# US 12,602,772 B2 · Systems and methods for rapid neural network-based image segmentation and radiopharmaceutical uptake determination

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,602,772 B2
- Document ID: US12602772B2
- Status: Granted
- Kind: B2
- Application number: 16/959,887
- Filed: 2019-01-07
- Published: 2020-10-29
- Granted: 2026-04-14
- Earliest claimed: 2018-01-08
- Assignees: Progenics Pharmaceuticals, Inc.; EXINI Diagnostics AB
- Applicants: Progenics Pharmaceuticals, Inc.; EXINI Diagnostics AB
- Inventors: Karl Vilhelm Sjöstrand; Jens Filip Andreas Richter; Kerstin Elsa Maria Johnsson; Erik Konrad Gjertsson
- Web page: https://patentgrep.com/patent/US12602772B2

## CPC

- G06T 7/0012: {Biomedical image inspection}
- A61B 6/032: {Transmission computed tomography [CT]}
- A61B 6/037: {Emission tomography}
- A61B 6/466: {adapted to display 3D data}
- A61B 6/5217: {extracting a diagnostic or physiological parameter from medical diagnostic data}
- A61B 6/5229: {combining image data of a patient, e.g. combining a functional image with an anatomical image}
- A61B 6/563: {involving image data transmission via a network}
- A61K 51/08: Peptides, e.g. proteins {, carriers being peptides, polyamino acids, proteins}
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 3/09: Supervised learning
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06T 7/62: of area, perimeter, diameter or volume
- G06T 12/30: Image post-processing, e.g. metal artefact correction
- G06T 15/08: Volume rendering
- G06N 3/105: {Shells for specifying net layout}
- G06T 2200/24: involving graphical user interfaces [GUIs]
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/10104: Positron emission tomography [PET]
- G06T 2207/10108: Single photon emission computed tomography [SPECT]
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30081: Prostate
- G06T 2207/30096: Tumor; Lesion
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- A61K: PREPARATIONS FOR MEDICAL, DENTAL OR TOILETRY PURPOSES (devices or methods specially adapted for bringing pharmaceutical products into particular physical or administering forms A61J3/00; chemical aspects of, or use of materials for deodorisation of air, for disinfection or sterilisation, or for bandages, dressings, absorbent pads or surgical articles A61L; soap compositions C11D)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## 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.

## Claims

### Claim 1

A method of detecting a prostate cancer status and/or quantifying a prostate cancer risk of a subject based on automated analysis of a 3D functional image of a portion of the subject, the method comprising:
(a) receiving, by a processor of a computing device, a 3D anatomical image of the subject obtained using an anatomical imaging modality, wherein the 3D anatomical image comprises a graphical representation of tissue within the subject, at least a portion of which corresponds to a pelvic region of the subject;
(b) receiving, by the processor, a 3D functional image of the subject obtained using a functional imaging modality, wherein the 3D functional image comprises a plurality of voxels, each representing a particular physical volume within the subject and having an intensity value that represents detected radiation emitted from the particular physical volume, wherein at least a portion of the plurality of voxels of the 3D functional image represent physical volumes within the pelvic region of the subject;
(c) determining, by the processor, using a first module, an initial volume of interest (VOI) within the 3D anatomical image, the initial VOI corresponding to tissue within the pelvic region of the subject and excluding tissue outside the pelvic region of the subject;
(d) identifying, by the processor, using a second module, a prostate volume within the initial VOI, said prostate volume corresponding to the prostate of the subject;
(e) determining, by the processor, a value of an uptake metric corresponding to a quantity of a radiopharmaceutical in the prostate of the subject based at least in part on intensity values of voxels of the 3D functional image that correspond to the prostate volume identified within the initial VOI of the 3D anatomical image;
(f) causing, by the processor, display of an interactive graphical user interface (GUI) for guiding a user through a quality control and reporting workflow;
(g) causing, by the processor, graphical rendering of the 3D anatomical image and/or the 3D functional image within the GUI, and causing, by the processor, display of, within the GUI, text and/or graphics representing the value of the uptake metric determined in step (e) along with a quality control graphical widget;
(h) receiving, by the processor, via the quality control graphical widget, a user input corresponding to disapproval of automated determination of the value of the uptake metric;
(i) causing, by the processor, display of a voxel selection graphical element, responsive to receipt of the user input corresponding to the disapproval of the automated determination of the value of the uptake metric, for user selection of one or more voxels of the 3D functional image for use in determining an updated value of the uptake metric;
(j) receiving, by the processor, via the voxel selection graphical element, the user selection of one or more voxels of the 3D functional image for use in determining the updated value of the uptake metric;
(k) updating, by the processor, the value of the uptake metric using the user selected voxels;
(l) determining, by the processor, the value of the uptake metric to be above a first threshold value and/or below a second threshold value, wherein the first and second threshold values are levels on a severity scale; and
(m) assigning, by the processor, a prostate cancer status to the subject based on the value of the uptake metric having been determined to be above the first threshold value and/or below the second threshold value, wherein the assigned prostate cancer status is one of a plurality of categories of clinical significance, each associated with a corresponding range of possible values of the uptake metric, and wherein the first and second threshold values are lower and upper bounds, respectively, of the particular range of values of the uptake metric corresponding to the assigned prostate cancer status.

