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 .
Response to Arguments
Rejections made under 35 U.S.C. 112(b) are withdrawn.
Applicant’s arguments with respect to claims 1-2, 4-6, 8-10, 13-15, 17, and 22 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-2, 4-7, 10, 13-17 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Guetter et al. (US 2012/0087561 A1), (hereinafter, Guetter) in view of Carolus et al. (US 11266380 B2), (hereinafter Carolus) and further in view of Wenzel et al. (US 10331981 B2), (hereinafter, Wenzel)
Regarding claim 1, Guetter teaches a computer-implemented method for providing a second result dataset of a second medical image of a patient (Guetter, “Exemplary embodiments of the present invention provide systems and methods for propagating user edits of computer-derived segmentation and/or computer-identified landmarks throughout a time series of images.”, pg. 2, paragraph 0025, lines 1-4, see Fig. 1 and 5), the method comprising:
at least one of receiving or determining a first result dataset, wherein the first result dataset is generated by an image-processing algorithm processing a first medical image of the patient acquired during an examination of the patient (Guetter, “First, image data may be acquired (Step S11). As discussed above, image data may be medical image data. The image data may be of N-dimensions, where N is a positive integer, and may include a time series of images… Segmentation may then be performed on the acquired image data (Step S12). The performance of segmentation may include identification of one or more regions-of interest ("ROI’s") within the image data. The segmentation may be performed across multiple frames of the acquired image, for example, all frames may be segmented.”, pg. 3, paragraphs 0030 and 31, lines 1-4 and 1-6, respectively, A time series of image frames are acquired. Segmentation is performed to generate multiple datasets corresponding to regions of interest for each image of the series.);
receiving a modified first result dataset, wherein the modified first result dataset is based on a user modification of the first result dataset (Guetter, “The user may then perform one or more edits to adjust the computer-calculated segmentation (Step S13). Editing of the segmentation results may be performed either at predetermined frames or frames selected by the user. The user may use a cursor or touchscreen to manually adjust the segmentation results to better fit the anatomical structure… Each image frame that the user edits may become a "keyframe."”, pg. 3, paragraph 0032 and 0033, lines 1-6 and 1-2, respectively);
receiving the second medical image of the patient, wherein the first medical image and the second medical image are of the same type (Guetter, “The time sequence of images may include a sequence of x-rays, magnetic resonance (MR) images, or computed tomography (CT) images.”, pg. 2, paragraph 0016, lines 5-7, “Exemplary embodiments of the present invention may then use the edits made to the one or more keyframes to automatically adjust one or more other image frames (Step S14).”, pg. 3, paragraph 0034, lines 1-4, The time series of images, taken from the same imaging modality, are initially received for keyframe selection and user modification. After a first modified result has been received by the user (i.e., an edited keyframe), the system receives additional images of the time series for further processing, such as propagating the user edits to other frames. Thus, the system receives the second medical image after receiving the first modified result, as required.);
determining the second result dataset of the second medical image based on a comparison of the first result dataset and the modified first result dataset, the determining the second result dataset including
generating the second result dataset by processing the second medical image with the image-processing algorithm (Guetter, “First, image data may be acquired (Step S11)… Segmentation may then be performed on the acquired image data (Step S12). The performance of segmentation may include identification of one or more regions-of interest ("ROI’s") within the image data. The segmentation may be performed across multiple frames of the acquired image, for example, all frames may be segmented.”, pg. 3, paragraphs 0030 and 31, lines 1-4 and 1-6, respectively, The system further process each image of the time series using a segmentation algorithm to generate multiple datasets indicating regions of interest. Note that the claim does not require that the image-processing algorithm used to generate the second result dataset must occur after the user modification is received. Under BRI, the same second image may be subjected to segmentation at an earlier stage of the process.), and
modifying the second result dataset based on the comparison of the first result dataset and the modified first result dataset, wherein the modifying the second result dataset is executed after the generating the second result dataset (Guetter, “Exemplary embodiments of the present invention may then use the edits made to the one or more keyframes to automatically adjust one or more other image frames (Step S14).”, pg. 3, paragraph 0034, lines 1-4, “Propagation of the edits may occur at a per-pixel level. For example, if a given pixel in a keyframe is moved up and to the right, a corresponding pixel in a proximate image frame may also be moved up and to the right”, pg. 3, paragraph 0037, lines 1-4, “The function
Φ
