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 § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 66-86 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Lyman et al. (hereinafter Lyman) (US 2020/0395119 A1).
Regarding claim 66: Lyman discloses (i) analyzing a medical image of the subject using a computer vision algorithm to label an image feature (A medical scan image analysis system 112 can be used to generate and/or perform one or more medical scan image analysis functions by utilizing a computer vision-based learning algorithm 1350 on a training set of medical scans with known annotation data, diagnosis data, labeling and/or medical code data, report data, patient history data, patient risk factor data, and/or other metadata associated with medical scans. These medical scan image analysis functions can be used to generate inference data for new medical scans that are triaged or otherwise require inferred annotation data, diagnosis data, labeling and/or medical code data, and/or report data. For example, some medical scan image analysis functions can correspond to medical scan inference functions of the medical scan diagnosing system or other medical scan analysis functions of a medical scan analysis function database. The medical scan image analysis functions can be used to determine whether or not a medical scan is normal, to detect the location of an abnormality in one or more slices of a medical scan, and/or to characterize a detected abnormality. The medical scan image analysis system can be used to generate and/or perform computer vision based medical scan image analysis functions utilized by other subsystems of the medical scan processing system as described herein, aiding medical professionals to diagnose patients and/or to generate further data and models to characterize medical scans. The medical scan image analysis system can include a processing system that includes a processor and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations., par. 49); (ii) generating a computer-generated finding that is based at least in part on the image feature (The medical scan image analysis functions can be used to determine whether or not a medical scan is normal, to detect the location of an abnormality in one or more slices of a medical scan, and/or to characterize a detected abnormality. The medical scan image analysis system can be used to generate and/or perform computer vision based medical scan image analysis functions utilized by other subsystems of the medical scan processing system as described herein, aiding medical professionals to diagnose patients and/or to generate further data and models to characterize medical scans., par. 49); (iii) analyzing the medical report of the subject using a natural language processing algorithm (A medical scan diagnosing system 108 can be used by hospitals, medical professionals, or other medical entities to automatically produce inference data for given medical scans by utilizing computer vision techniques and/or natural language processing techniques. This automatically generated inference data can be used to generate and/or update diagnosis data or other corresponding data of corresponding medical scan entries in a medical scan database. The medical scan diagnosing system can utilize a medical scan database, user database, and/or a medical scan analysis function database by communicating with the database storage system 140 via the network 150, and/or can utilize another medical scan database, user database, and/or function database stored in local memory., par. 46); (iv) detecting a user-generated finding in the medical report (The medical scan report labeling system 104 can be used to automatically assign medical codes to medical scans based on user identified keywords, phrases, or other relevant medical condition terms of natural text data in a medical scan report of the medical scan, identified by users of the medical scan report labeling system 104. The medical scan report labeling system 104 can be operable to transmit a medical report that includes natural language text to a first client device for display. Identified medical condition term data can be received from the first client device in response. An alias mapping pair in a medical label alias database can be identified by determining that a medical condition term of the alias mapping pair compares favorably to the identified medical condition term data. A medical code that corresponds to the alias mapping pair and a medical scan that corresponds to the medical report can be transmitted to a second client device of an expert user for display, and accuracy data can be received from the second client device in response. The medical code is mapped to the first medical scan in a medical scan database when the accuracy data indicates that the medical code compares favorably to the medical scan. The medical scan annotator system 106 can be used to gather annotations of medical scans based on review of the medical scan image data by users of the system such as radiologists or other medical professionals. Medical scans that require annotation, for example, that have been triaged from a hospital or other triaging entity, can be sent to multiple users selected by the medical scan annotator system 106, and the annotations received from the multiple medical professionals can be processed automatically by a processing system of the medical scan annotator system, allowing the medical scan annotator system to automatically determine a consensus annotation of each medical scan. Furthermore, the users can be automatically scored by the medical scan annotator system based on how closely their annotation matches to the consensus annotation or some other truth annotation, for example, corresponding to annotations of the medical scan assigned a truth flag. Users can be assigned automatically to annotate subsequent incoming medical scans based on their overall scores and/or based on categorized scores that correspond to an identified category of the incoming medical scan., pars. 43-44); wherein the user-generated finding is based at least in part on the medical image (Some medical scans can include one or more abnormalities, which can be identified by a user, par. 59); (v) detecting a discrepancy between the computer-generated finding and the user-generated finding (In some embodiments, disagreement between an inference function's labeling data and the clinical project manager's labeling data can be caused by the clinical project manager being incorrect rather than the inference function being incorrect. For example, if a highly reliable inference function with very favorable accuracy data 631 generates labeling data that is different from labeling data generated by a fairly new clinical project manager, the inference function's labeling data may correspond to the correct labeling