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 .
Priority
Receipt is acknowledged that application is a National Stage application of PCT/EP2021/070768 with a priority date of 07/26/2021 is acknowledged under 35 USC 119(e) and 37 CFR 1.78.
Receipt is acknowledged that application claims priority to foreign application with application number EP20188914.4 dated 07/31/2020. Copies of certified papers required by 37 CFR 1.55 have been received. Priority is acknowledged under 35 USC 119(e) and 37 CFR 1.78.
Claim Status
This action is in response to the application filed on March 11, 2026, claim(s) 1-9, 13-14, and 16 are pending and have been examined.
Response to Arguments
Argument: On page 7, the applicant alleges, “Vega does not teach defining any specific imaging plane or volume based on the landmark’s predicted presence or position.”
Response: The examiner respectfully disagrees. Vega teaches, in Fig. 2, Col 7, Lines 60-67 – Col 8, Lines 1-9, “At step 214, a diagnostic spiral CT scan is automatically started at the predicted beginning location of the target organ. The localizer spiral CT scan continues at the first x-ray intensity until the beginning of the target organ is anticipated in the real-time localizer scan images and proximity to the predicted start location of is detected (e.g., it is determined that the scan is within a predetermined distance of the predicted start location of the target organ). Once proximity to predicted location of the anatomical landmark (e.g., lung apex) indicating the beginning of the target landmark is detected, the x-ray intensity is automatically adjusted to drive the x-ray intensity up to the second x-ray intensity used for a diagnostic scan of the target organ, such that the diagnostic part of the CT scan of the target organ starts at the predicted beginning location of the target organ, such that the diagnostic part of the CT scan of the target organ starts at the predicted beginning location of the target organ,” the predicted beginning location of the target organ is considered to be the predetermined anatomical landmark; the scan of the target organ starts at the predicted beginning location of the target organ and a spiral CT scan is automatically started at the predicted beginning location of the target organ, a spiral CT scan captures a complete anatomical volume of data in a single pass, therefore, a volume based on the landmark’s predicted presence or position is imaged.
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.
Claim(s) 1, 8-9, 13, and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Liu et al, WO 2016182551 in view of .
Regarding claim 1, Liu teaches
A computer-implemented method of predicting a presence and/or position of a predetermined anatomical landmark with respect to a computed tomography medical image the computer-implemented method comprising (see Liu, Paragraph [0012], “a method and system for landmark detection in medical images using deep neural networks”, and Liu, Paragraph [0014], “medical image can be acquired using any type of imaging modality, such as computed tomography (CT), magnetic resonance imaging (MRI), ultrasound, x-ray fluoroscopy, position emission tomography (PET), Dyna CT, etc”):
obtaining the medical image that contains a plurality of pixels or voxels (see Liu, Paragraph [0012], “a method and system for landmark detection in medical images using deep neural networks.”, and Liu, Paragraph [0014], “medical image can be acquired using any type of imaging modality, such as computed tomography (CT), magnetic resonance imaging (MRI), ultrasound, x-ray fluoroscopy, position emission tomography (PET), Dyna CT, etc.”),
processing the medical image using a machine-learning algorithm to generate, for each pixel or voxel of the medical image, an indicator representing a likelihood that the corresponding pixel or voxel represents part of a predetermined anatomical landmark (see Liu, Paragraph [0021], “the trained deep neural can be a discriminative deep neural network that calculates, for an image patch centered at a voxel, a probability that the target landmark is located at that voxel”, and Liu Paragraph [0025], “For example, the medical image or a portion of the medical image can be displayed on the display device, and the landmark location can be highlighted or annotated in the displayed image. In a possible embodiment, a probability map in which each voxel of the medical image is assigned a color corresponding to a detection probability calculated for that voxel by the trained deep neural network can be displayed on the display device,” the target landmark is considered to be a predetermined anatomical landmark; the highlighted, annotated and/or assigned color is considered to be an indicator);
and processing a plurality of the generated indicators to predict the presence and/or position of the predetermined anatomical landmark with respect to the medical image (see Liu, Paragraph [0024], “the trained deep neural network calculates a probability for each voxel based on the subset of voxels input to the deep neural network from the image patch centered at that voxel, and either selects a voxel having the highest probability or clusters a number of voxels having highest probabilities to determine the location of the landmark in the medical image”).
