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 .
Status of the Claims
Claims 1-4, 6-11 are currently pending in the present application, with claims 1, 10, and 11 being independent.
Response to Amendments / Arguments
Applicant's arguments filed 04/24/2026 have been fully considered but they are not persuasive.
Applicant argues: The references fail to disclose “generate a transformed image…in response to a ratio of a region occluded by earwax being less than a threshold ratio compared to a region of the entire tympanum in the target image”. Applicant further argues the Office Action improperly separates the threshold determination from the transformed-image generation and that Douglas merely discloses unrelated threshold concepts.
Examiner replies: The rejection relies on the combined teachings of Douglas et al. (US 20150065803) and Siddiquee et al. "Learning fixed points in generative adversarial networks: From image-to-image translation to disease detection and localization." In Proceedings of the IEEE/CVF international conference on computer vision, pp. 191-200. 2019, as understood by a person of ordinary skill in the art, rather than on Douglas alone teaching the limitation. Douglass expressly discloses evaluating tympanic membrane visibility and obstruction conditions using threshold-based determinations prior to further image analysis operations. For example, Douglas teaches determining when a minimum amount of tympanic membrane is sufficiently visibly within the image (Par. 0036; determine when a minimum amount of tympanic membrane is showing (e.g., more than 20%, more than 25%, more than 30%, more than 35%, more than 40%, more than 45%, more than 50%, more than 55%, more than 60%, more than 65%, more than 70%, more than 75%, more than 80%, more than 85%, more than 90%, more than 95%, etc.) in the image), and further discloses obstruction thresholds used to determine whether examination operations should proceed or terminate (Par. 0329; Thresholds to determine when an obstruction warrants ending the exam can be determined via a standard machine learning method, wherein the training set consists of a set of otoscopic exams and labels, where the labels indicate which exams have dangerous obstructions and which do not). Douglas additionally discloses ML-based tympanic membrane segmentation, pathology analysis, and feature extraction operations (Par. 0063, 0172-0176; TM segmentation consists of pixel-based machine learning…supervised machine learning and the model…To generate training data, the user generates a training set of images…each image contains an outlined contour of the TM to yield the TM segmentation mask…The image subjects may include healthy TMs, pathological TMs (e.g., acute otitis media, otitis media with effusion, foreign bodies, etc.), or images that do not contain a TM).
Siddiquee expressly discloses transforming diseased medical images into corresponding healthy images using a machine-learning image translation model and further discloses lesion localization by subtracting the transformed healthy image from the original diseased image (Pg. 192, Fig. 2 description; translate any image, diseased or healthy, into a healthy image, allowing diseased regions to be revealed by subtracting those two images…Section 1; GAN trained for virtual healing aims to turn any image, with unknown health status, into a healthy one. Pg. 197, Section 4.2, Left Column; The desired GAN behaviour is to translate diseased images to healthy ones while keeping healthy images intact…).
A person of ordinary skill in the art would have understood that Douglas’s obstruction/visibility threshold determination would naturally function as a gating condition before applying Siddiquee’s GAN-based image transformation processing, because reliable pathological-to-normal image transformation predictably depends on sufficient visibility of the relevant anatomical structure and the location of obstructed regions. Identifying whether sufficient tympanic membrane visibility exists, as taught by Douglas, before applying GAN-based transformation processing to obstructed regions, as taught by Siddiquee, would be obvious as transformation reliability predictably depends on the extent and location of abnormal or obstructed anatomical regions. The rejection does not rely on improperly separating the claimed limitations, but rather Douglas supplies the claimed obstruction-ratio threshold determination used to determine whether sufficient tympanic membrane visibility exists prior to downstream analysis operations of Siddiquee’s abnormal-to-normal transformation processing. The rejection relies on the combined workflow, more specifically that sufficient unobstructed anatomical visibility is first confirmed before performing downstream medical-image transformation operations.
Further, “in response to” language constitutes contingent operational language under MPEP 211.04(II), Douglas expressly discloses obstruction threshold determinations governing whether examination or image analysis operations proceed (Par. 0329), thereby already suggesting conditional downstream processing based on the claimed threshold condition. Therefore, Douglas in view of Siddiquee teach the limitation of “generate a transformed image…in response to a ratio of a region occluded by earwax being less than a threshold ratio compared to a region of the entire tympanum in the target image”, and a person of ordinary skill in the art would have recognized that Siddiquee’s transformation/localization techniques could improve Douglas’s tympanic pathology visualization and diagnostic workflow by improving diagnostic interpretation and visualization using known medical image enhancement techniques.
