a dictation style (Kay: ¶ 0049, i.e., “different macros are available to the radiologist based on the template being used to create the report. The selection of template may be based on which radiologist is dictating the report”; ¶ 0050, i.e., “These available macros are displayed to the radiologist, and may be selected by a radiologist by dictating”; ¶ 0066).
Regarding (new) claim 30, Kay and Dai teach the method of claim 21, wherein the radiologist style is a writing style (Kay: ¶ 0049, i.e., “different macros are available to the radiologist based on the template being used to create the report. The selection of template may be based on which radiologist”; ¶ 0067-0068).
Regarding (new) claim 31, Kay and Dai teach the method of claim 21, wherein the trained machine learning model is trained using a set of report templates (Dai: page 6002, “Algorithm 3," “Style Transformer network” is trained using “datasets” as “Input; page 6002, section 4.1 “Datasets”).
The obviousness of combining the teachings of Kay and Dai are discussed in the rejection of claim 21, and incorporated herein.
Regarding (new) claim 32, Kay and Dai teach the method of claim 21, wherein generating the impression section comprises generating the impression section from a dictation (Kay: ¶ 0056, i.e., “the radiologist were to then select that entry, e.g. by…audibly dictating the name of the macro”; ¶ 0066, i.e., “radiologists are also able to access macros through…dictation software”).
Regarding (new) claim 33, Kay and Dai teach the method of claim 21, further comprising determining compliance of the impression section with a standard (Kay: ¶ 0095, i.e., “In the event that the text that the radiologist dictates does not justify the application of an intended billing code, the radiologist is warned to that effect before the physician is allowed to sign and send the report”; ¶ 0096, i.e., “notifying the radiologist when additional findings are required to satisfy a particular code, it is possible for the radiologist to ensure that all necessary findings are included in the report”).
Regarding (new) claim 34, Kay teaches a computing system (Kay: ¶ 0097), configured to automatically generate an impression section of a radiology report by performing a process, the process comprising:
receiving a string of text from the findings section of the radiology report, the string of text comprising a set of finding words (Kay: ¶ 0056-0057); and
with a trained…model stored at the computing system, automatically determining a radiologist style based on a radiologist identifier of a radiologist (Kay: ¶ 0049, i.e., “different macros are available to the radiologist based on the template being used to create the report”; ¶ 0067-0068), wherein the radiologist style is determined based on features of impression sections in a historical report previously generated by the radiologist (Kay: ¶ 0067, i.e., “the entries that the radiologist has dictated for each field are recorded in a database. When that same template is later used by that same radiologist, those previous entries are accessed. When a particular field is selected, not only are the macro choices for that field made available to the radiologist, but also the text that the radiologist has previously dictated in that field in connection with other previous studies”; ¶ 0068, i.e., “the phrases are sorted to provide the radiologist with the most recently used phrases at the top of the list and the least recently used phrases towards the bottom”); and
generating, with the trained…model, the impression section based on the radiologist style, wherein the impression section is configured to mimic the radiologist style (Kay: abstract, i.e., “entry of text in one field of the report may cause related text to be propagated to other fields, such as from the findings to the impression, automatically as specified by the radiologist”; ¶ 0065, i.e., “propagate part of the findings to the Impression, by causing some of the text included in the Findings to also be included in the Impression”); and
automatically inserting the impression section into the radiology report as a proposed impression section (Kay: abstract, i.e., “entry of text in one field of the report may cause related text to be propagated to other fields, such as from the findings to the impression, automatically as specified by the radiologist”; ¶ 0065, i.e., “propagate part of the findings to the Impression, by causing some of the text included in the Findings to also be included in the Impression”).
Yet, Kay does not explicitly teach, but Dai teaches, in the same field of endeavor,
…a trained machine learning model (Dai: page 5999, under broadest reasonable interpretation, a person having ordinary skill in the art would have understood the trained “style transfer system” of Dai as the association of the template “based on the institution, the reading radiologist, and the study description” of Kay, which is the claimed trained machine learning model)…;
Therefore, it would have been prima facie obvious to one of ordinary skill in the art at the time of the invention was made to combine the noted features of Dai with the teachings of Kay since the combination of the references is merely simple substitution of one known element for another producing a predictable result (KSR rationale B). Since each individual element and its function are shown in the prior art, albeit shown in separate references, the difference between the claimed subject matter and the prior art rests not on any individual element or function but in the very combination itself— that is, in the substitution of the association of the template “based on the institution, the reading radiologist, and the study description” taught by Kay for the trained “style transfer system” as taught by Dai, respectively. Thus, the simple substitution of one known element for another producing a predictable result renders the claim obvious.