may represent a deformation field that acts upon the segmentation/landmarks of the unedited frame(s) to propagate the user edits.”, pg. 4, paragraph, 0043, lines 1-3, The system implicitly performs a comparison between the unedited segmentation and the manually edited segmentation in a keyframe. This comparison captures the manual edit as a deformation, which can then be propagated to other frames in the time series.), and the modifying the second result dataset includes at least one of inserting a first medical finding into the second result dataset, removing a second medical finding from the second result dataset, or altering a third medical finding within the second result dataset (Guetter, “The user may use a cursor or touchscreen to manually adjust the segmentation results to better fit the anatomical structure.”, pg. 3, paragraph 0032, lines 4-6, The user alters the initial segmentation result in the keyframe. This altered result can then be applied to modify additional images of the series.); and
providing the second result dataset (Guetter, see Fig. 3 and 4),
wherein the image-processing algorithm is not modified between generating the first result dataset and determining the second result dataset (Guetter, “Some approaches therefore use user modifications as a basis for re-executing the segmentation algorithm. However, such approaches may be computationally expensive”, pg. 1, paragraph 0007, lines 8-11, “Image segmentation may be automatically performed using a computer algorithm. The manual edits may be provided by a human user and include manual adjustments to the ROI to more accurately represent a particular structure. Propagation of the manual edits to the other image frames may include modifying the ROI of one or more of the image frames that have not been manually edited in a manner similar to the manner of the manual edits.”, pg. 1, paragraph 0014, lines 11-20, The segmentation algorithm is executed only once on all frames in the time series. Once the initial segmentation is complete, manual edits can be applied to selected keyframes. These edits are then propagated to other frames in the series without any re-execution or modification of the original algorithm.).
Guetter does not teach wherein the second medical image is acquired during a follow-up examination of the patient.
However, Carolus teaches wherein the second medical image is acquired during a follow-up examination of the patient (Carolus, “The present invention is based on the idea of using 3D scout ultrasound images for establishing a correspondence between a first and a second 2D ultrasound image. The solution presented herein is particularly advantageous for providing comparable 2D ultrasound images from a first, initial 2D ultrasound examination and a second, follow-up 2D ultrasound examination.”, column 3, lines 11-17, “The first 3D scout ultrasound image and the first 2D ultrasound image can be stored together with information or data indicative of their relative position and/or orientation. This data can be received by the image processing device together with the first 3D scout ultrasound image and the first 2D ultrasound image. For example, the coordinates and orientation of the first 2D ultrasound image with respect to the first 3D scout ultrasound image can be stored… When a second, follow-up 2D ultrasound image with an identical view is required, a second 3D scout ultrasound scan be acquired and registered with the first, initial 3D scout ultrasound image. Through the knowledge of their correspondence and the relative orientation and/or position of the first, initial 2D ultrasound image with respect to the first 3D scout ultrasound image, the corresponding control signal for acquisition of the second, follow-up 2D ultrasound image can be deduced and the follow-up 2D ultra-sound image with an identical view as the initial 2D ultrasound image can be acquired.”, columns 3 and 4, lines 52-67 and 1-6, respectively, “Generally speaking, a first (scout) ultrasound image can refer to an initial examination and a second (scout) ultrasound image can refer to a follow-up examination. A follow-up examination may be carried out at a later point in time, for example a few weeks or months after the initial examination, to assess a healing process or progression of a disease. For example, the first 3D scout ultrasound image and the first 2D ultrasound image are acquired together at the initial examination, whereas the second 3D scout ultrasound image and the second 2D ultrasound image are subsequently acquired at the follow-up examination.”, column 4, lines 36-46). Guetter teaches propagating manual user edits to regions of interest across a time series of medical images (Guetter, paragraph 0025-27). Guetter teaches that this time series of medical images is taken over a span of time but does not specify that the time sequence corresponds to follow-up examinations for the patient. Carolus teaches capturing medical images during initial and follow-up patient examinations and performing registration of the images to a common coordinate frame (see above). Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to have modified time sequence of Guetter to include time spans corresponding to follow-up examinations as taught by Carolus (Carolus, columns 3 and 4, lines 52-67 and 1-6, respectively, column 4, lines 36-46). The motivation for doing so would have been to enable automatic propagation of manuel edits from initial examination to follow-up examination, thereby reducing the time required by physicians to process follow-up images. The combination of Guetter in view of Carolus would use the initial and follow-up examination image registration methods of Carolus to provide the transformation necessary to propagate user edits across the separate examination. Further, one skilled in the art could have combined the elements as described above by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine the teachings of Guetter with Carolus to obtain the invention as specified above.