Applicant argues: The references fail to disclose “a second machine learning model, which is different from the first machine learning model”
Examiner replies: Douglas expressly discloses ML-based segmentation and feature extraction operations for tympanic membrane analysis (Par. 0172-0176; TM segmentation consists of pixel-based machine learning…supervised machine learning and the model…To generate training data, the user generates a training set of images…each image contains an outlined contour of the TM to yield the TM segmentation mask…The image subjects may include healthy TMs, pathological TMs (e.g., acute otitis media, otitis media with effusion, foreign bodies, etc.), or images that do not contain a TM), while Siddiquee expressly discloses a separate GAN-based image translation model configured to transform diseased medical images into corresponding healthy images (Pg. 192, Fig. 2 description; translate any image, diseased or healthy, into a healthy image, allowing diseased regions to be revealed by subtracting those two images…Section 1; GAN trained for virtual healing aims to turn any image, with unknown health status, into a healthy one. Pg. 197, Section 4.2, Left Column; The desired GAN behaviour is to translate diseased images to healthy ones while keeping healthy images intact…). The combined system therefore teaches a first ML model used for extraction/segmentation and a second, different ML model used for image transformation, as recited.
Applicant argues: Siddiquee fails to disclose displaying aligned transformed and target images
Examiner replies: Siddiquee expressly discloses lesion localization by subtracting the transformed healthy image from the original diseased image (Pg. 192, Fig. 2. Pg. 197, Section 4.2, Left Column; having translated the images into the healthy domain, we then detect the presence and location of a lesion in the difference image by subtracting the translated healthy image from the input image… Fig. 4b…ResNet-50-CAM at 32x32 resolution). Such subtraction-based localization necessarily requires the transformed healthy image and the original diseased image to remain spatially aligned at corresponding anatomical positions. Otherwise, subtraction of corresponding image regions would not accurately localize lesions as disclosed by Siddiquee. Accordingly, Siddiquee teaches aligned positional correspondence between the transformed and the target image.
Regarding the remaining arguments: Applicant argues with respect to the amended claim language, which is fully addressed in the prior art rejections set forth below.
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.
Claim(s) 1-11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Douglas et al. (US 20150065803), hereinafter referred to as “Douglas”, in view of Siddiquee et al. "Learning fixed points in generative adversarial networks: From image-to-image translation to disease detection and localization." In Proceedings of the IEEE/CVF international conference on computer vision, pp. 191-200. 2019, hereinafter referred to as “Siddiquee”.
Regarding claim 1, Douglas discloses an apparatus for processing a tympanum image (Abstract; methods and apparatuses for assisting the acquisition and analysis of images of the tympanic membrane), the apparatus comprising:
a processor configured to extract, from a tympanum image (Par. 0031; processor to: receive an image of the subject's ear canal…extract, at a plurality of different scales, a set of feature values for each of the subregions…identify, on a representation of the image, a tympanic membrane region of the image. Par. 0171; feature extraction consists of extracting a machine-readable set of image properties ("features")), a tympanum outline of the tympanum image (Par. 0029; identifying the tympanic membrane region may include any appropriate identification, including visual (e.g., identifying a tympanic membrane region from the image on a representation of the image by circling/outlining, highlighting, coloring, etc.). Par. 0172; TM segmentation map. Par. 0176; image contains an outlined contour of the TM to yield the TM segmentation map) and an earwax region of the tympanum image (Par. 0036; indicate when the image is obstructed (e.g., by wax, foreign body, etc.) …Par. 0214; color features may be extracted…color features may include…any color property associated with the TM or other outer ear structures, such as the ear canal, wax, hair, etc. Par. 0172; segmentation likelihood map. Par. 0176; pathological TMs (e.g., acute otitis media, otitis media with effusion, foreign bodies, etc.)) using a first machine learning model (Par. 0172-0176; TM segmentation consists of pixel-based machine learning…supervised machine learning and the model…To generate training data, the user generates a training set of images…each image contains an outlined contour of the TM to yield the TM segmentation mask…The image subjects may include healthy TMs, pathological TMs (e.g., acute otitis media, otitis media with effusion, foreign bodies, etc.), or images that do not contain a TM.),
