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-11894141-B2
Publication Date
2024-02-06
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
The invention provides a network-based, cloud-based decision support system for medical imaging, in which a processor receives and stores a plurality of medical images in a database and associates each medical image with a corresponding patient. The system accesses one or more medical images for a particular patient, automatically analyzes the one or more medical images using a machine learning algorithm, and generates a radiologist report for the patient. The system is configured to operate on a composite image of the particular patient.
The composite image comprises a CT scan overlaid with a nuclear medicine image obtained at a substantially same time as the CT scan and following administration of an imaging agent comprising a Prostate Specific Membrane Antigen binding agent comprising a radionuclide. The automatic analysis 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. Using the nuclear medicine image with the identified 3D boundary or boundaries, the system computes a value of each of one or more risk indices indicative of cancer state or progression in the patient.
The disclosed approach is also directed to repeatedly receiving and storing, over time, a series of medical images for one or more patients in order to obtain image series taken over time. The system automatically analyzes the series using a machine learning algorithm to determine values of one or more risk indices for each medical image of the series, thereby tracking determined values over a course of prostate cancer progression and treatment. The determined values are stored for further processing and/or caused to be displayed as a graphical representation.
Claims Coverage
The independent claims cover a network-based, cloud-based decision support system and corresponding methods for analyzing PSMA-binding composite medical images and tracking prostate cancer risk indices over time. The inventive feature set includes automatic machine-learning analysis, geographic identification of 3D tissue boundaries, computation of risk index values indicative of cancer state or progression, radiologist report generation, and storage or graphical display of longitudinal risk index values.
Cloud-based network decision support system with machine learning analysis and radiologist report generation
A network-based decision support system comprising a processor and a memory, wherein instructions cause the processor to receive and store medical images associated with patients; access one or more medical images for a particular patient; automatically analyze the one or more medical images using a machine learning algorithm; and generate a radiologist report for the particular patient.
PSMA composite image analysis with geographically identified 3D boundaries
The one or more medical images comprise a composite image with a CT scan overlaid with a nuclear medicine image obtained at a substantially same time as the CT scan and following administration of an imaging agent comprising a PSMA binding agent comprising a radionuclide, and instructions cause automatic analysis of the composite image by using the composite image to geographically identify a 3D boundary for each of one or more regions of imaged tissue within the nuclear medicine image.
Risk index computation indicative of cancer state or progression using 3D boundaries
Instructions cause the processor to compute, using the nuclear medicine image with the identified 3D boundary or boundaries of the one or more regions, a value of each of one or more risk indices, each risk index value indicative of cancer state or progression in the patient.
Time-series tracking method for prostate cancer progression and treatment efficacy
A method for tracking prostate cancer progression and treatment efficacy over time, comprising repeatedly receiving and storing, over time, a plurality of medical images for each of 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 of the series, thereby tracking determined values over a course of prostate cancer progression and treatment; and storing the determined values and/or causing display of a graphical representation of the determined values.
Tracking prostate cancer efficacy with composite CT/nuclear medicine and 3D boundary-based risk index computation
The series of medical images comprises a CT scan overlaid with a nuclear medicine image acquired at a substantially same time and following administration of an imaging agent comprising a PSMA binding agent comprising a radionuclide, wherein step (b) comprises using 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 computing the value of each risk index using the nuclear medicine image with the identified 3D boundary or boundaries.
Cloud-based tracking system for prostate cancer progression and treatment efficacy
A system for tracking prostate cancer progression and treatment efficacy over time, comprising a processor and a memory, wherein instructions cause the processor to repeatedly receive and store, over time, a plurality of medical images for one or more patients to obtain a series of medical images 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 of the series, thereby tracking determined values over a course of prostate cancer progression and treatment; and store the determined values and/or cause display of a graphical representation of the determined values.
Across the independent claims, the inventive core combines cloud-based or networked image data handling with machine-learning analysis of PSMA CT/nuclear medicine composite images, geographic identification of 3D tissue boundaries, and computation of risk index values indicative of cancer state or progression. Additional independent claim coverage extends these capabilities to longitudinal time-series analysis for tracking prostate cancer progression and treatment efficacy, including storing and/or displaying graphical representations of risk index values.
Stated Advantages
Automatically generates a radiologist report for a patient according to one or more medical images.
Computes risk index values indicative of cancer state or progression in the patient.
Tracks determined risk index values over a course of prostate cancer progression and treatment.
Stores determined risk index values for further processing and/or causes display of a graphical representation of the determined values.
Documented Applications
Decision support for cancer treatment decision-making using machine-learning risk analysis based on PSMA-binding composite CT/nuclear medicine images.
Longitudinal tracking of prostate cancer progression and treatment efficacy over time using series of medical images and risk index values.
Cloud-based decision support imaging workflows using PSMA radiotracers, including whole-body bone scan index (BSI) from 99mTc-MDP gamma scans, and PET-CT and SPECT-CT composite fusion to compute risk indices correlated to prognosis and tracked over time.
Generating radiologist reports based on automatically analyzed composite CT and nuclear medicine images after administration of imaging agents comprising PSMA binding agents comprising radionuclides.
Interested in licensing this patent?