# US 11,896,434 B2 · Systems and methods for frame indexing and image review > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,896,434 B2 - Document ID: US11896434B2 - Status: Granted - Kind: B2 - Application number: 17/299,851 - Filed: 2019-12-11 - Published: 2022-03-10 - Granted: 2024-02-13 - Earliest claimed: 2018-12-17 - Assignees: Koninklijke Philips N.V. - Applicants: Koninklijke Philips N.V. - Inventors: Earl M. Canfield; Thanasis Loupas; Robert Gustav Trahms; David Hope Simpson - Web page: https://patentgrep.com/patent/US11896434B2 ## CPC - A61B 8/463: {characterised by displaying multiple images or images and diagnostic data on one display} - A61B 8/5223: {for extracting a diagnostic or physiological parameter from medical diagnostic data (for algorithms to analyse biomedical images G06T7/0012)} - A61B 8/085: {for locating body or organic structures, e.g. tumours, calculi, blood vessels, nodules} - A61B 8/0866: {involving foetal diagnosis; pre-natal or peri-natal diagnosis of the baby} - A61B 8/469: {for selection of a region of interest} - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/08: Learning methods - G06N 3/088: Non-supervised learning, e.g. competitive learning - G06N 3/09: Supervised learning - A61B 8/0883: {for diagnosis of the heart} - G06N 3/044: Recurrent networks, e.g. Hopfield networks - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract The present disclosure describes imaging systems configured to generate index information to indicate which image frames in a plurality of image frames include one or more target anatomical features, such as a head or femur of a fetus. The confidence levels of the presence of the target anatomical features are also determined. The system may be configured to determine if the target anatomical feature is present in an image frame by implementing at least one neural network. Merit levels based on the quality of the image frames may also be determined. Measurements of the one or more items of interest may be acquired. Visual representations (500) of the index information (502), confidence levels, merit levels, and/or measurements may be provided via a user interface. A user interface may receive user inputs based on the visual representations to navigate to specific image frames (508) of the plurality of image frames. ## Claims ### Claim 1 An ultrasound imaging system comprising: an ultrasound transducer configured to acquire echo signals responsive to ultrasound pulses transmitted toward a region of interest; one or more processors in communication with the ultrasound transducer and configured to: receive a plurality of image frames generated from the ultrasound echoes; determine, for each image frame of the plurality of image frames, whether target anatomical feature is present in the image frames; and generate, for each of the image frames of the plurality of image frames, index information based on a confidence level indicating the target anatomical feature is present in the given image frame; and a user interface in communication with the one or more processors and configured to display a visual representation of the index information, wherein the visual representation comprises a marker associated with the target anatomical feature, and wherein the visual representation further includes a first axis representing an order of the plurality of image frames and wherein the maker is located on the first axis at a location representing the given image frame where the target anatomical feature is present. ### Claim 2 (depends on 1) The ultrasound imaging system of claim 1, wherein the visual representation further includes a legend indicating the marker is associated with the target anatomical feature. ### Claim 3 (depends on 1) The ultrasound imaging system of claim 1, wherein the visual representation further includes a second axis representing a magnitude of the confidence level. ### Claim 4 (depends on 1) The ultrasound imaging system of claim 1, wherein the marker includes a visual characteristic that varies based on the confidence level. ### Claim 5 (depends on 4) The ultrasound imaging system of claim 4, wherein the visual characteristic is at least one of color or height. ### Claim 6 (depends on 1) The ultrasound system of claim 1, wherein the user interface includes a selector configured to be controlled by a user input. ### Claim 7 (depends on 6) The ultrasound system of claim 6, wherein the user input determines a location of the selector on the visual representation and the location determines an image frame of the plurality of image frames to be displayed, and optionally wherein the location is on the marker. ### Claim 8 (depends on 1) The ultrasound imaging system of claim 1, wherein the one or more processors are configured to determine whether the target anatomical feature is present in the image frames by inputting the frames into a neural network trained with imaging data comprising the target anatomical feature. ### Claim 9 (depends on 1) The ultrasound imaging system of claim 1, wherein the visual representation is configured to display the index information based on the confidence levels above a threshold value. ### Claim 10 (depends on 1) he ultrasound imaging system of claim 1, wherein the one or more processors are configured to determine that a standard view has been acquired and the user interface is configured to display a list of standard views and a graphical indicator on the list indicating that the standard view has been acquired. ### Claim 11 (depends on 1) The ultrasound imaging system of claim 1, wherein the one or more processors are further configured to determine merit levels based on the index information of the plurality of image frames, the merit levels associated with a quality of the image frames. ### Claim 12 A method comprising: acquiring echo signals responsive to ultrasound pulses transmitted into a region of interest by a transducer operatively coupled to an ultrasound system; generating a plurality of image frames from the ultrasound echoes; processing each of a plurality of image frames to determine a confidence level, wherein the confidence level is a probability that a target anatomical feature is present in the image frame; generating, for each processed frame, index information based on the confidence level for each frame; generating a visual representation of the index information; and causing a user interface to display the visual representation corresponding to the index information, wherein the visual representation comprises a first axis representation an order of the plurality of image frames and a plurality of markers located on the first axis at locations representing the image frames where the target anatomical feature is present. ### Claim 13 (depends on 12) The method of claim 12, further comprising generating merit levels of the image frames where the target anatomical feature is present, the merit levels associated with an image quality of the respective image frames, and optionally wherein the method further comprises displaying an image of the frames having a highest merit level. ### Claim 14 (depends on 12) The method of claim 12, further comprising making a measurement of the target anatomical feature from an image frame where the target anatomical feature is present. ### Claim 15 (depends on 12) The method of claim 12, further comprising causing the user interface to display a selector with the visual representation, wherein the selector may determine an image frame of the plurality of image frames to be displayed by the user interface based on a user input.