obtain a target image for an entire tympanum (Par. 0029; a separate image including just the extracted tympanic membrane may be generated), a tympanum outline of the target image (Par. 0029; In general, identifying the tympanic membrane region may include any appropriate identification, including visual (e.g., identifying a tympanic membrane region from the image on a representation of the image by circling/outlining, highlighting, coloring, etc.)…or setting one or more registers associated with an image to indicate that the image includes a tympanic membrane, or portion of a tympanic membrane (e.g., above a threshold minimum amount of tympanic membrane region), and an earwax region of the target image based on the tympanum outline of the tympanum image (Par. 0039; indicate when the image is obstructed (e.g., by wax, foreign body, etc.) . Par. 0045; indicate an occlusion of an ear canal from the image)
(Douglas Par. 0039-0045; indicate when the image is obstructed (e.g., by wax, foreign body, etc.) …detecting at least a portion of a tympanic membrane from an image of a subject's ear canal…indicate an occlusion of an ear canal from the image. Par. 0214; color features may be extracted…Color features may include the mean, standard deviation, or other statistics of any color property associated with the TM or other outer ear structures, such as the ear canal, wax, hair, etc.) being less than a threshold ratio compared to a region of the entire tympanum in the target image (Douglas Par. 0036; guiding a subject to take an image may examine images (digital images) of a patient's ear canal being taken by the user, e.g., operating an otoscope to determine when a minimum amount of tympanic membrane is showing (e.g., more than 20%, more than 25%, more than 30%, more than 35%, more than 40%, more than 45%, more than 50%, more than 55%, more than 60%, more than 65%, more than 70%, more than 75%, more than 80%, more than 85%, more than 90%, more than 95%, etc.) in the image. Par. 0329; Thresholds to determine when an obstruction warrants ending the exam can be determined via a standard machine learning method, wherein the training set consists of a set of otoscopic exams and labels, where the labels indicate which exams have dangerous obstructions and which do not),
Examiner’s note: As noted above in examiner’s response to arguments, in reference to “in response to”, Douglas’s threshold determinations are not disclosed in isolation, but rather are expressly used to determine whether subsequent examination and image analysis operations should proceed, and therefore discloses conditionally controlling downstream image processing operations based on obstruction or visibility thresholds.
Douglas does not disclose generate a transformed image in which an abnormal region of the target image is changed to a normal region by inputting the target image to a second machine learning model, which is different from the first machine learning mode, the processor being configured to generate the transformed
In the same art of medical image analysis, Siddiquee discloses generate a transformed image in which an abnormal region of the target image is changed to a normal region by inputting the target image to a second machine learning model, which is different from the first machine learning mode, the processor being configured to generate the transformed (Pg. 192, Fig. 2 description; translate any image, diseased or healthy, into a healthy image, allowing diseased regions to be revealed by subtracting those two images…Section 1; GAN trained for virtual healing aims to turn any image, with unknown health status, into a healthy one. Pg. 197, Section 4.2, Left Column; The desired GAN behaviour is to translate diseased images to healthy ones while keeping healthy images intact…),
Examiner’s note: As noted above in examiner’s response to arguments, Douglas expressly discloses ML-based segmentation and feature extraction operations for tympanic membrane analysis (Par. 0172-0176), while Siddiquee expressly discloses a separate GAN-based image translation model configured to transform diseased medical images into corresponding healthy images (Pg. 192, Fig. 2 description. Section 1; GAN trained for virtual healing aims to turn any image, with unknown health status, into a healthy one. Pg. 197, Section 4.2). The combined system therefore teaches a first ML model used for extraction/segmentation and a second, different ML model used for image transformation, as recited.
and a display configured to display at least one of the transformed image and the target image so that a tympanum region of the transformed image is aligned at a position corresponding to a position of a tympanum region of the target image (Pg. 192, Fig. 2. Pg. 197, Section 4.2, Left Column; having translated the images into the healthy domain, we then detect the presence and location of a lesion in the difference image by subtracting the translated healthy image from the input image… Fig. 4b…ResNet-50-CAM at 32x32 resolution).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to incorporate Siddiquee’s medical-image transformation model into Douglas’s tympanic-image analysis system. Doing so allows improved analysis and visualization of tympanic abnormalities for users, patients, and clinicians. Douglas already detects tympanic membrane disease and evaluates image adequacy based on wax-occlusion thresholds, therefore, applying a known ML-based image to image translation would predictably allow clinicians to compare diseased regions with normalized anatomy, yielding predictable results in enhancing diagnosis and assessment using well-known medical imaging reconstruction techniques.
