# US 12,217,445 B2 · Probability map-based ultrasound scanning > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,217,445 B2 - Document ID: US12217445B2 - Status: Granted - Kind: B2 - Application number: 15/977,091 - Filed: 2018-05-11 - Published: 2018-11-15 - Granted: 2025-02-04 - Earliest claimed: 2017-05-11 - Assignees: Verathon Inc. - Applicants: Verathon Inc. - Inventors: Joon Hwan Choi - Web page: https://patentgrep.com/patent/US12217445B2 ## CPC - G06T 7/62: of area, perimeter, diameter or volume - A61B 5/7267: {involving training the classification device} - 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 8/0883: {for diagnosis of the heart} - A61B 8/0891: {for diagnosis of blood vessels} - A61B 8/14: Echotomography - A61B 8/42: {Details of probe positioning or probe attachment to the patient} - 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 8/5292: {using additional data, e.g. patient information, image labeling, acquisition parameters} - A61B 8/565: {involving data transmission via a network} - G06N 3/045: Combinations of networks - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/08: Learning methods - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06T 7/0014: {using an image reference approach} - G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS - G16H 30/40: for processing medical images, e.g. editing - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - A61B 5/4325: {of the uterine cavities, e.g. uterus, fallopian tubes, ovaries} - A61B 5/4381: {Prostate evaluation or disorder diagnosis} - G06T 2207/10132: Ultrasound image - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/30084: Kidney; Renal - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract A system may include a probe configured to transmit ultrasound signals to a target of interest, and receive echo information associated with the transmitted ultrasound signals. The system may also include at least one processing device configured to process the received echo information using a machine learning algorithm to generate probability information associated with the target of interest. The at least one processing device may further classify the probability information and output image information corresponding to the target of interest based on the classified probability information. ## Claims ### Claim 1 A system, comprising: a hand-held probe configured to be positioned on an external surface of a patient's body, and configured to: transmit ultrasound signals to a target of interest, wherein the target of interest comprises the patient's bladder or prostate, and receive echo information associated with the transmitted ultrasound signals; and at least one processing device configured to: process the received echo information using a machine learning algorithm to generate probability information associated with the target of interest, wherein the probability information comprises a value indicating whether a portion of an image associated with the processed echo information is within the target of interest, process the probability information generated by the machine learning algorithm to identify the target of interest, wherein when processing the probability information, the at least one processing device is configured to binarize the probability information to identify portions of the image within the target of interest, calculate, based on the processed binarized probability information, a second value corresponding to a volume or size-related measurement associated with the target of interest, output image information corresponding to the target of interest based on the processed binarized probability information, and output the second value. ### Claim 2 (depends on 1) The system of claim 1, wherein when calculating the second value, the at least one processing device is further configured to: calculate, based on the binarized probability information, the second value, wherein the size-related measurement corresponds to at least one of a length, height, width, depth, diameter or area associated with the target of interest. ### Claim 3 (depends on 1) The system of claim 1, wherein when processing the received echo information, the at least one processing devices is configured to use a convolutional neural network algorithm. ### Claim 4 (depends on 1) The system of claim 1, further comprising: a display configured to receive the image information, display the image information and display the second value, wherein the second value corresponds to a volume of the bladder or the prostate. ### Claim 5 (depends on 4) The system of claim 4, wherein the display is further configured to: simultaneously display B-mode image data corresponding to the received echo information and the image information corresponding to the target of interest. ### Claim 6 (depends on 1) The system of claim 1, wherein the at least one processing device is further configured to: generate aiming instructions for directing the probe to the target of interest. ### Claim 7 (depends on 1) The system of claim 1, wherein the target of interest comprises the bladder. ### Claim 8 (depends on 1) The system of claim 1, wherein the at least one processing device is further configured to: receive information comprising at least one of gender information for a subject, information indicating that the subject is a child, age information, age range information, or body mass index information, and process the received echo information based on the received information. ### Claim 9 (depends on 1) The system of claim 1, wherein the at least one processing device is further configured to: automatically determine at least one of demographic information of a subject, clinical information of the subject, or device information associated with the probe, and process the received echo information based on the automatically determined information. ### Claim 10 (depends on 1) The system of claim 1, wherein when processing the received echo information, the at least one processing device is configured to: process the received echo information to generate output image data, process pixels associated with the output image data, determine values for each