Detailed Action
1. Claims 1-20 are pending in this Application.
Notice of Pre-AIA or AIA Status
2. 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 amendment
4. Applicant’s response to the last Office Action filed on 03/11/2026 has been entered and made of record.
5. Claims 1 and 11 have been amended.
.
Response to Argument
6. The Applicant’s argument filed 05/29/2026 is fully consider. For Examiner response see discussion below.
a. Applicants argue “At FIG. 9, Dascal presents a flowchart for detecting a metal wire in an x-ray image. The filters applied at steps 520 to 535 are applied sequentially to the image, to enhance the elongated structures (that is, the sought-after wires) in the image. At any given point, Dascal only has one filtered image, which is an image that has been filtered one or more times. The applicant teaches something different in these regards, and in particular, teachings applying different filters to the same image to provide a plurality of different filtered images.”
As to above argument [a], Examiner respectfully disagrees with the Applicant’s for the reason discuss below:
Dascal specifically teaches two flites the adaptive thresholding (see Fig. step 535) and intensity filter ( see Fig.1 step 510). The outputs image date of the X- ray image filtered by the adaptive thresholding and intensity filter are fussed using the “AND” operator ( see Fig.9 step 540).
It is known that Adaptive thresholding is an image filter technique that removes uneven brightness and shadows by calculating local pixel thresholds in small neighborhood windows instead of using one global value. On the other hand an intensity filter adjusts pixel brightness or contrast based on fixed global or local rules, while an adaptive thresholding filter binarizes an image by calculating a unique local threshold for each pixel based on its surrounding neighborhood. From the above description it is clear that two filters are different filters applied to the same x-ray image. The output of the two filters generate different filtered images of the same x-ray image .
b. The Applicant’s argue, “In addition, Dascal teaches merging a ridge enhancing filter output result with an adaptive intensity filter result using a pixel-wise AND operator, to thereby obtain a merged metallic wire mask component. Again, the applicant teaches something different in these regards, by using multi-cue probabilistic fusion to fuse the plurality of different filtered images. One advantage of using multi-cue probabilistic fusion is that spurious detections (such as false positive or false negative responses) are suppressed, thereby more accurately locating the radiopaque object (see paragraph 0061 of the applicant's specification). Notably, Dascal does not suppress spurious detections.”
As to above argument [b] Examiner agree with the Applicant’s argument. Specifically Dascal does not teach the multi-cue probabilistic fusion to fuse the plurality of different filtered images.
However, after further search and consideration a new prior art (“A novel edge detection in medical images by fusing of multi-model from different spatial structure clues”, by Jia et al.,) that teach the added limitation is found. Specifically Jia teaches A novel edge detection in medical images by fusing of multi-model from different spatial structure clues. It combines two matrices: one for the most probable distribution of edge points (based on neighborhood variance) and one for brightness difference weights. Fusing these matrices creates a final edge image using a threshold method (see abstract Fig.2, page 1294 1st par.,)
PNG
media_image1.png
221
664
media_image1.png
Greyscale
No additional argument is presented by the Applicant.
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 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 of this title, 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.
7. Claims 1-3,6-8, 11-13 and 16-18 are rejected r under 35 U.S.C. 103(a) as being unpatentable over Dascal et al., ( hereafter Dascal), US 20170140532 A, pub. 05/18/2017, in view of Jia Xibin et al., (hereafter Jia) “A novel edge detection in medical images by fusing of multi-model from different spatial structure clues”, Bio-Medical Materials and Engineering, pub. 2014.
