# US 2019/0244348 A1 · Methods and systems for utilizing quantitative imaging

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

- Number: US 2019/0244348 A1
- Document ID: US20190244348A1
- Status: Published application
- Kind: A1
- Application number: 16/206,454
- Filed: 2018-11-30
- Published: 2019-08-08
- Earliest claimed: 2015-08-14
- Assignees: Elucid Bioimaging Inc.
- Applicants: Elucid Bioimaging Inc.
- Inventors: Andrew J. Buckler; Kjell Johnson; Xiaonan Ma; Keith A. Moulton; Mark A. Buckler; Vladimir Valtchinov; David S. Paik
- Web page: https://patentgrep.com/patent/US20190244348A1

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- A61B 6/032: {Transmission computed tomography [CT]}
- G06F 18/211: Selection of the most significant subset of features
- G06F 18/2148: {characterised by the process organisation or structure, e.g. boosting cascade}
- G06F 18/24: Classification techniques
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06N 3/096: Transfer learning
- G06N 20/00: Machine learning
- G06T 3/00: Geometric image transformations in the plane of the image
- G06T 5/73: Deblurring; Sharpening
- G06T 7/11: Region-based segmentation
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/82: using neural networks
- G06V 20/69: Microscopic objects, e.g. biological cells or cellular parts
- G16H 30/40: for processing medical images, e.g. editing
- G06T 2207/10048: Infrared image
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/10088: Magnetic resonance imaging [MRI]
- G06T 2207/10101: Optical tomography; Optical coherence tomography [OCT]
- G06T 2207/10104: Positron emission tomography [PET]
- G06T 2207/10108: Single photon emission computed tomography [SPECT]
- G06T 2207/10132: Ultrasound image
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30096: Tumor; Lesion
- G06T 2207/30104: Vascular flow; Blood flow; Perfusion
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Systems and methods for analyzing pathologies utilizing quantitative imaging are presented herein. Advantageously, the systems and methods of the present disclosure utilize a hierarchical analytics framework that identifies and quantify biological properties/analytes from imaging data and then identifies and characterizes one or more pathologies based on the quantified biological properties/analytes. This hierarchical approach of using imaging to examine underlying biology as an intermediary to assessing pathology provides many analytic and processing advantages over systems and methods that are configured to directly determine and characterize pathology from underlying imaging data.

## Claims

### Claim 1

A method for computer aided phenotyping of a pathology, the method comprising:
deriving a machine learned model based on known ground truths, wherein the machine learned model is configured to:
(a) receive, as input, an enriched radiological dataset for a patient which includes analyte measurement and/or classification of one or more of: (i) anatomic structure, (ii) shape or geometry or (iii) tissue characteristic, type, or character, with objective validation for a set of analytes relevant to the pathology; and
(b) process the enriched radiological dataset to determine one or more of characteristics of a pathology including one or more of: (i) a phenotype for the pathology, (ii) a fractional flow reserve for the pathology, (iii) a high risk plaque for the pathology, (iv) a predictive outcome optionally including time to event for the outcome or (v) a cancer subtype for the pathology; and
implementing the machine learned model in an analytics system, wherein the analytics system is configured to process a received radiological dataset for a patient to create the enriched radiological dataset and use the machine learned model to process the enriched radiological dataset to determine the one or more of characteristics of the pathology.

### Claim 2 (depends on 1)

The method of claim 1 wherein deriving the machine learned model includes:
providing a training set comprising radiological data correlated with non-radiological ground truths with respect to the one or more of characteristics of the pathology for a plurality of patients;
enriching the training set so that the radiological data includes analyte measurement and/or classification of one or more of: (i) anatomic structure, (ii) shape or geometry or (iii) tissue characteristic, type, or character, with objective validation for a set of analytes relevant to the pathology; and
training the machine learned model using the training set.

### Claim 3 (depends on 2)

The method of claim 2, wherein the machine learned model is configured to process the enriched radiological dataset to determine a phenotype for the pathology.

### Claim 4 (depends on 2)

The method of claim 2, wherein the machine learned model is configured to process the enriched radiological dataset to determine a fractional flow reserve for the pathology.