processed pixel, identify a peak value, and fill in an area around a point associated with the peak value to identify a portion of the target of interest. ### Claim 11 (depends on 1) The system of claim 1, wherein when processing the received echo information, the at least one processing device is configured to: identify higher order harmonic information with respect to a frequency associated with the transmitted ultrasound signals, and generate the probability information based on the identified higher order harmonic information. ### Claim 12 (depends on 1) The system of claim 1, wherein the probe is configured to transmit the received echo information to the at least one processing device via a wireless interface. ### Claim 13 (depends on 1) The system of claim 1, wherein the target of interest comprises the prostate. ### Claim 14 (depends on 1) The system of claim 1, wherein the at least one processing device is further configured to: receive information comprising at least one of medical history information of a subject or information obtained via a physical examination of the subject, and process the received echo information based on the received information. ### Claim 15 (depends on 1) The system of claim 1, wherein the at least one processing device is further configured to: output visual information associated with boundaries of the target of interest based on the processed binarized probability information. ### Claim 16 A method, comprising: transmitting, via a hand-held ultrasound probe configured to be positioned on an external surface of a patient's body, ultrasound signals to a target of interest, wherein the target of interest comprises a bladder, a prostate gland or a kidney; receiving, via the hand-held ultrasound probe, echo information associated with the transmitted ultrasound signals; processing the received echo information using a machine learning algorithm to generate probability information associated with the target of interest, wherein the probability information comprises a value indicating whether a portion of an image associated with the processed echo information is within the target of interest; processing the probability information generated by the machine learning algorithm to identify the target of interest, wherein the processing the probability information comprises binarizing the probability information to identify portions of the image within the target of interest; calculating, based on the processed binarized probability information, a second value corresponding to a volume or size-related measurement associated with the target of interest; outputting image information corresponding to the target of interest based on the processed binarized probability information; and outputting the second value. ### Claim 17 (depends on 16) The method of claim 16, wherein calculating the second value comprises: calculating, based on the binarized probability information, the second value, wherein the size-related measurement corresponds to at least one of a length, height, width, depth, diameter or area associated with the target of interest; and outputting the second value to a display. ### Claim 18 (depends on 16) The method of claim 16, further comprising: simultaneously displaying B-mode image data corresponding to the echo information and the output image information corresponding to the target of interest. ### Claim 19 (depends on 16) The method of claim 16, further comprising: receiving, prior to transmitting the ultrasound signals to the target of interest, information comprising at least one of gender information for a subject, age information for the subject, age range information for the subject, body mass index information for the subject, body size of the subject, or weight of the subject; and processing the received echo information based on the received information. ### Claim 20 A system, comprising: a memory; and at least one processing device configured to: receive, from a hand-held probe configured to be positioned on an external surface of a patient's body, image information corresponding to a target of interest, wherein the target of interest comprises a bladder, a prostate gland, a uterus, or a kidney, process the received image information using a machine learning algorithm to generate probability information associated with the target of interest, process the probability information generated by the machine learning algorithm to identify the target of interest, wherein when processing the probability information, the at least one processing device is configured to binarize the probability information to identify portions of the processed image information within the target of interest, calculate a value corresponding to a volume or size-related measurement associated with the target of interest, output second image information corresponding to the target of interest based on the processed binarized probability information, and output the value. ### Claim 21 (depends on 20) The system of claim 20, further comprising: a display, wherein when calculating the value, the at least one processing device is further configured to: calculate, based on the processed binarized probability information, the value, wherein the size-related measurement corresponds to at least one of a length, height, width, depth, diameter or area associated with the target of interest; and output the value to the display. ### Claim 22 (depends on 20) The system of claim 20, wherein the machine learning algorithm comprises a convolutional neural network algorithm and the memory stores instructions to execute the convolutional neural network algorithm. ### Claim 23 (depends on 20) The system of claim 20, further comprising: the hand-held probe, wherein the hand-held probe is configured to: transmit ultrasound signals to the target of interest, receive echo information associated with the transmitted ultrasound signals, and forward the echo information to the at least one processing device, wherein the at least one processing device is further configured to: generate, using the machine learning algorithm, the image information corresponding to the target of interest based on the echo information.