### Claim 2 (depends on 1)

The method of claim 1, wherein increasing levels on the severity scale indicate increasing severity of cancer and/or increasing cancer risk for the subject.

### Claim 3 (depends on 1)

The method of claim 1, wherein the severity scale comprises no more than ten discrete levels.

### Claim 4 (depends on 3)

The method of claim 3, wherein the severity scale comprises no more than five discrete levels.

### Claim 5 (depends on 1)

The method of claim 1, wherein each level on the severity scale is also associated with a specific Gleason score or a range of two or more Gleason scores.

### Claim 6 (depends on 5)

The method of claim 5, wherein the severity scale comprises two or more discrete levels associated with Gleason scores greater than or equal to seven.

### Claim 7 (depends on 1)

The method of claim 1, wherein the uptake metric is a target-to-background ratio (TBR) representing a ratio between (i) a target intensity value and (ii) a background intensity value, wherein determining the TBR value at step (e) comprises:
determining the target intensity value using intensity values of one or more voxels of the 3D functional image that correspond to the prostate volume identified within the initial VOI of the 3D anatomical image;
determining the background intensity value using intensity values of one or more voxels of the 3D functional image that correspond to a reference volume identified within the 3D anatomical image; and
determining, as the TBR value for the subject, the ratio of the target intensity value to the background intensity value.

### Claim 8 (depends on 7)

The method of claim 7, wherein the reference volume identified within the 3D anatomical image corresponds to a gluteal muscle of the subject.

### Claim 9 (depends on 1)

The method of claim 1, wherein the 3D functional image is obtained following administration to the subject of the radiopharmaceutical, said radiopharmaceutical comprising a prostate-specific membrane antigen (PSMA) binding agent.

### Claim 10 (depends on 1)

The method of claim 1, wherein the 3D functional image is a single photon emission computed tomography (SPECT) image.

### Claim 11 (depends on 1)

The method of claim 1, wherein the 3D anatomical image is a computed tomography (CT) image.

### Claim 12 (depends on 1)

The method of claim 1, comprising:
(n) causing, by the processor, rendering of a graphical representation of the levels on the severity scale with a visual identification of the assigned prostate cancer status for the subject for display within the GUI.

### Claim 13 (depends on 1)

The method of claim 1, comprising diagnosing the subject according to the assigned prostate cancer status.