data, where the clinical project manager made an error. Such cases where a highly reliable inference function can be utilized to extend the quality assurance process to evaluate performance of the clinical project manager, as well as the set of labelers 1-N, to ensure that the clinical project manager is generating the true golden labeling data and is correcting the labelers appropriately. In such embodiments, the medical scan labeling quality assurance system 3004 can be further operable to generate performance score data and/or otherwise evaluate the clinical project manager or other expert user alternatively or in addition to evaluating the set of labelers 1-N and/or the inference function 1-L., par. 388); and (vi) flagging the discrepancy between the computer-generated finding and the user-generated finding (Inference functions that are flagged over time can be automatically decommissioned and/or retrained, for example, via remediation step 1140 of FIG. 6B. In some cases, performance score data and/or correction data for some or all inference functions in a given quality assurance process can be sent to a client device associated with a system administrator, software engineer, and/or data scientist that is responsible for managing and/or generating computer vision models and/or other models discussed herein to notify the system administrator, software engineer, and/or data scientist of the performance of the corresponding model. This can include sending all performance score data and/or correction data generated for a given inference function to a client device of a user associated with the given inference function for review, for example, in conjunction with the medical scans 1-M to enable the user to review and understand places where the model performed well and where the model performed poorly. This can include sending only performance score data and/or correction data generated for a given inference function to a client device of a user associated with the given inference function for review in response to the inference function being flagged., par. 385 and In other embodiments, neither the inference function's labeling data nor the clinical project manager's labeling data can be immediately assigned as golden labeling data when disagreement between the inference function's labeling data and the clinical project manager's labeling data occurs. In cases where the inference function's labeling data does not match the clinical project manager's labeling data for one or more medical scans, these one or more medical scans, or the entire set of medical scans 1-M, can be sent to one or more other experts for review to clear the discrepancy. In some cases, the medical scan labeling quality assurance system 3004 or other subsystem 101 determines the golden labeling data by performing a consensus function, which can include applying the annotation consensus function of FIG. 15A to the labeling data generated by the inference function and the labeling data generated by the clinical project manager. For example, the medical scan labeling quality assurance system 3004 implements the medical scan annotating system 106 to generate the golden labeling data as the final consensus annotation of FIG. 15A. The medical scan labeling quality assurance system 3004 can weigh the labeling data generated by the inference function and the labeling data generated by the clinical project manager to identify which labeling data corresponds to the golden labeling data for a given quality assurance process. The weight assigned to the inference function can be based on the accuracy data 631 of the inference function, generated based on one or more prior quality assurance processes. The weight assigned to the inference clinical project manager can be based on the accuracy data 531 of the clinical project manager in their user profile entry 354, generated based on one or more prior quality assurance processes. In some cases, the higher accuracy of and/or more favorable of the accuracy data 631 and accuracy data 531 can denote the inference function or the clinical project manager, respectively, has its labeling data set as the golden labeling data., par. 390).
Regarding claim 67: Lyman satisfies all the elements of claim 66. Lyman further discloses wherein the detecting of the user-generated finding in the medical report (The medical scan report labeling system 104 can be used to automatically assign medical codes to medical scans based on user identified keywords, phrases, or other relevant medical condition terms of natural text data in a medical scan report of the medical scan, identified by users of the medical scan report labeling system 104. The medical scan report labeling system 104 can be operable to transmit a medical report that includes natural language text to a first client device for display. Identified medical condition term data can be received from the first client device in response. An alias mapping pair in a medical label alias database can be identified by determining that a medical condition term of the alias mapping pair compares favorably to the identified medical condition term data. A medical code that corresponds to the alias mapping pair and a medical scan that corresponds to the medical report can be transmitted to a second client device of an expert user for display, and accuracy data can be received from the second client device in response. The medical code is mapped to the first medical scan in a medical scan database when the accuracy data indicates that the medical code compares favorably to the medical scan. The medical scan annotator system 106 can be used to gather annotations of medical scans based on review of the medical scan image data by users of the system such as radiologists or other medical professionals. Medical scans that require annotation, for example, that have been triaged from a hospital or other triaging entity, can be sent to multiple users selected by the medical scan annotator system 106, and the annotations received from the multiple medical professionals can be processed automatically by a processing system of the medical scan annotator system, allowing the medical scan annotator system to automatically determine a consensus annotation of each medical scan. Furthermore, the users can be automatically scored by the medical scan annotator system based on how closely their annotation matches to the consensus annotation or some other truth annotation, for example, corresponding to annotations of the medical scan assigned a truth flag. Users can be assigned automatically to annotate subsequent incoming medical scans based on their overall scores and/or based on categorized scores that correspond to an identified category of the incoming medical scan., pars. 43-44) comprises the use of a natural-language algorithm (natural language processing, par. 46).