Regarding claim 2, Douglas in view of Siddiquee discloses the apparatus of claim 1, and further discloses wherein the display is configured to:
display a graphic object indicating (Douglas Par. 0044; The indicator may be visual, audible, or both…indicator includes a flash, highlight, signal, text message, or the like, which may be displayed on the screen (e.g., of display device) the abnormal region on the target image (Douglas Par. 0045; indicate an occlusion of an ear canal from the image…Par. 0063; indicating the probability of each of a plurality different diseases),
Douglas does not disclose display a graphic object indicating a region in which the abnormal region is replaced by the normal region on the transformed image.
In the same art of medical image analysis, Siddiquee discloses display a graphic object indicating a region in which the abnormal region is replaced by the normal region on the transformed image (Fig. 2).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the tympanic image analysis apparatus of Douglas to include a graphic object indicating abnormal region replaced by the normal region on the transformed image, as taught by Siddiquee. The motivation lies in the advantage of improved visualization and interpretation of transformed medical images. Clearly marking or indicating the transformed region on the display would provide visual analysis for users/medical practitioners or automated systems, thereby yielding predictable enhancements in diagnostic accuracy and user guidance.
Regarding claim 3, Douglas in view of Siddiquee discloses the apparatus of claim 1, and further discloses wherein the processor is configured to:
determine whether the tympanum image is about an entire tympanum based on the tympanum outline of the tympanum image (Douglas Par. 0029; identifying a tympanic membrane region from the image on a representation of the image by circling/outlining, highlighting, coloring, etc.…. portion of a tympanic membrane (e.g., above a threshold minimum amount of tympanic membrane region. Par. 0036; determine when a minimum amount of tympanic membrane is showing (e.g., more than 20%, more than 25%, more than 30%, more than 35%, more than 40%, more than 45%, more than 50%, more than 55%, more than 60%, more than 65%, more than 70%, more than 75%, more than 80%, more than 85%, more than 90%, more than 95%, etc.) in the image…),
and determine the target image based on the tympanum image in response to determining that the tympanum image is about an entire tympanum (Douglas Par. 0037; detecting at least a portion of the tympanic membrane from the image may comprise…estimating, for each individual subregion within the plurality of subregions, a probability that the individual subregion is part of a tympanic membrane based on the extracted sets of feature values for the individual subregion. Par. 0168-0189; TM Detection (Segmentation)).
Douglas and Siddiquee are combined for the reason set forth above with respect to claim 1.
Regarding claim 4, Douglas in view of Siddiquee discloses the apparatus of claim 1, and further discloses wherein the processor is configured to:
determine whether the tympanum image is about an entire tympanum based on the tympanum outline of the tympanum image (Douglas Par. 0029; identifying a tympanic membrane region from the image on a representation of the image by circling/outlining, highlighting, coloring, etc.…. portion of a tympanic membrane (e.g., above a threshold minimum amount of tympanic membrane region. Par. 0036; determine when a minimum amount of tympanic membrane is showing (e.g., more than 20%, more than 25%, more than 30%, more than 35%, more than 40%, more than 45%, more than 50%, more than 55%, more than 60%, more than 65%, more than 70%, more than 75%, more than 80%, more than 85%, more than 90%, more than 95%, etc.) in the image…),
obtain an additional tympanum image in response to determining that the tympanum image is about a portion of a tympanum (Douglas Par. 0040-0049; detecting one or more deeper regions in the image…indicating a direction to orient the otoscope based on the detected one or more deeper regions; determining if the image includes a tympanic membrane…indicating when an image of the tympanic membrane has been taken…detecting one or more deeper regions comprises: determining a field of view for the image),
extract a tympanum outline of the additional tympanum image and an earwax region of the additional tympanum image from the additional tympanum image (Douglas Par. 0043; extracting a set of feature values from a plurality of subregions from the image, estimating, for each subregion, a probability that the subregion is part of a tympanic membrane based on the extracted sets of feature values; and indicating when an image of the tympanic membrane has been taken) using the first machine learning model (Par. 0047; using a trained model to determine if the one or more regions are deeper regions in an ear canal),
update a temporary image by stitching the additional tympanum image to the tympanum image (Douglas Par. 0267-0269; one can capture multiple sections of the anatomical part of interest and then "stitch" them together into a composite image (i.e., a "panorama" or "mosaic”) …otoscopic TM stitching is shown in FIG. 21),
determine whether the temporary image is about an entire tympanum based on a tympanum outline of the temporary image (Douglas FIG. 22-23 and Par. 0269; Modified feature detection or feature matching to allow for matches between smooth frames, e.g., those containing a healthy tympanic membrane; and/or Alternate methods of matching frames e.g., via optical flow for videos),
and determine the target image based on the temporary image in response to determining that the temporary image is about an entire tympanum (Douglas Par. 0267-0269; composite image. Par. 0037; detecting at least a portion of the tympanic membrane from the image may comprise…estimating, for each individual subregion within the plurality of subregions, a probability that the individual subregion is part of a tympanic membrane based on the extracted sets of feature values for the individual subregion. Par. 0168-0189; TM Detection (Segmentation)). Examiner's note: composite image is used as the input image to perform the steps of determining the target image).