As to claim 1, Dascal teaches A method (Abstract [0006] methods for detecting position and size of contrast cloud in an x-ray image including with respect to a sequence of x-ray images) comprising: by a control circuit ( [0085] on or more computer program products, i.e., one or more modules of computer program instructions encoded on a computer readable medium for execution by, or to control the operation of, a data processing apparatus):
accessing information regarding at least one field of view of a particular patient, which field of view contains information regarding at least one radiopaque object (Fig. 9 [0121] In step 535, bright areas in the image are rejected by performing adaptive thresholding on the input image as a processing step. Metallic wires are radio-opaque, and will appear as dark elongate regions on an x-ray image. );
processing the information regarding the at least one field of view using a plurality of different filters to yield a plurality of filtered fields of view that are each different from one another (Fig. 9,. [0117] and [0122] In step 540, the ridge enhancing filter output result and the adaptive intensity filter result are merged using a pixel-wise AND operator, to obtain a merged metallic wire mask component. The angiography image processing software modules and methods described herein connect and filter wire fragments that are detected in the images) each of the filtered fields of view comprising a differently filtered version of the at least one field of view( as discussed above Dascal applies two distinct filters—an intensity filter and an adaptive thresholding filter—to the same X-ray image, producing two different output images. The intensity filter modifies pixel brightness or contrast using set rules, while adaptive thresholding binarizes the image via unique local neighborhood threshold. From the above description it is clear that two filters are different filters applied to the same x-ray image. The output of the two filters generate different filtered images of the same x-ray image ):
fusing the plurality of filtered fields of view (Fig. 9, [0117] and [0122], In step 550, the wire can be extracted in fragments, and other components in the image which are not related to the wire can be detected. The wire fragments can be joined using a combined measurement of a takeoff angle and a distance between the fragments. The methods to determine the location of the wire and/or the wire tip from frames of data such as angiography frames(see [0072] ) by suppressing spurious detections ([0009], [0139], method includes eliminating false bifurcations. In order to obtain accurate results of bifurcation points, elimination of false bifurcation-like features such as vessel crossings and ribs is needed. For that purposes a series of one or more filters is applied as shown in [0139]);
however, it is noted that Dascal does not specifically teach the underline portion of the following limitation: “fusing the plurality of filtered fields of view using multi-cue probabilistic fusion”
On the other hand in the same filed of endeavor A novel edge detection algorithm in medical images by fusing of multi-model from different spatial structure clues of Jia teaches
fusing the plurality of filtered fields of view using multi-cue probabilistic fusion (Abstract Fig.2, page 1294 1st par., teaches A novel edge detection in medical images by fusing of multi-model from different spatial structure clues. It combines two matrices: one for the most probable distribution of edge points (based on neighborhood variance) and one for brightness difference weights. Fusing these matrices creates a final edge image using adaptive threshold method)It combines two matrices: one for the most probable distribution of edge points (based on neighborhood variance) and one for brightness difference weights. Fusing these matrices creates a final edge image using adaptive threshold method
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to replace the pixel-wise AND operator taught by Dascal with the multimodal spatial fusion method taught by Jia, because multimodal spatial fusion uses neighborhood variance and brightness weights with an adaptive threshold to capture structural details, outperforming a simple pixel-wise AND operator by preserving faint boundaries, reducing noise, and adapting to local contrast changes rather than dropping valid edge pixels of the metallic wires.
Claim 11 is rejected the same as claim 1 except claim 11 is directed to an apparatus claim. The rejection of claim 1coves all the limitation of claim 11.
As to claim 2, Dascal teaches the information regarding the at least one field of view comprises an x-ray image(Fig. 9, [006], ([0006], methods for detecting contrast cloud related parameters in an x-ray image including with respect to a sequence of x-ray images).
Claim 12 is rejected the same as claim 2 except claim 12 is directed to an apparatus claim. The rejection of claim 2 coves all the limitations of claim 12.
As to claim 3, Dascal teaches the information regarding the at least one field of view comprises only a single x-ray image ( Fig.7 [0111] . FIG. 7 illustrates an exemplary image 350 in which a potential position and size of a contrast cloud from a single x-ray frame has been detected.)
Claim 13 is rejected the same as claim 3 except claim 13 is directed to an apparatus claim. The rejection of claim 3 coves all the limitations of claim 13.
As to claim 6, Dascal teaches the plurality of different filters includes at least one image filter ( Fig.9, [0117], [0122] In step 540 of Fig.9 , the ridge enhancing filter output result and the adaptive intensity filter result are merged using a pixel-wise AND operator, to obtain a merged metallic wire mask component).