### Claim 14 (depends on 1)

The method of claim 1, comprising:
causing, by the processor, within the GUI, display of a graphical representation of the severity scale with a visual identification of the assigned prostate cancer status for the subject;
receiving, by the processor, via the GUI, a user approval of the assigned prostate cancer status; and
responsive to the user approval of the assigned prostate cancer status, generating, by the processor, a signed report comprising the approved prostate cancer status.

### Claim 15 (depends on 1)

The method of claim 1, wherein the 3D functional image is a positron emission tomography (PET) image.

### Claim 16

A system for detecting a prostate cancer status and/or quantifying a prostate cancer risk of a subject based on automated analysis of a 3D functional image of a portion of the subject, the system comprising:
a processor of a computing device; and
a memory having instructions stored thereon, wherein the instructions, when executed by the processor, cause the processor to:
(a) receive a 3D anatomical image of the subject obtained using an anatomical imaging modality, wherein the 3D anatomical image comprises a graphical representation of tissue within the subject, at least a portion of which corresponds to a pelvic region of the subject;
(b) receive a 3D functional image of the subject obtained using a functional imaging modality, wherein the 3D functional image comprises a plurality of voxels, each representing a particular physical volume within the subject and having an intensity value that represents detected radiation emitted from the particular physical volume, wherein at least a portion of the plurality of voxels of the 3D functional image represent physical volumes within the pelvic region of the subject;
(c) determine, using a first module, an initial volume of interest (VOI) within the 3D anatomical image, the initial VOI corresponding to tissue within the pelvic region of the subject and excluding tissue outside the pelvic region of the subject;
(d) identify, using a second module, a prostate volume within the initial VOI, said prostate volume corresponding to the prostate of the subject;
(e) determine a value of an uptake metric corresponding to a quantity of radiopharmaceutical in the prostate of the subject based at least in part on intensity values of voxels of the 3D functional image that correspond to the prostate volume identified within the initial VOI of the 3D anatomical image;
(f) cause display of an interactive graphical user interface (GUI) for guiding a user through a quality control and reporting workflow;
(g) cause graphical rendering of the 3D anatomical image and/or the 3D functional image within the GUI, and cause display of, within the GUI, text and/or graphics representing the value of the uptake metric determined in step (e) along with a quality control graphical widget;
(h) receive via the quality control graphical widget, a user input corresponding to disapproval of automated determination of the value of the uptake metric;
(i) cause display of a voxel selection graphical element, responsive to receipt of the user input corresponding to the disapproval of the automated determination of the value of the uptake metric, for user selection of one or more voxels of the 3D functional image for use in determining an updated value of the uptake metric;
(j) receive, via the voxel selection graphical element, the user selection of one or more voxels of the 3D functional image for use in determining the updated value of the uptake metric;
(k) update the value of the uptake metric using the user selected voxels;
(l) determine the value of the uptake metric to be above a first threshold value and/or below a second threshold value, wherein the first and second threshold values are levels on a severity scale; and
(m) assign a prostate cancer status to the subject based on the value of the uptake metric having been determined to be above the first threshold value and/or below the second threshold value, wherein the assigned prostate cancer status is one of a plurality of categories of clinical significance, each associated with a corresponding range of possible values of the uptake metric, and wherein the first and second threshold values are lower and upper bounds, respectively, of the particular range of values of the uptake metric corresponding to the assigned prostate cancer status.

### Claim 17 (depends on 16)

The system of claim 16, wherein the system is a cloud-based system.

### Claim 18 (depends on 16)

The system of claim 16, wherein the processor is a processor of a network-based computing device.

### Claim 19 (depends on 16)

The system of claim 16, wherein the instructions cause the processor to:
cause display of a graphical representation of the severity scale with a visual identification of the assigned prostate cancer status for the subject within the GUI;
receive, via the GUI, a user approval of the assigned prostate cancer status; and
responsive to the user approval of the assigned prostate cancer status, generate a signed report comprising the approved prostate cancer status.

### Claim 20 (depends on 16)

The system of claim 16, wherein the 3D functional image is a positron emission tomography (PET) image.