Liu does not expressively teach
wherein the medical image is a non-diagnostic survey image that has a lower resolution than a diagnostic image of a subsequent medical imaging scan
defining, using the predicted presence and/or position of the predetermined anatomical landmark, a plane and/or a volume to be imaged during the subsequent medical imaging scan, wherein the plane and/or the volume is defined so as to either avoid irradiating the predetermined anatomical landmark or to capture a volume which includes the landmark;
and controlling a medical imaging scan in accordance with the plane and/or the volume in order to acquire the diagnostic medical image during the subsequent medical imaging scan.
However, Vega in a similar invention in the same field of endeavor teaches
wherein the medical image is a non-diagnostic survey image that has a lower resolution than a diagnostic medical image of a subsequent medical imaging scan (see Vega, Col 6, Lines 19-35, “At step 210, a localizer spiral scan is automatically started at the beginning of the confidence range before the target organ. The localizer spiral CT scan is a spiral CT acquisition (i.e., acquisition acquired while rotating the gantry around the patient), that is performed with a first x-ray intensity that is lower than a second x-ray intensity used for a diagnostic scan of the target organ. The x-ray intensity of the localizer spiral CT scan can be a predetermined x-ray intensity (e.g., set based on individual settings of the CT scanner) that is high enough to acquire image information for an initial screening to determine an extent of the target organ, but lower than the x-ray intensity used for a diagnostic scan of the target organ, as a lower image quality is acceptable in the localizer spiral CT scan than is required to make a diagnostic assessment of the target organ”);
defining, using the predicted presence and/or position of the predetermined anatomical landmark, a plane and/or a volume to be imaged during the subsequent medical imaging scan, wherein the plane and/or the volume is defined so as to either avoid irradiating the predetermined anatomical landmark or to capture a volume which includes the landmark (see Vega, Fig. 2, Col 7, Lines 60-67 – Col 8, Lines 1-9, “At step 214, a diagnostic spiral CT scan is automatically started at the predicted beginning location of the target organ. The localizer spiral CT scan continues at the first x-ray intensity until the beginning of the target organ is anticipated in the real-time localizer scan images and proximity to the predicted start location of is detected (e.g., it is determined that the scan is within a predetermined distance of the predicted start location of the target organ). Once proximity to predicted location of the anatomical landmark (e.g., lung apex) indicating the beginning of the target landmark is detected, the x-ray intensity is automatically adjusted to drive the x-ray intensity up to the second x-ray intensity used for a diagnostic scan of the target organ, such that the diagnostic part of the CT scan of the target organ starts at the predicted beginning location of the target organ, such that the diagnostic part of the CT scan of the target organ starts at the predicted beginning location of the target organ,” and “Col 9, Lines 65-67- Col 10, Lines 1-3, “ensuring that full coverage of the target organ has been reached and preventing the patient from being exposed to radiation beyond what is necessary to achieve full coverage of the target organ,” predetermined anatomical landmark; the scan of the target organ starts at the predicted beginning location of the target organ and a spiral CT scan is automatically started at the predicted beginning location of the target organ, a spiral CT scan captures a continuous volume of data in a single pass, therefore a volume is imaged)
and controlling a medical imaging scan in accordance with the plane and/or the volume in order to acquire the diagnostic medical image during the subsequent medical imaging scan (see Vega, Fig. 2, Col 8, Lines, 8-18, “Since there will be a slight time delay between acquiring the localizer scan images, detecting the landmarks and estimating the beginning location of the target organ, and providing this information back to the CT scanner to control the CT scanner to increase the x-ray intensity, anticipating/predicting the beginning location of the target organ allows the CT scanner to be controlled to increase the x-ray intensity and start the diagnostic scan at the beginning location of the target organ,” and Col 9, Lines, 49-58, “At step 218, the CT scan of the target organ is automatically stopped once the predicted end location of the target organ is reached. For example, in response to determination that a proximity to the predicted end location has been reached (e.g., the scan is within a predetermined distance from the end location), the CT scanner can be controlled to stop the diagnostic spiral CT scan immediately after the predicted end position of the target organ has been scanned”)
The combination of Liu and Vega are analogous art because they are both in the same field of endeavor of anatomical landmark detection. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention for the localizer spiral CT scan to be performed with a first x-ray intensity that is lower than a second x-ray intensity used for a diagnostic scan and for one or more anatomical landmark detectors to be trained from annotated training images as taught in the method of Vega in the method of Liu to reduce the total radiation dose as compared with the convention method of CT lung acquisition (see Vega, Col 3, Lines 10-14).