Regarding claim 68: Lyman satisfies all the elements of claim 66. Lyman further discloses further comprising, after (vi), providing a user the option to edit the user-generated finding (Each medical scan entry 352 can be identified by its own medical scan identifier 353, and can include or otherwise map to medical scan image data 410, and metadata such as scan classifier data 420, patient history data 430, diagnosis data 440, annotation author data 450, confidence score data 460, display parameter data 470, similar scan data 480, training set data 490, and/or other data relating to the medical scan. Some or all of the data included in a medical scan entry 352 can be used to aid a user in generating or editing diagnosis data 440, for example, in conjunction with the medical scan assisted review system 102, the medical scan report labeling system 104, and/or the medical scan annotator system 106. Some or all of the data included in a medical scan entry 352 can be used to allow one or more subsystems 101, such as automated portions of the medical scan report labeling system 104 and/or the medical scan diagnosing system 108, to automatically generate and/or edit diagnosis data 440 or other data the medical scan. Some or all of the data included in a medical scan entry 352 can be used to train some or all medical scan analysis functions of the medical scan analysis function database 346 such as one or more medical scan image analysis functions, one or more medical scan natural language analysis functions, one or more medical scan similarity analysis functions, one or more medical report generator functions, and/or one or more medical report analysis functions, for example, in conjunction with the medical scan image analysis system 112, the medical scan natural language analysis system 114, and/or the medical scan comparison system 116., par. 60).
Regarding claim 69: Lyman satisfies all the elements of claim 66. Lyman further discloses further comprising generating a list of user-generated findings comprising the user generated finding (The user profile entry 354 can include report formatting data 570, which can indicate report formatting preferences indicated by the user. This can include font, text size, header data, bulleting or numbering type, margins, file type, preferences for including one or more full or cropped image slices 412, preferences for including similar medical scans, preferences for including additional medical scans in reports, or other formatting preference to list natural language text data and/or image data corresponding to each abnormality. Some or all of the report formatting data 570 can be based on interface preference data 560. The report formatting data 570 can be used by one or more subsystems to automatically generate report data 449 of medical scans based on the preferences of the requesting user., par. 100).
Regarding claim 70: Lyman satisfies all the elements of claim 69. Lyman further discloses further comprising generating a list of computer-generated findings comprising the computer-generated finding (A medical scan analysis function entry 356 can include training parameters 620. This can include training set data 621, which can include identifiers for the data used to train the medical scan analysis function, such as a set of medical scan identifiers 353 corresponding to the medical scans used to train the medical scan analysis function, a list of medical scan reports and corresponding medical codes used to train the medical scan analysis function, etc. Alternatively or in addition to identifying particular scans of the training set, the training set data 621 can identify training set criteria, such as necessary scan classifier data 420, necessary abnormality locations, classifiers, or other criteria corresponding to abnormality annotation data 442, necessary confidence score data 460, for example, indicating that only medical scans with diagnosis data 440 assigned a truth flag 461 or with confidence score data 460 otherwise comparing favorably to a training set confidence score threshold are included, a number of medical scans to be included and proportion data corresponding to different criteria, or other criteria used to populate a training set with data of medical scans. Training parameters 620 can include model type data 622 indicating one or more types of model, methods, and/or training functions used to determine the medical scan analysis function by utilizing the training set 621. Training parameters 620 can include model parameter data 623 that can include a set of features of the training data selected to train the medical scan analysis function, determined values for weights corresponding to selected input and output features, determined values for model parameters corresponding to the model itself, etc. The training parameter data can also include testing data 624, which can identify a test set of medical scans or other data used to test the medical scan analysis function. The test set can be a subset of training set 621, include completely separate data than training set 621, and/or overlap with training set 621. Alternatively or in addition, testing data 624 can include validation parameters such as a percentage of data that will be randomly or pseudo-randomly selected from the training set for testing, parameters characterizing a cross validation process, or other information regarding testing. Training parameters 620 can also include training error data 625 that indicates a training error associated with the medical scan analysis function, for example, based on applying cross validation indicated in testing data 624., par. 103).