Guetter in view of Carolus does not teach wherein each of the first medical finding, the second medical finding, and the third medical finding is at least one of a quantitative finding or a qualitative finding.
However, Wenzel teaches wherein each of the first medical finding, the second medical finding, and the third medical finding is at least one of a quantitative finding or a qualitative finding (Wenzel, “The role of imaging in the detection and differential diagnosis of neuro-degenerative diseases has increased in recent years. One reason is the emerging availability of quantification techniques that are able to detect subtle changes in the brain which occur in an early phase of the disease, or even in a pre-symptomatic phase… Image analysis techniques help quantify brain atrophy by classifying the brain tissue voxels into different tissue classes such as Gray Matter (GM), White Matter (WM), and Cerobrospinal Fluid (CSF).”, column 1, lines 25-40, “The above measures involve accessing an image of a brain of a patient. The image may thus represent a brain scan, and may be obtained from various imaging modalities, including but not limited to Tl-weighted Magnetic Resonance Imaging (MRI). An automated tissue classification technique is applied to the image based on a prior probability map… Having obtained the tissue classification map, the tissue classification map is displayed on a display and a user is enabled to provide user feedback which is indicative of an area of misclassification in the tissue classification map and which is indicative of a correction of the misclassification. As such, the user provides user feedback which is indicative of where a misclassification occurred and at what the correction should be. For example, the user feedback may indicate a region to be biased towards white matter.”, column 3, lines 19-51, An automatic brain tissue classification is performed on a medical image using a prior probability map, generating qualitative data (e.g., tissue class labels) in the form of a classification map. A user is enabled to correct this qualitative data by identifying misclassified regions and specifying corrections.).
Guetter in view of Carolus teaches propagating user corrections made to segmentation results across a time series of medical images (Guetter, “FIG.1 is a flow chart illustrating a method for propagating user edits of computer-derived segmentation throughout a time series of images according to an exemplary embodiment of the present invention.”, pg. 3, paragraph 0029, lines 1-4, see Fig. 1). Specifically, Guetter in view of Carolus teaches deformation-aware propagation of user edits which are made to segmentation results of regions of interest (Guetter, “The computer-derived segmentation may include the identification of a region-of-interest (ROI) which may include the delineation of a particular anatomical structure, a region or tumor of diseased tissue, a foreign body, or any other aspect of the imagery that is of particular concern.”, pg. 2, paragraph 0026, “The function <I> may represent a deformation field that acts upon the segmentation/landmarks of the unedited frame(s) to propagate the user edits.”, pg. 4, paragraph 0043, lines 1-3), but does not expressly teach the propagation of qualitative or quantitative data. Wenzel teaches medical image tissue segmentations and classification, which utilizes user edits for qualitative data corrections made to medical images (see above). Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to have modified the segmentation method of Guetter in view of Carolus to include qualitative data such as tissue classification, to be corrected by the user, as taught by Wenzel (Wenzel, column 3, lines 19-51). The motivation for doing so would have been to generate a robust system which considers user corrections for both segmentation and classification, thereby enabling an accurate assesses for brain atrophy across a time series of images (as suggested by Wenzel, “Brain tissue classification is particularly useful in assessing brain atrophy, since the gray matter volume serves as a biomarker for cortical atrophy.”, column 1, lines 37-40). The combination of Guetter in view of Carolus and further in view of Wenzel would generate a dual segmentation and classification system, in which user corrections to qualitative data (e.g., tissue classification maps) can be propagated across the time series of medical images. This would be accomplished by evaluating deformation fields corresponding to both segmentation and classification map corrections. Further, one skilled in the art could have combined the elements as described above by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine the teachings of Guetter in view of Carolus with Wenzel to obtain the invention as specified in claim 1.
