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-12431246-B2
Publication Date
2025-09-30
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 generates and causes display of an interactive graphical user interface (GUI) element comprising a radiologist report. The system receives and stores a plurality of medical images in a database, accesses one or more medical images including a computed tomography (CT) scan overlaid with a positron emission tomography (PET) scan for a first patient, and automatically analyzes the medical images to support cancer state or progression assessment.
The system automatically analyzes the CT and PET by automatically segmenting the CT scan using a convolutional neural network (CNN) to identify 3D boundaries of one or more regions of imaged tissue. The identified 3D boundaries are transferred to the PET scan, one or more hotspots are identified within the PET scan, and one or more risk indices are computed using the PET scan and the identified 3D boundaries, where each risk index value is indicative of a cancer state or progression in the first patient.
The system generates and causes display of the GUI element comprising the radiologist report for the first patient according to the accessed medical images and the computed values of the one or more risk indices. The computed risk indices include a first risk index based on an average intensity of detected hotspots within one or more of the 3D boundaries or a first risk index based on a maximal intensity of detected hotspots within one or more of the 3D boundaries.
In some embodiments, the PET scan is obtained following administration of an imaging agent comprising [18F] DCFPyL or a radionuclide where the radionuclide is a radioisotope of gallium (Ga).
Claims Coverage
Independent claims identified across the input cover a network-based decision support system and related methods. The shared inventive features are CT-overlaid-with-PET access, CNN-based CT segmentation to identify 3D boundaries, transfer of the boundaries to PET, hotspot identification, computation of risk indices indicative of cancer state or progression, and generation/display of an interactive GUI element comprising a radiologist report.
Network-based radiologist-report GUI generation from CT-overlaid-with-PET
Receiving and storing medical images, accessing CT scan overlaid with PET scan for a first patient, automatically analyzing the CT and PET to compute one or more risk indices indicative of a cancer state or progression, and generating and causing display of an interactive GUI element comprising the radiologist report based on the medical images and the risk index values.
Cnn segmentation of CT to define 3D boundaries and transferring boundaries to PET
Automatically segmenting the CT scan using a convolutional neural network (CNN) to identify 3D boundaries of one or more regions of imaged tissue, transferring the identified 3D boundaries to the PET scan, identifying one or more hotspots within the PET scan, and computing risk index values using the PET scan and the identified 3D boundaries.
Risk index computation based on average intensity of hotspots
Computing a first risk index based on an average intensity of detected hotspots within one or more of the 3D boundaries, where the risk index value is indicative of a cancer state or progression in the first patient.
Risk index computation based on maximal intensity of hotspots
Computing a first risk index based on a maximal intensity of detected hotspots within one or more of the 3D boundaries, where the risk index value is indicative of a cancer state or progression in the first patient.
PET scan obtained following administration of imaging agent comprising [18F] DCFPyL
Accessing a PET scan obtained following administration to the first patient of an imaging agent comprising [18F] DCFPyL and using that PET scan in the automatically analyzing workflow that computes risk indices and generates the radiologist-report GUI.
PET obtained following administration of a radionuclide comprising gallium (Ga)
Accessing CT overlaid with PET for the first patient where the PET scan is obtained following administration of an imaging agent comprising a radionuclide, where the radionuclide is a radioisotope of gallium (Ga), and performing the CNN segmentation, hotspot identification, risk index computation, and radiologist-report GUI generation.
The independent claims collectively cover a network-based decision support system and methods that integrate CT-overlaid-with-PET medical images with CNN-based CT 3D boundary segmentation, transfer of 3D boundaries to PET for hotspot identification, computation of risk indices indicative of cancer state or progression, and generation and display of an interactive GUI element comprising a radiologist report, with PET acquisition in some embodiments following administration of [18F] DCFPyL or a gallium (Ga) radioisotope.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?