Regarding claim 8, Liu in view of Vega further teaches the computer-implemented method of claim 1,
wherein the predetermined anatomical landmark is an anatomical landmark defined by a predetermined set of guidelines for performing medical image scanning (see Vega, Col, Lines, “one or more landmark detectors can be trained from annotated training images to detect anatomical landmarks in the start confidence range (e.g., vertebrae, anatomical landmarks from nearby organs, etc.) and to estimate a predicted location of the anatomical landmark corresponding to the beginning of the target organ (e.g., lung apex) based on the detected anatomical landmarks in the start confidence range,” one or more landmark detectors can be trained from annotated training images which contain annotated anatomical landmarks that are based on CT guidelines for anatomical landmarks which includes vertebrae and anatomical landmarks from nearby organs).
The rationale of claim 1 has been applied herein.
Regarding claim 9, Liu in view of Vega further teaches the computer-implemented method of claim 1, further comprising:
controlling a user interface to provide an output responsive to the predicted presence and/or position of the anatomical landmark with respect to the computer tomography image (Liu Paragraph [0025], “For example, the medical image or a portion of the medical image can be displayed on the display device, and the landmark location can be highlighted or annotated in the displayed image. In a possible embodiment, a probability map in which each voxel of the medical image is assigned a color corresponding to a detection probability calculated for that voxel by the trained deep neural network can be displayed on the display device”, and Paragraph [0027], “The computer 502 also includes other input/output devices 508 that enable user interaction with the computer 502 (e.g., display, keyboard, mouse, speakers, buttons, etc.). Such input/output devices 508 may be used in conjunction with a set of computer programs as an annotation tool to annotate volumes received from the image acquisition device 520,” highlighting and annotating is considered to be controlling a user interface to provide an output responsive).
The rationale of claim 1 has been applied herein.
As per claim 13, Claim 13 claims a processing system configured to do the same limitations as Claim 1, therefore the rejection and rationale is analogous to that made in Claim 1.
Liu further teaches a processing system (see Liu, Paragraph [0027], “The above-described methods for landmark detection in medical image using a deep neural network may be implemented on a computer using well-known computer processors, memory units, storage devices, computer software, and other components. A high-level block diagram of such a computer is illustrated in FIG. 5. Computer 502 contains a processor 504, which controls the overall operation of the computer 502 by executing computer program instructions which define such operation.”)
As per claim 16, Claim 16 claims a non-transitory computer-readable medium for storing executable instructions, which cause a method to do the same limitations as Claim 1, therefore the rejection and rationale is analogous to that made in Claim 1.
Liu further teaches a non-transitory computer-readable medium for storing executable instructions (see Liu, Paragraph [0027], “The computer program instructions may be stored in a storage device 512 (e.g., magnetic disk) and loaded into memory 510 when execution of the computer program instructions is desired. Thus, the steps of the method of FIG. 1 may be defined by the computer program instructions stored in the memory 510 and/or storage 512 and controlled by the processor 504 executing the computer program instructions,” and Claim 17)
Claim(s) 2 and 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Liu et al, WO 2016182551 in view of in view of Georgescu et al, US 9792531.
Regarding claim 2, Liu in view of Vega further teaches the computer-implemented method of claim 1,
identifying the largest cluster of high likelihood pixels/voxels (see Liu, Paragraph [0024], “either selects a voxel having the highest probability or clusters a number of voxels having highest probabilities to determine the location of the landmark in the medical image.”);
and predicting the position of the predetermined anatomical landmark to lie within the identified largest cluster of high likelihood pixels/voxels (see Liu, Paragraph [0024], “The trained deep neural network can then cluster the predicted landmark locations calculated for each voxel to determine the location of the landmark in the medical image.”).
