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-10340046-B2
Publication Date
2019-07-02
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 decision support system that receives and stores a plurality of medical images in a database, accesses medical images or related data upon user request for display on a user computing device, and automatically analyzes the medical images. The system generates a radiologist report for a patient and applies a machine learning algorithm to update a process for automatically analyzing medical images using accumulated image data in the database. For PET-CT, the system overlays a PET scan with a CT scan to create a composite image (PET-CT) of the first patient.
The document further describes tracking prostate cancer progression and treatment efficacy over time by repeatedly receiving and storing series of medical images taken over time for one or more patients. The series include composite SPECT-CT images and composite PET-CT images, and the system automatically analyzes the image series to determine values of one or more risk indices for each medical image of the series, thereby tracking the determined values over a course of prostate cancer progression and treatment.
In the described automated analysis, the system geographically identifies 3D boundaries of a prostate region within the SPECT scan of the composite SPECT-CT image and computes a value of a first risk index using the SPECT scan with the identified 3D boundary. For composite PET-CT images, the system geographically identifies 3D boundaries of one or more metastatic regions within the PET scan, including regions corresponding to patient tissue locations outside of the prostate, and computes a value of a second risk index using the PET scan with the identified 3D boundaries of the one or more metastatic regions. The determined risk-index values are stored for further processing or caused to be displayed as a graphical representation.
Claims Coverage
Independent claims in the provided material include one network-based decision support system claim and multiple processor-implemented method/system claims for tracking prostate cancer progression and treatment efficacy over time. The independent claims collectively specify six main inventive features spanning network-based storage/display and automated radiologist report generation with machine learning update, PET-CT composite overlay, longitudinal composite imaging acquisition and risk-index computation, and geographic 3D boundary identification for prostate and metastatic regions to compute risk indices.
Network-based image decision support with radiologist report generation and machine learning update
A network-based decision support system comprising a processor and a memory having instructions, where the instructions receive and store a plurality of medical images in a database, access medical images or related data upon user request for transmission for display, automatically analyze one or more medical images, generate a radiologist report, and apply a machine learning algorithm to update a process for automatically analyzing using accumulated image data in the database.
PET-CT composite overlay
The plurality of medical images comprise a positron emission tomography (PET) scan and a CT scan of a first patient, and the instructions cause the processor to overlay the PET scan with the CT scan to create a composite image (PET-CT).
Tracking prostate cancer progression over time using longitudinal composite SPECT-CT and PET-CT risk indices
A method for tracking prostate cancer progression and treatment efficacy over time that repeatedly receives and stores a plurality of medical images over time to obtain series of medical images, automatically analyzes the series to determine values of one or more risk indices for each medical image of the series, and thereby tracks determined values of the one or more risk indices over a course of prostate cancer progression and treatment.
Geographic 3D boundary identification of a prostate region from composite SPECT-CT to compute a first risk index
Automatically analyzing each composite SPECT-CT image by using the composite SPECT-CT image to geographically identify a 3D boundary of a prostate region within the SPECT scan of the composite SPECT-CT image, and computing a value of a first risk index using the SPECT scan with the identified 3D boundary of the prostate region.
Geographic 3D boundary identification of metastatic regions from composite PET-CT to compute a second risk index
Automatically analyzing each composite PET-CT image by using the composite PET-CT image to geographically identify a 3D boundary of one or more metastatic regions within the PET scan, where the metastatic regions include regions corresponding to patient tissue locations outside of the prostate, and computing a value of a second risk index using the PET scan with the identified 3D boundaries of the one or more metastatic regions.
Storing and displaying graphical representations of determined risk-index values
For each patient, storing the determined values of the one or more risk indices for the patient for further processing or causing display of a graphical representation of the determined values of the one or more risk indices for the patient.
Across the independent claims, the document centers on a network-based decision support system and processor-implemented methods that store and serve medical images, automatically analyze them to generate radiologist reports, use machine learning to update automated analysis, and overlay PET with CT to form composite PET-CT images. For longitudinal prostate cancer tracking, the independent claims compute one or more risk index values by geographically identifying 3D boundaries of a prostate region from composite SPECT-CT and metastatic regions outside the prostate from composite PET-CT, then storing and optionally displaying graphical representations of the determined risk-index values.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Tracking prostate cancer progression and treatment efficacy over time using a series of medical images and automatically determined values of one or more risk indices.
Interested in licensing this patent?