Douglas and Siddiquee are combined for the reason set forth above with respect to claim 1.
Regarding claim 6, Douglas in view of Siddiquee discloses the apparatus of claim 1, and further discloses wherein the processor is configured to:
calculate an objective function value (Douglas Par. 0175-0177; 0 to 1) between a temporary output image,
which is generated by applying the second machine learning model (Douglas Par. 0176; supervised machine learning) to a training abnormal tympanum image and a ground truth tympanum image (Douglas Par. 0175-; To generate training data, the user generates a training set of images, which may be frames from one or more videos, where each image contains an outlined contour of the TM to yield the TM segmentation mask…The image subjects may include healthy TMs, pathological TMs (e.g., acute otitis media, otitis media with effusion, foreign bodies, etc.), … TM segmentation maps may be provided as a "gold standard" output for the images.),
and repeatedly update a parameter of the second machine learning model so that the calculated objective function value converges (Douglas Par. 0175; further training/updating may be performed…extracted features may be fed to a machine learning method for classification. Par. 0185; The features may then be applied to an implementation of a pre-trained supervised machine learning classification model (e.g., a support vector machine or random forest model) included as part of the apparatus to predict whether the given pixel is part of the tympanic membrane or not. The output may be a "probability image," which consists of a probability from 0 to 1 that each processed pixel is part of the tympanic membrane.)
Douglas and Siddiquee are combined for the reason set forth above with respect to claim 1.
Regarding claim 7, Douglas in view of Siddiquee discloses the apparatus of claim 1, and further discloses wherein the processor is configured to repeatedly update a parameter of the first machine learning model so that an objective function value between temporary output data comprising a tympanum outline (Douglas Par. 0176; outlined contour of the TM) and an earwax region (Douglas color feature associated with wax in Par. 0214) extracted using the first machine learning model from a training tympanum image and ground truth data converges (Douglas Par. 0175; further training/updating may be performed…extracted features may be fed to a machine learning method for classification. Par. 0185; The features may then be applied to an implementation of a pre-trained supervised machine learning classification model (e.g., a support vector machine or random forest model) included as part of the apparatus to predict whether the given pixel is part of the tympanic membrane or not. The output may be a "probability image," which consists of a probability from 0 to 1 that each processed pixel is part of the tympanic membrane).
Douglas and Siddiquee are combined for the reason set forth above with respect to claim 1.
Regarding claim 8, Douglas in view of Siddiquee discloses the apparatus of claim 1, and further discloses wherein the processor is configured to provide an earwax removal guide (Douglas Par. 0039; additional guide by providing one or more directions, including directions on a display screen showing the images, audible cues, textual cues, or the like…when the image is obstructed (e.g., by wax, foreign body, etc. Par. 0362; use can rotate and move the mobile device… simulated pathologies…such as removal or wax)) in response to a case in which the ratio of the region occluded by earwax (Douglas Par. 0039-0045; indicate when the image is obstructed (e.g., by wax, foreign body, etc.) …detecting at least a portion of a tympanic membrane from an image of a subject's ear canal…indicate an occlusion of an ear canal from the image. Par. 0214; color features may be extracted…Color features may include the mean, standard deviation, or other statistics of any color property associated with the TM or other outer ear structures, such as the ear canal, wax, hair, etc.) is greater than or equal to the threshold ratio compared to the region of the entire tympanum in the target image (Douglas Par. 0036; guiding a subject to take an image may examine images (digital images) of a patient's ear canal being taken by the user, e.g., operating an otoscope to determine when a minimum amount of tympanic membrane is showing (e.g., more than 20%, more than 25%, more than 30%, more than 35%, more than 40%, more than 45%, more than 50%, more than 55%, more than 60%, more than 65%, more than 70%, more than 75%, more than 80%, more than 85%, more than 90%, more than 95%, etc.) in the image. Par. 0329; Thresholds to determine when an obstruction warrants ending the exam can be determined via a standard machine learning method, wherein the training set consists of a set of otoscopic exams and labels, where the labels indicate which exams have dangerous obstructions and which do not) and the display is configured to display the target image and the earwax removal guide (Douglas Par. 0297-0329; guidance system…images (or a subset of images) being received and/or displayed, to identify a TM…indication is displayed to the user).