Regarding claim 2, Guetter in view of Carolus and further in view of Wenzel teaches the method according to claim 1, further comprising: receiving the first medical image, and determining the first result dataset by processing the first medical image with the image-processing algorithm (Guetter, “First, image data may be acquired (Step S11). As discussed above, image data may be medical image data. The image data may be of N-dimensions, where N is a positive integer, and may include a time series of images… Segmentation may then be performed on the acquired image data (Step S12). The performance of segmentation may include identification of one or more regions-of interest ("ROI’s") within the image data. The segmentation may be performed across multiple frames of the acquired image, for example, all frames may be segmented.”, pg. 3, paragraphs 0030 and 31, lines 1-4 and 1-6, respectively).
Regarding claim 4, Guetter in view of Carolus and further in view of Wenzel teaches the method according to claim 1, wherein the determining the second result dataset further comprises: determining a mapping between (i) medical findings contained at least one of in the first result dataset or in the modified first result dataset and (ii) medical findings contained in the second result dataset, wherein the modifying the second result dataset is based on said mapping (Guetter, “function
Φ
may be generated to transform edits made in a keyframe to another frame of the image sequence and thereby generate the mapping between the frames to propagate individual locations,”, pg. 4, paragraph 0042, lines 1-4, A mapping of individual findings is established between the frames in order to propagate the edits made on the keyframe.).
Regarding claim 5, Guetter in view of Carolus and further in view of Wenzel teaches the method according to claim 4, wherein the determining the second result dataset further comprises: determining a registration between the first medical image and the second medical image at least one of based on the first result dataset and the second result dataset or based on the first medical image and the second medical image, wherein the mapping between medical findings contained in the first result dataset and medical findings contained in the second result dataset is based on said registration (Guetter, “The function
Φ
may be generated by a registration of all frames representing the geometrical mapping between the frames.”, pg. 4, paragraph 0042, 7-9, All frames of the series are registered to facilitate the mapping.).
Regarding claim 6, Guetter in view of Carolus and further in view of Wenzel teaches the method according to claim 5, wherein at least one of the registration or the mapping is based on a deformable transformation (Guetter, “The function
Φ
may represent a deformation field that acts upon the segmentation/landmarks of the unedited frame(s) to propagate the user edits.”, pg. 4, paragraph, 0043, lines 1-3, “”, A deformation field is used to model the manual edits applied to the keyframe. This deformation is then used to transform and propagate the edits into the other frames at different time points.).
Regarding claim 10, Guetter in view of Carolus and further in view of Wenzel teaches the method according to claim 1, wherein at least one of
the modified first result dataset includes a false-negative medical finding not contained in the first result dataset, and the first medical finding corresponds to the false-negative medical finding;
the first result dataset includes a false-positive medical finding not contained in the modified first result dataset, and the second medical finding corresponds to the false-positive medical finding; or
the modified first result dataset includes a modified medical finding corresponding to a modification of an original medical finding contained in the first result dataset, the third medical finding corresponds to the original medical finding, and the altering the third medical finding is performed in accordance with the modification of the original medical finding (Guetter, “The user may use a cursor or touchscreen to manually adjust the segmentation results to better fit the anatomical structure.”, pg. 3, paragraph 0032, lines 4-6, The initial segmentation of the keyframe is manually edited by a user to produce an altered segmentation dataset. This altered result can then be applied to modify additional images of the series. The combination of Guetter in view of Wenzel would enable this manual edit to be performed additionally on qualitative data, such as tissue classification.).
Regarding claim 13, Guetter in view of Carolus and further in view of Wenzel teaches the method according to claim 1, wherein the providing the second result dataset comprises: providing an indication about at least one of modifications of the second result dataset or modifications of the image-processing algorithm (Guetter, “FIG. 3 illustrates a sequence of image frames including keyframes and image frames that are not keyframes and further illustrates the effect of the keyframes on the other frames according to an exemplary embodiment of the present invention.”, pg. 4, paragraph 0044, see Fig. 3, Frames (b)-(d) and (f) represent non-keyframes that are modified based on propagation of user defined edits.).
Claim 14 corresponds to claim 1, additionally reciting a providing system comprising an interface unit and computation unit. Guetter in view of Carolus and further in view of Wenzel teaches an interface unit and computation unit (Guetter, “The computer system referred to generally as system 1000 may include, for example, a central processing unit (CPU) 1001, random access memory (RAM) 1004, a printer interface 1010, a display unit 1011…”, pg. 5, paragraph 0061, lines 1-4) to perform the method according to claim 1. As indicated in the analysis of claim 1, Guetter in view of Carolus and further in view of Wenzel teaches the method according to claim 1. Therefore, claim 14 is rejected for the same reason of obviousness as claim 1.