Regarding claim 71: Lyman satisfies all the elements of claim 70. Lyman further discloses further comprising comparing the list of user-generated findings to the list of computer-generated findings (Diagnosis data 440 can include data that indicates an automated diagnosis, a tentative diagnosis, and/or data that can otherwise be used to support medical diagnosis, triage, medical evaluation and/or other review by a medical professional or other user. The diagnosis data 440 of a medical scan can include a binary abnormality identifier 441 indicating whether the scan is normal or includes at least one abnormality. In some embodiments, the binary abnormality identifier 441 can be determined by comparing some or all of confidence score data 460 to a threshold, can be determined by comparing a probability value to a threshold, and/or can be determined by comparing another continuous or discrete value indicating a calculated likelihood that the scan contains one or more abnormalities to a threshold. In some embodiments, non-binary values, such as one or more continuous or discrete values indicating a likelihood that the scan contains one or more abnormalities, can be included in diagnosis data 440 in addition to, or instead of, binary abnormality identifier 441. One or abnormalities can be identified by the diagnosis data 440, and each identified abnormality can include its own set of abnormality annotation data 442. Alternatively, some or all of the diagnosis data 440 can indicate and/or describe multiple abnormalities, and thus will not be presented for each abnormality in the abnormality annotation data 442. For example, the report data 449 of the diagnosis data 440 can describe all identified abnormalities, and thus a single report can be included in the diagnosis., par. 69).
Regarding claim 72: Lyman satisfies all the elements of claim 71. Lyman further discloses further comprising generating a statistic (The medical assisted review system can automatically generate state change data such as a change in size, volume, malignancy, or other changes to various classifiers of the abnormality. This can be achieved by automatically comparing image data of one or more previous scans and the current scan and/or by comparing abnormality data of the previous scan to abnormality data of the current scan. In some embodiments, such metrics can be calculated by utilizing the medical scan similarity analysis function, for example, where the output of the medical scan similarity analysis function such as the similarity score indicates distance, error, or other measured discrepancy in one or more abnormality classifier categories 444 and/or abnormality pattern categories 446. This calculated distance, error, or other measured discrepancy in each category can be used to quantify state change data, indicate a new classifier in one or more categories, to determine if a certain category has become more or less severe, or otherwise determine how the abnormality has changed over time. In various embodiments, this data can be displayed in one window, for example, where an increase in abnormality size is indicated by overlaying or highlighting an outline of the current abnormality over the corresponding image slice of the previous abnormality, or vice versa. In various embodiments where several past scans are available, such state change data can be determined over time, and statistical data showing growth rate changes over time or malignancy changes over time can be generated, for example, indicating if a growth rate is lessening or worsening over time., par. 42) that is based at least in part on the comparison of the list of user-generated findings and the list of computer- generated findings (Diagnosis data 440 can include data that indicates an automated diagnosis, a tentative diagnosis, and/or data that can otherwise be used to support medical diagnosis, triage, medical evaluation and/or other review by a medical professional or other user. The diagnosis data 440 of a medical scan can include a binary abnormality identifier 441 indicating whether the scan is normal or includes at least one abnormality. In some embodiments, the binary abnormality identifier 441 can be determined by comparing some or all of confidence score data 460 to a threshold, can be determined by comparing a probability value to a threshold, and/or can be determined by comparing another continuous or discrete value indicating a calculated likelihood that the scan contains one or more abnormalities to a threshold. In some embodiments, non-binary values, such as one or more continuous or discrete values indicating a likelihood that the scan contains one or more abnormalities, can be included in diagnosis data 440 in addition to, or instead of, binary abnormality identifier 441. One or abnormalities can be identified by the diagnosis data 440, and each identified abnormality can include its own set of abnormality annotation data 442. Alternatively, some or all of the diagnosis data 440 can indicate and/or describe multiple abnormalities, and thus will not be presented for each abnormality in the abnormality annotation data 442. For example, the report data 449 of the diagnosis data 440 can describe all identified abnormalities, and thus a single report can be included in the diagnosis., par. 69).
