Systems and methods for rapid neural network-based image segmentation and radiopharmaceutical uptake determination
Inventors
Sjöstrand, Karl Vilhelm • Richter, Jens Filip Andreas • Johnsson, Kerstin Elsa Maria • Gjertsson, Erik Konrad
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12602772-B2
Publication Date
2026-04-14
Expiration Date
Abstract
Presented herein are systems and methods that provide for automated analysis of three-dimensional (3D) medical images of a subject in order to automatically identify specific 3D volumes within the 3D images that correspond to specific organs and/or tissue. In certain embodiments, the accurate identification of one or more such volumes can be used to determine quantitative metrics that measure uptake of radiopharmaceuticals in particular organs and/or tissue regions. These uptake metrics can be used to assess disease state in a subject, determine a prognosis for a subject, and/or determine efficacy of a treatment modality.
Core Innovation
The invention provides a method and system for detecting a prostate cancer status and/or quantifying a prostate cancer risk of a subject based on automated analysis of a 3D anatomical image and a 3D functional image. The 3D anatomical image is used to define tissue within a pelvic region and to determine an initial volume of interest that excludes tissue outside the pelvic region.
The method identifies a prostate volume within the initial volume of interest and determines a value of an uptake metric corresponding to a quantity of a radiopharmaceutical in the prostate based at least in part on intensity values of voxels of the 3D functional image that correspond to the prostate volume. The method causes display of an interactive graphical user interface for guiding a user through a quality control and reporting workflow, including graphical rendering of the 3D anatomical image and/or the 3D functional image, text and/or graphics representing the value of the uptake metric, and a quality control graphical widget.
Responsive to user disapproval of automated determination of the uptake metric, the GUI causes display of a voxel selection graphical element for user selection of one or more voxels for use in determining an updated value of the uptake metric. The method determines whether the uptake metric is above a first threshold value and/or below a second threshold value, where the threshold values are levels on a severity scale, and assigns a prostate cancer status based on whether the uptake metric falls within a corresponding range of possible values for a category of clinical significance.
Claims Coverage
Independent claim coverage comprises two independent claims, a method and a system, with four merged inventive features centered on automated image-based uptake-metric determination, GUI-driven quality control, and severity-scale thresholding to assign prostate cancer status categories.
Automated prostate volume localization in a pelvic-region VOI
Determining an initial volume of interest within the 3D anatomical image corresponding to tissue within the pelvic region and excluding tissue outside the pelvic region, and identifying a prostate volume within the initial volume of interest.
Uptake metric based on functional-image voxel intensity within prostate volume
Determining a value of an uptake metric corresponding to a quantity of a radiopharmaceutical in the prostate based at least in part on intensity values of voxels of the 3D functional image that correspond to the prostate volume.
Interactive GUI quality control and voxel-based recalculation
Causing display of an interactive graphical user interface for a quality control and reporting workflow, receiving user disapproval of automated determination, displaying a voxel selection graphical element, receiving user-selected voxels, and updating the uptake metric using the user selected voxels.
Severity scale thresholding to assign prostate cancer status categories
Determining the uptake metric to be above a first threshold value and/or below a second threshold value, where the threshold values are levels on a severity scale, and assigning a prostate cancer status as one of a plurality of categories of clinical significance associated with corresponding ranges of possible values of the uptake metric.
Across the independent claims, the invention centers on identifying a prostate volume from 3D anatomical and functional images, determining an uptake metric from voxel intensities, using an interactive GUI for quality control and voxel selection, and assigning prostate cancer status using severity-scale threshold ranges.
Stated Advantages
Reproducibility.
Reduced inter-reader variability and reduced intra-reader variability.
Faster than slice-by-slice manual ROI selection.
Enables automated detection of prostate cancer status and/or quantification of prostate cancer risk using uptake metric determination based on prostate volume and functional-image voxel intensities.
Supports a quality control and reporting workflow via an interactive GUI with a quality control graphical widget and voxel selection for updated uptake metric determination.
Assigns prostate cancer status using severity-scale thresholds mapped to categories of clinical significance associated with ranges of uptake metric values.
Documented Applications
Detecting prostate cancer status and/or quantifying prostate cancer risk using automated analysis of 3D anatomical (pelvic region) and 3D functional images, followed by quality control and reporting workflow with threshold-based severity-scale categorization.
Interested in licensing this patent?