Claim 15 corresponds to claim 1, additionally reciting a non-transitory computer-readable storage medium. Guetter in view of Carolus and further in view of Wenzel teaches a non-transitory computer-readable storage medium (Guetter, “A computer system includes a processor and a non-transitory, tangible, program storage medium, readable by the computer system,”, pg. 2, paragraph 0017, lines 1-3) to perform the method according to claim 1. As indicated in the analysis of claim 1, Guetter in view of Carolus and further in view of Wenzel teaches the method according to claim 1. Therefore, claim 15 is rejected for the same reason of obviousness as claim 1.
Claim 17 corresponds to claim 1, additionally reciting a providing system comprising a memory and processor. Guetter in view of Carolus and further in view of Wenzel teaches the addition of a memory and processor (Guetter, “The computer system referred to generally as system 1000 may include, for example, a central processing unit (CPU) 1001, random access memory (RAM) 1004…”, pg. 5, paragraph 0061, lines 1-4) to perform the method according to claim 1. As indicated in the analysis of claim 1, Guetter in view of Carolus and further in view of Wenzel teaches the method according to claim 1. Therefore claim 17 is rejected for the same reason of obviousness as claim 1.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Guetter et al. (US 2012/0087561 A1) in view of Carolus et al. (US 11266380 B2) and further in view of Wenzel et al. (US 10331981 B2) and Guo (US 2015/0242697 A1).
Regarding claim 8, Guetter in view of Carolus and further in view of Wenzel teaches the method according to claim 7, wherein the modifying the second result dataset further comprises:
determining a first region within the first medical image and a second region within the second medical image, wherein the first region and the second region correspond to at least one of the first medical finding to be inserted, the second medical finding to be removed or the third medical finding to be altered (Guetter, “Segmentation may then be performed on the acquired image data (Step S12). The performance of segmentation may include identification of one or more regions-ofinterest
("ROIs") within the image data.”, pg. 3, paragraph 0031, lines 1-4, The system performs segmentation for regions of interest. This allows the user edits to be propagated between corresponding regions of interest of the time series of medical images.).
Guetter in view of Carolus and further in view of Wenzel does not teach determining a similarity score between the first region and the second region, wherein at least one of the inserting the first medical finding, the removing the second medical finding or the altering the third medical finding is executed only in response to the similarity score fulfilling a criterion.
However, Guo teaches determining a similarity score between the first region and the second region, wherein at least one of the inserting the first medical finding, the removing the second medical finding or the altering the third medical finding is executed only in response to the similarity score fulfilling a criterion (Guo, “At 214, a template matching algorithm can be performed based on differences between the respective first and second neutrosophic similarity Scores for each of the pixels of the first and second images,”, pg. 7, paragraph 0059, lines 1-4, “Then, at 216, the first and second images can be registered using the one or more registration parameters. For example, the template (e.g., the 3D template, etc.) can be transformed using the optimal Xo Yo Zo, and 𝝓 as the registration parameters, and the transformed result can be used as the object region within the second image.”, pg. 7 and 8, paragraph 0059, lines 25-30, A similarity between regions is determined. The region of the first image is altered and applied to the second image based on the calculated similarity score per pixel).
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to have modified Guetter in view of Carolus and further in view of Wenzel by including the template matching algorithm as taught by Guo (Guo, pg. 7 and 8, paragraph 0059) to determine a similarity score between regions in a set of images for annotation insertion. The motivation for doing so would have been to implement a quantifiable process for importing particular area or volumes of interest across similar medical images, thereby assisting in the current evaluation of the image (as suggested by Guo, “Furthermore, during a real-time visualization and evaluation, prior analysis of a particular area or volume of interest could be imported, to assist in the current evaluation of the image.”, pg. 1, paragraph 0002, lines 15-18). Further, one skilled in the art could have combined the elements as described above by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine the teachings of Guetter in view of Carolus and further in view of Wenzel with Guo to obtain the invention as specified in claim 8.
