Network for medical image analysis, decision support system, and related graphical user interface (GUI) applications
Inventors
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11424035-B2
Publication Date
2022-08-23
Expiration Date
Abstract
Described herein is a platform and supported graphical user interface (GUI) decision-making tools for use by medical practitioners and/or their patients, e.g., to aide in the process of making decisions about a course of cancer treatment and/or to track treatment and/or the progress of a disease.
Core Innovation
A network-based decision support system receives and stores a plurality of medical images in a database, accesses one or more medical images upon user request for transmission to a user computing device for display, automatically analyzes the medical images using a machine learning algorithm, and generates a radiologist report for the particular patient according to the medical images.
The medical images include a composite image comprising a CT scan overlaid with a nuclear medicine image acquired at a substantially same time and following administration of an imaging agent including a Prostate Specific Membrane Antigen binding agent comprising a radionuclide. The system uses the composite image to geographically identify a 3D boundary for each of one or more regions of imaged tissue within the nuclear medicine image and computes a risk map comprising a graphical denotation marking a region of risk of cancer or risk of recurrence of cancer.
In related embodiments, the system repeatedly receives and stores medical images over time to obtain a series of medical images taken over time. The processor automatically analyzes the series using a machine learning algorithm to determine values of one or more risk indices for each medical image, thereby tracking determined values over a course of prostate cancer progression and treatment efficacy, and generates and stores a risk map for further processing or display.
Claims Coverage
The document provides four independent claims. Across these claims, the coverage concentrates on composite CT and nuclear medicine PSMA-agent imaging, machine-learning analysis, 3D boundary identification for tissue regions, and generating a graphical risk map and risk-index values that track cancer risk or recurrence risk over time.
Network-based decision support system with composite CT and nuclear medicine PSMA imaging risk map
A network-based decision support system comprising a processor and a memory with instructions to receive and store a plurality of medical images in a database, access one or more medical images upon user request for display, automatically analyze the images using a machine learning algorithm, and generate a radiologist report, wherein the medical images comprise a composite image with a CT scan overlaid with a nuclear medicine image acquired at a substantially same time and following administration of a PSMA binding agent comprising a radionuclide, and wherein the composite image is used to geographically identify a 3D boundary for each of one or more regions of imaged tissue and compute a risk map comprising a graphical denotation marking a region of risk of cancer or risk of recurrence of cancer.
Server-executed method using machine learning on composite CT and nuclear medicine to generate risk map
A method comprising receiving and storing a plurality of medical images in a database, accessing one or more medical images associated with a particular patient upon user request for display, automatically analyzing the one or more medical images using a machine learning algorithm, and generating a radiologist report, wherein the medical images comprise a composite image with a CT scan overlaid with a nuclear medicine image acquired at a substantially same time and following administration of a PSMA binding agent comprising a radionuclide, and wherein the composite image is used to geographically identify a 3D boundary for each of one or more regions of imaged tissue and compute, using the nuclear medicine image with the identified 3D boundary or boundaries, a risk map comprising a graphical denotation marking regions of risk of cancer or risk of recurrence of cancer.
System for tracking prostate cancer progression using time-series composite PSMA imaging and 3D boundaries
A system for tracking prostate cancer progression and treatment efficacy over time for one or more patients comprising a processor and a memory having instructions to repeatedly receive and store, over time, a plurality of medical images for each patient to obtain a series taken over time, automatically analyze the series using a machine learning algorithm to determine values of one or more risk indices for each medical image and thereby track determined values over a course of prostate cancer progression and treatment efficacy, and generate a risk map comprising a graphical denotation marking a region of risk of cancer or risk of recurrence of cancer, wherein the series comprises composite images comprising a CT scan overlaid with a corresponding nuclear medicine image acquired at a substantially same time and following administration of a PSMA binding agent comprising a radionuclide, and wherein the composite image is used to geographically identify a 3D boundary for each of one or more regions of imaged tissue and compute the value of each risk index and the risk map.
Tracking risk indices over time using composite CT and nuclear medicine images
A method for tracking prostate cancer progression and treatment efficacy over time comprising repeatedly receiving and storing in a database over time a plurality of medical images for one or more patients to obtain a series of medical images taken over time; automatically analyzing the series using a machine learning algorithm to determine values of one or more risk indices for each medical image to track determined values over the course of prostate cancer progression and treatment and to generate a risk map marking a region of risk of cancer or risk of recurrence of cancer; and storing the determined values and the risk map for each patient for further processing or for causing display, wherein the series of medical images comprises composite images with a CT scan overlaid with a corresponding nuclear medicine image acquired substantially same time after administration of a PSMA binding agent comprising a radionuclide and wherein the nuclear medicine image with the identified 3D boundary(ies) is used to compute the value of each risk index and the risk map.
Across the independent claims, the inventive core is automated generation of a radiologist report and cancer-risk outputs from composite CT overlaid with concurrent nuclear medicine imaging obtained after administration of a PSMA binding agent comprising a radionuclide. The approach geographically identifies 3D boundaries for tissue regions within the nuclear medicine image and uses those boundaries to compute a graphical risk map marking regions of cancer risk or recurrence risk, with progression-focused embodiments additionally computing and storing risk-index values over a series of images taken over time.
Stated Advantages
Provides a risk map comprising a graphical denotation marking a region of risk of cancer or risk of recurrence of cancer.
Generates a radiologist report according to the one or more medical images.
Tracks determined values of one or more risk indices over a course of prostate cancer progression and treatment for the patient.
Stores determined values of one or more risk indices and the risk map for further processing or display of a graphical representation.
Documented Applications
Risk mapping from composite CT/nuclear medicine images for regions of risk of cancer or risk of recurrence of cancer.
Tracking prostate cancer progression and treatment efficacy over time by repeatedly analyzing composite images to determine values of one or more risk indices and a risk map.
Interested in licensing this patent?