Liu in view of Vega does not expressively teach
identifying as high likelihood pixels/voxels, any pixels/voxels having a corresponding indicator that indicates a likelihood that the corresponding pixel or voxel of the image represents part of a predetermined anatomical landmark exceeds a predetermined threshold;
However, Georgescu’531 in a similar invention in the same field of endeavor teaches
identifying as high likelihood pixels/voxels, any pixels/voxels having a corresponding indicator that indicates a likelihood that the corresponding pixel or voxel of the image represents part of a predetermined anatomical landmark exceeds a predetermined threshold (see Georgescu’ 531 Col 15, Lines 32-46, “The landmark target may then be identified on the medical image of the patient when the cumulative reward value indicates a proximity of the adjacent state space within a pre-defined reward threshold distance value of the landmark target on the medical image. The target landmark is not present in the medical image when the cumulative reward value is outside a pre-defined failure threshold distance value. An indication may be generated indicating that the target landmark is not present in the medical image”, the reward value is considered to be an indictor; when the cumulative reward value indicates outside a pre-defined failure threshold distance that is considered to be exceeds a predetermined threshold);
The combination of Liu, Vega, and Georgescu are analogous art as they are all in the same field of endeavor of anatomical landmark detection. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to determine whether the cumulative reward value is within or outside a pre-defined failure threshold distance value as taught in the in the method of Georgescu’531 in the method of Liu in view of Vega for conducting image evaluation and identifying one or several anatomical landmarks (see Georgescu’531, Col 2, Lines 32-33).
As per claim 14, Claim 14 claims the same limitation as Claim 2 and is dependent upon a similarly rejected independent claim. Therefore the rejection and rationale is analogous to that made in Claim 2.
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Liu et al, WO 2016182551 in view of in view of Georgescu et al, US 9792531 in further view of Frey et al, US 20010041884.
Regarding claim 3, Liu in view of Vega in view of Georgescu’531 does not expressively teach the computer-implemented method of claim 2,
identifying a centroid of the identified largest cluster of high likelihood pixels/voxels as the position of the predetermined anatomical landmark.
However, Frey in a similar invention in the same field of endeavor teaches
identifying a centroid of the identified largest cluster of high likelihood pixels/voxels as the position of the predetermined anatomical landmark (see Frey, Paragraph [0194], “the centroids are determined by first computing which pixels should be processed and grouping them together into clusters. The intensity-weighted centroid of each cluster is then computed.”, computing intensity-weighted centroid is considered identifying a centroid which is well understood in the art).
The combination of Liu, Vega, Georgescu, and Frey are analogous art as they are all in the same field of endeavor of biomedical imaging. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to compute intensity-weighted centroids in the method of Frey in the method of Liu in view of Vega in view of Georgescu’531 to find the center of each focus spot (see Frey, Paragraph [0111]).
Claim(s) 4-5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Liu et al, WO 2016182551 in view of in view of Georgescu et al, US 9792531 in view of Clark US 20230389854 and in further view of Blondel et al, CN 102184558.
Regarding claim 4, Liu in view of Vega in view of Georgescu’531 further teaches the computer-implemented method of claim 2 further comprising:
clustering on the high likelihood pixels/voxels to identify one or more clusters of high likelihood pixels/voxels (see Liu, Paragraph [0024], “either selects a voxel having the highest probability or clusters a number of voxels having highest probabilities to determine the location of the landmark in the medical image.”, clusters a number of voxels having highest probabilities is considered to be clustering to identify one or more clusters of high likelihood pixels/voxels).
Liu in view of Vega in view of Georgescu’531 does not expressively teach the computer-implemented method of claim 2,
performing a clustering algorithm
However, Clark in a similar invention in the same field of endeavor teaches
performing a clustering algorithm (see Clark, Paragraph [0329], “A cluster-forming algorithm was used to segment the LC within this space, defined as the 4 adjacent voxels (1.96 mm.sup.2) with the highest mean signal.”)
The combination of Liu, Vega, Georgescu, and Clark are analogous art as they are all in the same field of endeavor of biomedical imaging. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to use a cluster-forming algorithm as taught in the method Clark in the method of Liu in view of Vega in view of Georgescu’531 to segment adjacent voxels with the highest mean signal (see Clark, Paragraph [0329]).