Regarding claim 73: Lyman satisfies all the elements of claim 66. Lyman further discloses further comprising presenting an option to incorporate the computer-generated finding into the medical report (The quality assurance process discussed in conjunction with FIGS. 13A-13E can be applied to inference functions as well as human labelers. As a particular example, the set of M quality assurance studies that are sent to professional labelers for labeling at a scheduled frequency, such as weekly, are also processed by one or more inference functions at this scheduled frequency This can include one or more inference functions 1105, one or more inference functions 3095, one or more inference function trained and/or performed via medical image analysis system 112, one or more inference functions of the function database 346, and/or any other inference functions discussed herein. The labels and/or annotations generated by the human labelers, plus the labels and/or other inference data generated by each inference function, are sent to an expert user, such as a clinical project manager, for review., par. 373).
Regarding claim 74: Lyman satisfies all the elements of claim 73. Lyman further discloses further comprising including the computer-generated finding in the medical report when a user accepts inclusion of the computer-generated finding within the medical report (In other embodiments, neither the inference function's labeling data nor the clinical project manager's labeling data can be immediately assigned as golden labeling data when disagreement between the inference function's labeling data and the clinical project manager's labeling data occurs. In cases where the inference function's labeling data does not match the clinical project manager's labeling data for one or more medical scans, these one or more medical scans, or the entire set of medical scans 1-M, can be sent to one or more other experts for review to clear the discrepancy., par. 390).
Regarding claim 75: Lyman satisfies all the elements of claim 74. Lyman further discloses wherein the computer-generated finding is included in a sentence or phrase (The medical scan report labeling system 104 can be used to automatically assign medical codes to medical scans based on user identified keywords, phrases, or other relevant medical condition terms of natural text data in a medical scan report of the medical scan, identified by users of the medical scan report labeling system 104. The medical scan report labeling system 104 can be operable to transmit a medical report that includes natural language text to a first client device for display. Identified medical condition term data can be received from the first client device in response. , par. 43) that is generated using the natural language processing algorithm (A medical scan diagnosing system 108 can be used by hospitals, medical professionals, or other medical entities to automatically produce inference data for given medical scans by utilizing computer vision techniques and/or natural language processing techniques. This automatically generated inference data can be used to generate and/or update diagnosis data or other corresponding data of corresponding medical scan entries in a medical scan database. The medical scan diagnosing system can utilize a medical scan database, user database, and/or a medical scan analysis function database by communicating with the database storage system 140 via the network 150, and/or can utilize another medical scan database, user database, and/or function database stored in local memory., par. 46).
Regarding claim 76: Lyman satisfies all the elements of claim 66. Lyman further discloses further comprising determining a score related to the medical report (Diagnosis data 440 can include data that indicates an automated diagnosis, a tentative diagnosis, and/or data that can otherwise be used to support medical diagnosis, triage, medical evaluation and/or other review by a medical professional or other user. The diagnosis data 440 of a medical scan can include a binary abnormality identifier 441 indicating whether the scan is normal or includes at least one abnormality. In some embodiments, the binary abnormality identifier 441 can be determined by comparing some or all of confidence score data 460 to a threshold, can be determined by comparing a probability value to a threshold, and/or can be determined by comparing another continuous or discrete value indicating a calculated likelihood that the scan contains one or more abnormalities to a threshold. In some embodiments, non-binary values, such as one or more continuous or discrete values indicating a likelihood that the scan contains one or more abnormalities, can be included in diagnosis data 440 in addition to, or instead of, binary abnormality identifier 441. One or abnormalities can be identified by the diagnosis data 440, and each identified abnormality can include its own set of abnormality annotation data 442. Alternatively, some or all of the diagnosis data 440 can indicate and/or describe multiple abnormalities, and thus will not be presented for each abnormality in the abnormality annotation data 442. For example, the report data 449 of the diagnosis data 440 can describe all identified abnormalities, and thus a single report can be included in the diagnosis., par. 69).