Douglas and Siddiquee are combined for the reason set forth above with respect to claim 1.
Regarding claim 9, Douglas in view of Siddiquee discloses the apparatus of claim 1, and further discloses wherein the processor is configured to select one tympanum image (Douglas Par. 0056; the subject/user may be allowed to select one of the plurality of similar tympanic membrane images) from among a plurality of normal tympanum images (Douglas Par. 0011; provide similar images (including time course images) from a database of such images, particularly where the database images are associated with related images and/or diagnosis/prognosis information.), based on at least one of age, gender, and race of a user (Douglas Par. 0011; database of similar images (for which one or more clinical identifiers may be associated. Par. 0221-0224; clinical information may include, but is not limited to: Age, Race, Sex…clinical information falls into one of two possible categories: numerical or categorical, which can be treated differently when converting them to features that are suitable for machine learning…) in response to a case in which the ratio of the region occluded by earwax (Douglas Par. 0039-0045; indicate when the image is obstructed (e.g., by wax, foreign body, etc.) …detecting at least a portion of a tympanic membrane from an image of a subject's ear canal…indicate an occlusion of an ear canal from the image. Par. 0214; color features may be extracted…Color features may include the mean, standard deviation, or other statistics of any color property associated with the TM or other outer ear structures, such as the ear canal, wax, hair, etc.) is greater than or equal to the threshold ratio compared to the region of the entire tympanum in the target image (Douglas Par. 0036; guiding a subject to take an image may examine images (digital images) of a patient's ear canal being taken by the user, e.g., operating an otoscope to determine when a minimum amount of tympanic membrane is showing (e.g., more than 20%, more than 25%, more than 30%, more than 35%, more than 40%, more than 45%, more than 50%, more than 55%, more than 60%, more than 65%, more than 70%, more than 75%, more than 80%, more than 85%, more than 90%, more than 95%, etc.) in the image. Par. 0329; Thresholds to determine when an obstruction warrants ending the exam can be determined via a standard machine learning method, wherein the training set consists of a set of otoscopic exams and labels, where the labels indicate which exams have dangerous obstructions and which do not),
and the display is configured to display the one tympanum image and the target image by aligning a tympanum region of the one tympanum image at a position corresponding to the position of the tympanum region of the target image (Douglas Par. 0053; displaying an image of a tympanic membrane may include: extracting a plurality of image features from a first image of a subject's tympanic membrane, wherein the image features include color and texture data; combining the extracted features into a feature vector for the first image; identifying a plurality of similar tympanic membrane images from a database of tympanic membrane images by comparing the feature vector for the first image to feature vectors for images in the database of tympanic membrane images; displaying (e.g., concurrently) the first image and the plurality of similar tympanic membrane images and indicating the similarity of each of the similar tympanic membrane images to the first image).
Douglas and Siddiquee are combined for the reason set forth above with respect to claim 1.
Regarding claim 10, claim 10 is the method claim of apparatus claim 1, and is accordingly rejected using substantially similar rationale as to that which is set for with respect to claim 1.
Regarding claim 11, claim 11 is the CRM claim (Douglas Par. 0167; …non-transitory computer-readable storage medium as a set of instructions capable of being executed by a processor…) of apparatus claim 1, and is accordingly rejected using substantially similar rationale as to that which is set for with respect to claim 1.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JENNY NGAN TRAN whose telephone number is (571)272-6888. The examiner can normally be reached Mon-Thurs 8am-5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Alicia Harrington can be reached at (571) 272-2330. 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.
/JENNY N TRAN/Examiner, Art Unit 2615
/ALICIA M HARRINGTON/Supervisory Patent Examiner, Art Unit 2615
Prosecution Insights