Regarding (new) claim 35, claim 35 recites substantially similar limitations analogous to those already addressed in claim 26, and thus, claim 35 is similarly analyzed and rejected in a manner consistent with the rejection of claim 26.
Regarding (new) claim 36, claim 36 recites substantially similar limitations analogous to those already addressed in claim 24, and thus, claim 36 is similarly analyzed and rejected in a manner consistent with the rejection of claim 24.
Regarding (new) claim 37, Kay and Dai teach the system of claim 34, wherein the computing system is further configured to interface with a database, wherein the database comprises at least one of: a Picture Archiving and Communication System (PACS), an electronic medical record (EMR) database, an electronic health record (EHR) database, or a Radiology Information System (RIS) (Kay: ¶ 0034).
Regarding (new) claim 38, Kay and Dai teach the system of claim 34, wherein the computing system is configured to transform a voice transcription received at the dictation device into the impression section (Kay: ¶ 0056, i.e., “the radiologist were to then select that entry, e.g. by…audibly dictating the name of the macro”; ¶ 0066, i.e., “radiologists are also able to access macros through…dictation software”) upon:
determining, with the trained machine learning model, a context (Dai: page 5999, section 3.3, “for a input sentence x = (x1; x2; :::; xn), the Transformer encoder Enc(x; _E) maps inputs to a sequence of continuous representations z = (z1; z2; :::; zn)”) based on the set of finding words (Dai: page 5999, section 3.3, under broadest reasonable interpretation, a person having ordinary skill in the art would have understood the “input sentence x = (x1; x2; :::; xn)” of Dai as “the text that is populated into the report” of Kay, which is the claimed set of finding words),
concatenating the context element (Dai: page 5999, section 3.3, “add an extra style embedding as input to the Transformer encoder Enc(x; s; _E). Therefore the network can compute the probability of the output condition both on the input sentence x and the style control variable s”) with the radiologist style (Dai: page 5999, section 3.3, under broadest reasonable interpretation, a person having ordinary skill in the art would have understood the “style control variable s” of Dai as “the template” of Kay, which is the claimed radiologist style) to produce a concatenated element, and
generating, with the trained machine learning model, the impression section based on the concatenated element (Dai: page 5999, section 3.2, under broadest reasonable interpretation, a person having ordinary skill in the art would have understood “the output of this function…the transferred sentence bx” of Dai as the “impression” of Kay, which is the claimed impression section; page 5999, section 3.3, “the Transformer decoder Dec(z; _D) estimates the conditional probability for the output sentence y… the probability of the next token is computed by a softmax classifier...softmax(ot), where ot is logit vector outputted by decoder network…we denote the predicted output sentence of this network by f_(x; s)”; page 6002, column 1, i.e., “we view the softmax distribution generated by f_ as a “soft” generated sentence”).
The obviousness of combining the teachings of Kay and Dai are discussed in the rejection of claim 34, and incorporated herein.
Regarding (new) claim 39, Kay and Dai teach the system of claim 34, wherein the radiologist style is a writing style (Kay: ¶ 0049, i.e., “different macros are available to the radiologist based on the template being used to create the report. The selection of template may be based on which radiologist”; ¶ 0067-0068) or a dictation style (Kay: ¶ 0049, i.e., “different macros are available to the radiologist based on the template being used to create the report. The selection of template may be based on which radiologist is dictating the report”; ¶ 0050, i.e., “These available macros are displayed to the radiologist, and may be selected by a radiologist by dictating”; ¶ 0066).
Regarding (new) claim 40, Kay and Dai teach the system of claim 34, wherein the computing system is further configured to receive, from the radiologist via a user interface, an input from a navigation device indicating an action selected from the group consisting of:
accepting the proposed impression section (Kay: ¶ 0033, i.e., “When the report is complete, the radiologist, through either voice command or button click, signs and sends the report”; ¶ 0051, i.e., “the reporting interface has a menu 300 containing menu elements 302”),
editing the proposed impression section, and
rejecting the proposed impression section.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 2019/0139218 A1 teaches automatically generating the impression section for radiology reports based on deep-learning.
CN 111414464 A teaches using historical conversation content to automatically generate text (i.e., for a school problem).
“Relation extraction between bacteria and biotopes from biomedical texts with attention mechanisms and domain-specific contextual representations” teaches training a model to extract lexical, syntactic, and semantic features from biomedical literature.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Emily Huynh whose telephone number is (571)272-8317. The examiner can normally be reached on M-Th 8-5 PM.
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, Robert Morgan can be reached on (571) 272-6773. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/EMILY HUYNH/Primary Examiner, Art Unit 3683