Regarding claim 77: Lyman satisfies all the elements of claim 66. Lyman further discloses wherein the medical report comprises a radiology report (In some embodiments, as illustrated in FIGS. 8D-8F, the medical picture archive integration system 2600 can further communicate with a report database 2625, such as a Radiology Information System (RIS), that includes a plurality of medical reports corresponding to the DICOM images stored by the medical picture archive system 2620., par. 179).
Regarding claim 78: Lyman satisfies all the elements of claim 66. Lyman further discloses wherein the image feature corresponds to an anatomical structure (At least one region of the image data that includes identifying facial structure can be determined by utilizing a medical image analysis function. For example, the medical image analysis function can include a facial detection function that determines the regions of the image data that include identifying facial structure based on searching the image data for pixels with a density value that corresponds to facial skin, facial bone structure, or other density of an anatomical mass type that corresponds to identifying facial structure, and the facial obfuscation function can be performed on the identified pixels. Alternatively or in addition, the facial detection function can determine the region based on identifying at least one shape in the image data that corresponds to a facial structure., par. 235), a tissue type (The abnormality classifier categories 444 can also include a malignancy category, and the abnormality classification data 445 can include a malignancy rating such as a Lung-RADS score, a Fleischner score, and/or one or more calculated values that indicate malignancy level, malignancy severity, and/or probability of malignancy. Alternatively or in addition, the malignancy category can be assigned a value of “yes”, “no”, or “maybe”. The abnormality classifier categories 444 can also include abnormality pattern categories 446 such as cardiomegaly, consolidation, effusion, emphysema, and/or fracture, and the abnormality classification data 445 for each abnormality pattern category 446 can indicate whether or not each of the abnormality patterns is present., par. 71), a tumor or tissue abnormality (Some medical scans can include one or more abnormalities, which can be identified by a user or can be identified automatically. Abnormalities can include nodules, for example malignant nodules identified in a chest CT scan. Abnormalities can also include and/or be characterized by one or more abnormality pattern categories such as such as cardiomegaly, consolidation, effusion, emphysema, and/or fracture, for example identified in a chest x-ray. Abnormalities can also include any other unknown, malignant or benign feature of a medical scan identified as not normal., par. 59), a contrast agent (Thus, the scan categories 1120 can correspond to one or more of a scan type, scan anatomical region data, hospital or other originating entity data, machine model data, machine calibration data, contrast agent data, geographic region data, and/or other scan classifying data 420. For example, a first medical scan inference function can be directed to characterizing knee x-rays, and a second medical scan inference function can be directed to chest CT scans., par. 108), or any combination thereof.
Regarding claim 79: Lyman satisfies all the elements of claim 66. Lyman further discloses wherein the image feature comprises one or more of nerve, blood vessel, lymphatic vessel, organ (lung, par. 71); cardiomegaly (enlarged heart), par. 71), joint, bone (fracture, par. 71), muscle, cartilage, lymph, blood, adipose, ligament, or tendon.
Regarding claim 80: Lyman satisfies all the elements of claim 66. Lyman further discloses further comprising analyzing a prior image study of the subject using the computer vision algorithm (A medical scan image analysis system 112 can be used to generate and/or perform one or more medical scan image analysis functions by utilizing a computer vision-based learning algorithm 1350 on a training set of medical scans with known annotation data, diagnosis data, labeling and/or medical code data, report data, patient history data, patient risk factor data, and/or other metadata associated with medical scans. These medical scan image analysis functions can be used to generate inference data for new medical scans that are triaged or otherwise require inferred annotation data, diagnosis data, labeling and/or medical code data, and/or report data. For example, some medical scan image analysis functions can correspond to medical scan inference functions of the medical scan diagnosing system or other medical scan analysis functions of a medical scan analysis function database. The medical scan image analysis functions can be used to determine whether or not a medical scan is normal, to detect the location of an abnormality in one or more slices of a medical scan, and/or to characterize a detected abnormality. The medical scan image analysis system can be used to generate and/or perform computer vision based medical scan image analysis functions utilized by other subsystems of the medical scan processing system as described herein, aiding medical professionals to diagnose patients and/or to generate further data and models to characterize medical scans. The medical scan image analysis system can include a processing system that includes a processor and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations., par. 49).