Claim 16 is rejected the same as claim 6 except claim 16 is directed to an apparatus claim. The rejection of claim 6 coves all the limitations of claim 16.
As to claim 7, Dascal teaches each of the plurality of different filters comprises an image filter( Fig.9, [0117],[0119], [0122] In step 520, image smoothing filter of the x-ray image, or image sequence, is performed to enhance elongated structures in the image. This filter is a modified anisotropic diffusion filter where the filter coefficients, at each iteration, are derived from the original image intensities combined with the blob and ridge detector)
Claim 17 is rejected the same as claim 7 except claim 17 is directed to an apparatus claim. The rejection of claim 7 coves all the limitations of claim 17.
As to claim 8, Dascal teaches the plurality of different filters includes at least one of: a contour detection filter (FIG. 11B. In one embodiment, such a filter or detector is implemented using a ridge enhancing filter, such as a Frangi filer or other suitable filter, that is applied to the image to enhance ridges in the image, as shown in FIG. 11B. A ridge enhancing filter can include a Hessian filter, a Frangi filter, or other ridge or edge
detectors.); an adaptive thresholding filter ([0108], [0110], In step A6, adaptive
thresholding is used on each pixel from the image created in step A5. The adaptive threshold being used is one that relates to the size of the neighborhood used to create the image in step A5, as shown in FIG. 6. In step A7, a component filter is used to remove large components from the image generated in step A6 );
Claim 18 is rejected the same as claim 8 except claim 18 is directed to an apparatus claim. The rejection of claim 8 coves all the limitations of claim 18.
8. Claims 9-10, 19 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Dascal, US 20170140532 A, in view of Jia “A novel edge detection in medical images by fusing of multi-model from different spatial structure clues”, further in view of Ibrahim et al., (hereafter Ibrahim), “Multi-Techniques for Analyzing X-ray Images for Early Detection and Differentiation of Pneumonia and Tuberculosis Based on Hybrid Features” , Pub. , 20 February 2023.
Regarding claim 9, while modified Dascal teaches the limitation of claim 1, but fails to teach the limitation claim 9.
On the other hand Ibrahim teaches the fused information regarding the at least one radiopaque object comprises a probabilistic-based likelihood image( Fig.1, Section 3: Materials and Methods, The X-ray images were enhanced to obtain improved images and then fed into the VGG16 and ResNet18, and second distinguishes between pneumonia and tuberculosis using an ANN network, based on fusing the features of VGG16 and ResNet18 before and after dimensionality reduction. It is known that ANN (Artificial Neural Network) are generally probabilistic or statistical models, particularly when using soft-max output layers, as they estimate the posterior probability of class membership.)
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 the well-known ANN (Artificial Neural Network) which are probabilistic or statistical models taught by Ibrahim into modified Dascal.
The suggestion/motivation for doing so would have been using the ANN to analyze image of radiopaque object offers significant advantages in enhancing detection accuracy, reducing image noise, and managing the uncertainties inherent in complex imaging, particularly in medical applications like X-ray, CT, and particle imaging.
Claim 19 is rejected the same as claim 9 except claim 19 is directed to an apparatus claim. The rejection of claim 9 coves all the limitation of claim 19.
As to claim 10, Ibrahim teaches the probabilistic-based likelihood image identifies a most-likely location of the at least one radiopaque object (Fig.1 the framework of the structure for the proposed systems for the diagnosis of X-rays of pneumonia and tuberculosis, and for distinguishing between them).
Claim 20 is rejected the same as claim 10 except claim 20 is directed to an apparatus claim. The rejection of claim 10 coves all the limitation of claim 20.
9. Claims 4-5 and 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over Dascal, US 20170140532 A, in view of Jia “A novel edge detection in medical images by fusing of multi-model from different spatial structure clues”, further in view Johnson; Frank (hereafter Johnson), US 20100010611A, pub . 01/14/2010.