Claim 22 is rejected under 35 U.S.C. 103 as being unpatentable over Guetter et al. (US 2012/0087561 A1) in view of Carolus et al. (US 11266380 B2) and further in view of Wenzel et al. (US 10331981 B2) and Riklin Raviv et al. (US 20170301085 A1), (hereinafter Riklin Raviv).
Regarding claim 22, Guetter in view of Carolus and further in view of Wenzel teaches the method according to claim 1. Guetter in view of Carolus and further in view of Wenzel does not teach wherein at least one of: the modified first result dataset includes a false-negative medical finding not contained in the first result dataset, and the first medical finding corresponds to the false-negative medical finding; or the first result dataset includes a false-positive medical finding not contained in the modified first result dataset, and the second medical finding corresponds to the false-positive medical finding.
However, Riklin Raviv teaches wherein at least one of: the modified first result dataset includes a false-negative medical finding not contained in the first result dataset, and the first medical finding corresponds to the false-negative medical finding; or the first result dataset includes a false-positive medical finding not contained in the modified first result dataset, and the second medical finding corresponds to the false-positive medical finding (Riklin Raviv, “3D interactive segmentation of medical images is disclosed herein, which provides an automated segmentation algorithm integrated with contextual knowledge, not readily available in the images alone, provided by an experienced physician or another human handler (jointly referred to herein as a “user”). Thus, the disclosed 3D interactive segmentation may provide more accurate segmentation results.”, pg. 3, paragraph 0029, lines 1-8, “Reference is now made to FIGS. 3A-3D, which show various views (i.e., axial, coronal, sagittal and 3D) of a CT 3D medical image of CH in a human brain of various patients (patient 1, patient 2, patient 3 and patient 4, correspondingly) segmented according to the disclosed probabilistic model. FIGS. 3A-3D present qualitative results of some of the tested cases. The fully automated segmentation (i.e., according to step 110 of the method of FIG. 1) is indicated in white dots (i.e., by a dotted boundary). The user input (i.e., user clicks according to step 120 of the method of FIG. 1) in indicated by white plus signs for false positive (i.e., indicating areas to be removed from the segmented ROI) and by white asterisks for false negative (i.e., indicating areas to be added to the segmented ROI). The final segmentation, i.e., with user interaction, is indicated by a white line (i.e., by a line boundary).”, pg. 8, paragraph 0073, lines 1-16).
Guetter in view of Carolus and further in view of Wenzel teaches propagating user edits, which correspond to user applied corrections of segmentation results, for a time series of images taken of patients (Guetter, “Exemplary embodiments of the present invention provide systems and methods for propagating user edits of computer-derived segmentation and/or computer-identified landmarks throughout a time series of images… The computer-derived segmentation may include the identification of a region-of-interest (ROI) which may include the delineation of a particular anatomical structure, a region or tumor of diseased tissue, a foreign body, or any other aspect of the imagery that is of particular concern. The user edits may include changes made to the delineation of the ROI.”, pg. 2, paragraph 0025-0027). Guetter in view of Carolus and further in view of Wenzel does not teach the insertion or removal of false-negative or false-positive medical findings. Riklin Raviv teaches an interactive segmentation of medical findings, which includes a user indicating false-negative and/or false-positive regions to be inserted or removed from segmentation results (see above). Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to have modified the user applied corrections of Guetter in view of Carolus and further in view of Wenzel to include the insertion or removal of false-negative or false-positive medical findings as taught by Riklin Raviv (Riklin Raviv, pg. 8, paragraph 0073, lines 1-16, see Fig. 3A-3D). The motivation for doing so would have been to allow the user directly flag incorrect segmentation regions (false-negative/false-positive) for system correction, thereby reducing the amount of manual editing required by the user. Further, one skilled in the art could have combined the elements as described above by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine the teachings of Guetter in view of Carolus and further in view of Wenzel with Riklin Raviv to obtain the invention as specified in claim 22.
Allowable Subject Matter
Claim 9 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
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 whose telephone number is (703)756-5533. The examiner can normally be reached Monday-Friday 9:00-5:00 (ET).
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, Sumati Lefkowitz can be reached on (571) 272-3638. 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.
/CONNOR L HANSEN/Examiner, Art Unit 2672
/SUMATI LEFKOWITZ/Supervisory Patent Examiner, Art Unit 2672
Prosecution Insights