Regarding claim 81: Lyman satisfies all the elements of claim 80. Lyman further discloses further comprising labeling the image feature in the prior image study (A medical scan image analysis system 112 can be used to generate and/or perform one or more medical scan image analysis functions by utilizing a computer vision-based learning algorithm 1350 on a training set of medical scans with known annotation data, diagnosis data, labeling and/or medical code data, report data, patient history data, patient risk factor data, and/or other metadata associated with medical scans. These medical scan image analysis functions can be used to generate inference data for new medical scans that are triaged or otherwise require inferred annotation data, diagnosis data, labeling and/or medical code data, and/or report data. For example, some medical scan image analysis functions can correspond to medical scan inference functions of the medical scan diagnosing system or other medical scan analysis functions of a medical scan analysis function database. The medical scan image analysis functions can be used to determine whether or not a medical scan is normal, to detect the location of an abnormality in one or more slices of a medical scan, and/or to characterize a detected abnormality. The medical scan image analysis system can be used to generate and/or perform computer vision based medical scan image analysis functions utilized by other subsystems of the medical scan processing system as described herein, aiding medical professionals to diagnose patients and/or to generate further data and models to characterize medical scans. The medical scan image analysis system can include a processing system that includes a processor and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations., par. 49).
Regarding claim 82: Lyman satisfies all the elements of claim 66. Lyman further discloses wherein the medical image is a radiographic image, a magnetic resonance imaging (MM) image, an ultrasound image, an endoscopy image, an elastography image, a thermogram image, a positron emission tomography (PET) image, a single photon emission computed tomography (SPECT) image, an optical coherence tomography (OCT) image, a computed tomography (CT) image, a microscopy image, or a medical photography image (FIG. 4A presents an embodiment of a medical scan entry 352, stored in medical scan database 342, included in metadata of a medical scan, and/or otherwise associated with a medical scan. A medical scan can include imaging data corresponding to a CT scan, x-ray, MRI, PET scan, Ultrasound, EEG, mammogram, or other type of radiological scan or medical scan taken of an anatomical region of a human body, animal, organism, or object and further can include metadata corresponding to the imaging data., par. 58).
Regarding claim 83: Lyman satisfies all the elements of claim 66. Lyman further discloses wherein the computer-generated finding comprises an identification or evaluation of a pathology (Some medical scans can include one or more abnormalities, which can be identified by a user or can be identified automatically. Abnormalities can include nodules, for example malignant nodules identified in a chest CT scan. Abnormalities can also include and/or be characterized by one or more abnormality pattern categories such as such as cardiomegaly, consolidation, effusion, emphysema, and/or fracture, for example identified in a chest x-ray. Abnormalities can also include any other unknown, malignant or benign feature of a medical scan identified as not normal. Some scans can contain zero abnormalities, and can be identified as normal scans. Some scans identified as normal scans can include identified abnormalities that are classified as benign, and include zero abnormalities classified as either unknown or malignant. Scans identified as normal scans may include abnormalities that were not detected by one or more subsystems and/or by an originating entity. Thus, some scans may be improperly identified as normal. Similarly, scans identified to include at least one abnormality may include at least one abnormality that was improperly detected as an abnormality by one or more subsystems and/or by an originating entity. Thus, some scans may be improperly identified as containing abnormalities., par. 59).
Regarding claim 84: Lyman satisfies all the elements of claim 83. Lyman further discloses wherein the identification or evaluation of said pathology comprises at least one of a severity, quantity, measurement, presence, or absence of said pathology or a sign or symptom thereof (Some medical scans can include one or more abnormalities, which can be identified by a user or can be identified automatically. Abnormalities can include nodules, for example malignant nodules identified in a chest CT scan. Abnormalities can also include and/or be characterized by one or more abnormality pattern categories such as such as cardiomegaly, consolidation, effusion, emphysema, and/or fracture, for example identified in a chest x-ray. Abnormalities can also include any other unknown, malignant or benign feature of a medical scan identified as not normal. Some scans can contain zero abnormalities, and can be identified as normal scans. Some scans identified as normal scans can include identified abnormalities that are classified as benign, and include zero abnormalities classified as either unknown or malignant. Scans identified as normal scans may include abnormalities that were not detected by one or more subsystems and/or by an originating entity. Thus, some scans may be improperly identified as normal. Similarly, scans identified to include at least one abnormality may include at least one abnormality that was improperly detected as an abnormality by one or more subsystems and/or by an originating entity. Thus, some scans may be improperly identified as containing abnormalities., par. 59; A priority score, ranking, or queue number of the scan priority data 427 can be generated by automatically by a subsystem based on the scan priority data 427, based on a severity of patient symptoms or other indicators in the risk factor data 432, based on a priority corresponding to the originating entity, based on previously generated diagnosis data 440 for the scan, and/or can be assigned by the originating entity and/or a user of the system., par. 63; As another example, one model is trained to detect lesion and another model is trained to measure lesions, where detection and measurement data is generated for a given medical scan both types of abnormalities is generated for a given medical scan by applying both of these models to the given medical scan., par. 368).