Regarding claim 4,while modified Dascal teaches the limitation of claim 1, but fails to teach the limitation claim 4.
On the other hand Johnson teaches the at least one radiopaque object comprises a fiducial (claim 7, a fiducial having at least a portion of its structure constructed of a radiopaque material.)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to replace guided wires for identifying radiopaque taught by Dascal with implanted fiducial markers taught by Johnson.
The suggestion/motivation for doing so would have been using implanted fiducial markers instead of guided wires for identifying radiopaque objects (such as tumors) offers superior accuracy, improved patient comfort, logistical flexibility, and also allowing for continuous, real-time tracking of internal motion
Claim 14 is rejected the same as claim 4 except claim 14 is directed to an apparatus claim. The rejection of claim 4 coves all the limitation of claim 14..
As to claim 5, Johnson teaches the fiducial comprises an implanted fiducial (claim 7, an external radiation beam tracking system having a radiopaque material tracking system operable for tracking and identifying a coordinate of the radiopaque material of the fiducial when implanted in a patient and further operable to direct the external beam to focus on the coordinate).
Claim 15 is rejected the same as claim 5 except claim 15 is directed to an apparatus claim. The rejection of claim 5 coves all the limitation of claim 15.
Prior art of record but not applied in the rejection
1. “A Robust Multiple Cues Fusion based Bayesian Tracker”, 2007 IEEE International Conference on Robotics and Automation” pub. April 2007, to Xiaoqin Zhang et al., disclosed:
This paper presented a robust multiple cues based tracking algorithm in the Bayesian framework. In our implementation, a MOG(mixture of Gaussian) based appearance model and distance transform based shape model is employed to form a robust multi-cue fusion tracker. Our approach combine the merits of both stochastic and deterministic tracking approaches in a unified Bayesian framework: the mean-shift algorithm is embedded into the particle filter framework seamlessly to give a prior to the hypotheses generation process, which significantly decrease the particle numbers. Moreover, a selective updating scheme is employed to accommodate the changes of appearance and illumination.
2. “A review on multimodal medical image fusion: Compendious analysis of medical modalities, multimodal databases, fusion techniques and quality metrics”, Computers in Biology and Medicine, pub 2022, to Muhammad Adeel Azam et al., disclosed:
In this article, a compendious review of different medical imaging modalities and evaluation of related multimodal databases along with the statistical results is provided. The medical imaging modalities are organized based on radiation, visible-light imaging, microscopy, and multimodal imaging. Results: The medical imaging acquisition is categorized into invasive or non-invasive techniques. The fusion techniques are classified into six main categories: frequency fusion, spatial fusion, decision-level fusion, deep learning, hybrid fusion, and sparse representation fusion. In addition, the associated diseases for each modality and fusion approach presented. The quality assessments fusion metrics are also encapsulated in this article. Conclusions: This survey provides a baseline guideline to medical experts in this technical domain that may combine preoperative, intraoperative, and postoperative imaging, Multi-sensor fusion for disease detection, etc. The advantages and drawbacks of the current literature are discussed, and future insights are provided accordingly ( see Abstract)
PNG
media_image2.png
856
1050
media_image2.png
Greyscale
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.
Contact Information
Any inquiry concerning this communication or earlier communication from the examiner should be directed to Mekonen Bekele whose telephone number is (469) 295-9077.The examiner can normally be reached on Monday -Friday from 9:00AM to 6:50 PM Eastern Time.
If attempt to reach the examiner by telephone are unsuccessful, the examiner’s supervisor Eng, George can be reached on (571) 272-7495.The fax phone number for the organization where the application or proceeding is assigned is 571-237-8300. Information regarding the status of an application may be obtained from the patent Application Information Retrieval (PAIR) system. Status information for published application may be obtained from either Private PAIR or Public PAIR.
Status information for unpublished application is available through Privet PAIR only.
For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have question on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866.217-919 (tool-free)
/MEKONEN T BEKELE/Primary Examiner, Art Unit 2699
Prosecution Insights