Liu in view of Vega in view of Georgescu’531 in further view of Clark does not expressively teach
and identifying the largest of the one or more clusters of high likelihood pixels/voxels
However, Blondel in a similar invention in the same field of endeavor teaches
and identifying the largest of the one or more clusters of high likelihood pixels/voxels (see Blondel Paragraph [0005], “based on the size and shape of the cluster and the cluster pixel probability, confidence values for each centroid distribution and indicates the corresponding likelihood of the actual body part.”).
The combination of Liu, Vega, Georgescu’531, Clark and Blondel are analogous art as they are all in the same field of endeavor of verifying object captured is a target object. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to indicate the likelihood of the corresponding body part based on the size and shape of the cluster pixel probability as taught in the method of Blondel in the method of Liu in view of Vega in view of Georgescu’531 in view of Clark to correctly identify the object captured (see Blondel, Abstract).
Regarding claim 5, Liu in view of Vega in view of Georgescu’531 in view of Clark in further view of Blondel further teaches the computer-implemented method of claim 4,
wherein each cluster of high likelihood pixels/voxels comprises: of pixels that are adjacent to at least one other pixel in the cluster of high likelihood pixels/voxels (see Clark, Paragraph [0329], “A cluster-forming algorithm was used to segment the LC within this space, defined as the 4 adjacent voxels (1.96 mm.sup.2) with the highest mean signal.”).
The rationale of claim 4 has been applied herein.
Claim(s) 6-7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Liu et al, WO 2016182551 in view of in view of Georgescu et al, US 11514571.
Regarding claim 6, Liu in view of Vega does not expressively teach the computer-implemented method of claim 1,
wherein each indicator is a numeric indicator representing a probability that the corresponding pixel represents part of the predetermined anatomical landmark.
However, Georgescu’571 in a similar invention in the same field of endeavor teaches the computer-implemented method of claim 1,
wherein each indicator is a numeric indicator representing a prediction or whether the corresponding pixel represents part of the predetermined anatomical landmark (see Georgescu’571, Col 4, Lines 22-29, “In one embodiment, the probability map may be converted to a binary segmentation mask by comparing the probability score to a threshold (e.g., 0.5) such that the binary segmentation mask has intensity values of 1 where the anatomical objects are located and 0 where the anatomical objects are not located”, the binary segmentation mask is considered to be a numeric indicator).
The combination of Liu, Vega, and Georgescu are analogous art as they are all in the same field of endeavor of anatomical landmark detection. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, for the probability map to be converted to a binary segmentation mask such that the binary segmentation mask has intensity values of 1 where the anatomical objects are located and 0 where the anatomical objects are not located as taught in the method of Georgescu’571 in the method of Liu in view of Vega for conducting image evaluation and identifying one or several anatomical landmarks (see Georgescu’571, Col 2, Lines 32-33).
Regarding claim 7, Liu in view of does not expressively teach the computer-implemented method of claim 1,
wherein each indicator is a binary indicator representing a prediction or whether the corresponding pixel represents part of the predetermined anatomical landmark.
However, Georgescu’571 in a similar invention in the same field of endeavor teaches
wherein each indicator is a binary indicator representing a prediction or whether the corresponding pixel represents part of the predetermined anatomical landmark (see Georgescu’571, Col 4, Lines 22-29, “In one embodiment, the probability map may be converted to a binary segmentation mask by comparing the probability score to a threshold (e.g., 0.5) such that the binary segmentation mask has intensity values of 1 where the anatomical objects are located and 0 where the anatomical objects are not located”, the binary segmentation mask is considered to be a binary indicator).
The combination of Liu, Vega, and Georgescu’571 are analogous art as they are all in the same field of endeavor of anatomical landmark detection. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, for the probability map to be converted to a binary segmentation mask such that the binary segmentation mask has intensity values of 1 where the anatomical objects are located and 0 where the anatomical objects are not located as taught in the method of Georgescu’571 in the method of Liu in view of Vega to determine where anatomical objects are located and not located (see Georgescu’571, Col 4, Lines 26-29).
Conclusion
THIS ACTION IS MADE FINAL. 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 DOMINIQUE JAMES whose telephone number is (703)756-1655. The examiner can normally be reached 9:00 am - 6:00 pm EST.
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, Emily Terrell can be reached on (571)270-3717. 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.
/DOMINIQUE JAMES/Examiner, Art Unit 2666 /MING Y HON/Primary Examiner, Art Unit 2666
Prosecution Insights