Regarding claim 85: Lyman satisfies all the elements of claim 83. Lyman further discloses wherein the user-generated finding (The medical scan report labeling system 104 can be used to automatically assign medical codes to medical scans based on user identified keywords, phrases, or other relevant medical condition terms of natural text data in a medical scan report of the medical scan, identified by users of the medical scan report labeling system 104. The medical scan report labeling system 104 can be operable to transmit a medical report that includes natural language text to a first client device for display. Identified medical condition term data can be received from the first client device in response. An alias mapping pair in a medical label alias database can be identified by determining that a medical condition term of the alias mapping pair compares favorably to the identified medical condition term data. A medical code that corresponds to the alias mapping pair and a medical scan that corresponds to the medical report can be transmitted to a second client device of an expert user for display, and accuracy data can be received from the second client device in response. The medical code is mapped to the first medical scan in a medical scan database when the accuracy data indicates that the medical code compares favorably to the medical scan. The medical scan annotator system 106 can be used to gather annotations of medical scans based on review of the medical scan image data by users of the system such as radiologists or other medical professionals. Medical scans that require annotation, for example, that have been triaged from a hospital or other triaging entity, can be sent to multiple users selected by the medical scan annotator system 106, and the annotations received from the multiple medical professionals can be processed automatically by a processing system of the medical scan annotator system, allowing the medical scan annotator system to automatically determine a consensus annotation of each medical scan. Furthermore, the users can be automatically scored by the medical scan annotator system based on how closely their annotation matches to the consensus annotation or some other truth annotation, for example, corresponding to annotations of the medical scan assigned a truth flag. Users can be assigned automatically to annotate subsequent incoming medical scans based on their overall scores and/or based on categorized scores that correspond to an identified category of the incoming medical scan., pars. 43-44) is based at least in part on the image feature (The abnormality classifier categories 444 can also include a malignancy category, and the abnormality classification data 445 can include a malignancy rating such as a Lung-RADS score, a Fleischner score, and/or one or more calculated values that indicate malignancy level, malignancy severity, and/or probability of malignancy. Alternatively or in addition, the malignancy category can be assigned a value of “yes”, “no”, or “maybe”. The abnormality classifier categories 444 can also include abnormality pattern categories 446 such as cardiomegaly, consolidation, effusion, emphysema, and/or fracture, and the abnormality classification data 445 for each abnormality pattern category 446 can indicate whether or not each of the abnormality patterns is present., par. 71).
Regarding claim 86: Lyman satisfies all the elements of claim 83. Lyman further discloses further comprising generating an impression based at least in part on the image feature (The labeling application can be utilized by users such as radiologists and/or other labelers responsible for labeling and/or annotating medical scans of the medical scan database with diagnosis data. The interactive interface 3075 can display image data of the medical scan to such a user in conjunction with a plurality of prompts to provide diagnosis, characterization, and/or localization labeling of the medical scan for at least one abnormality identified by the user. The plurality of prompts can present a fixed set of differential diagnosis options allowing the user to select one or more of the differential diagnosis options corresponding to one or more abnormalities detected by the user in the medical scan. The plurality of prompts can present a fixed set of characterization options to classify, describe, or otherwise characterize the one or more differential diagnoses identified in the fixed set of diagnosis data options. The plurality of prompts can present a fixed set of localization options to indicate a region of interest and/or specific anatomical location associated with the one or more differential diagnoses identified in the fixed set of diagnosis data options., par. 256).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHARLOTTE M BAKER whose telephone number is (571)272-7459. The examiner can normally be reached Mon - Fri 8:00-5:00.
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, JENNIFER MEHMOOD can be reached at (571)272-2976. 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.
/CHARLOTTE M BAKER/Primary Examiner, Art Unit 2664
24 July 2026
Prosecution Insights