### Claim 5 (depends on 2)

The method of claim 2, wherein the machine learned model is configured to process the enriched radiological dataset to determine a high risk plaque for the pathology.

### Claim 6 (depends on 2)

The method of claim 2, wherein the machine learned model is configured to process the enriched radiological dataset to determine a predictive outcome optionally including time to event for the outcome.

### Claim 7 (depends on 2)

The method of claim 2, wherein the machine learned model is configured to process the enriched radiological dataset to determine a cancer subtype for the pathology.

### Claim 8 (depends on 2)

The method of claim 2, wherein enriching the training set further includes spatial transformations of the radiological data to accentuate biologically-significant spatial context.

### Claim 9 (depends on 2)

The method of claim 2, wherein the analyte measurement and/or classification for enriching the training set includes semantic segmentation to identify and classify regions of interest in the radiological data.

### Claim 10 (depends on 9)

The method of claim 9, wherein the regions of interest are identified with respect to cross-sections of a pathology-specific structure in the radiological dataset.

### Claim 11 (depends on 2)

The method of claim 2, wherein enriching the training set includes both (i) semantic segmentation to identify and classify regions of interest in cross-sections of a pathology-specific structure in the radiological data to produce an annotated dataset and (ii) spatially transforming the annotated dataset with respect to the cross-sections of a pathology-specific structure to produce a pathology-appropriate transformed dataset.

### Claim 12 (depends on 11)

The method of claim 11, wherein the pathology-appropriate transformed dataset is an unwrapped dataset.

### Claim 13 (depends on 2)

The method of claim 2, wherein an image volume in the radiological data in the training set is preprocessed to form a region of interest containing a physiological target, lesion, and/or set of lesions that is to be analyzed.

### Claim 14 (depends on 13)

The method of claim 13, wherein the region of interest and/or the physiological target, lesion, and/or set of lesions are at least one of (i) automatically determined from the radiological data or (ii) identified by a user from the radiological data.

### Claim 15 (depends on 13)

The method of claim 13, wherein the region of interest includes one or more cross sections, each composed of projections through that volume.

### Claim 16 (depends on 2)

The method of claim 2, wherein enriching the training set includes ground truth annotation of analyte sub-regions as well as providing a spatial context of how such analytes sub-regions present in cross-section.

### Claim 17 (depends on 16)

The method of claim 16, wherein the spatial context provides a common basis for analysis of enhanced dataset relative to histological cross-sections.

### Claim 18 (depends on 16)

The method of claim 16, wherein the spatial context includes providing a coordinate system based on polar coordinates relative to a centroid of each cross-section.

### Claim 19 (depends on 2)

The method of claim 2, wherein enriching the training set includes ground truth annotation of analyte sub-regions using ex vivo classification independent of or in conjunction with image-based classification based on a common spatial context between the radiological dataset and ex vivo data.

### Claim 20 (depends on 2)

The method of claim 2, wherein the radiological data in the training set includes computed tomography (CT), dual energy computed tomography (DECT), spectral computed tomography (spectral CT), computed tomography angiography (CTA), cardiac computed tomography angiography (CCTA), magnetic resonance imaging (MRI), multi-contrast magnetic resonance imaging (multi-contrast MRI), ultrasound (US), positron emission tomography (PET), intra-vascular ultrasound (IVUS), optical coherence tomography (OCT), near-infrared radiation spectroscopy (NIRS), and/or or single-photon emission tomography (SPECT) diagnostic images.

### Claim 21 (depends on 2)

The method of claim 2, wherein enriching the training set includes using image deblurring or restoring is used to identify lesions of interest and extract pathology composition quantitatively.

### Claim 22 (depends on 2)

The method of claim 2, wherein enriching the training set includes spatially transforming cross-sectional segmented images into a pathology-appropriate transformed reference frame.

### Claim 23 (depends on 2)

The method of claim 2, wherein the pathology is related to the vasculature, wherein the machine learned classification model provides for fractional flow reserve classification of plaque.

### Claim 24 (depends on 23)

The method of claim 23, wherein a ground truth basis used in training the fractional flow reserve classification of plaque involves calcification, lipid-rich, necrotic, hemorrhagic, fibrotic, ulcerated, remodeled, thrombosed, and/or other atherogenic characteristic, singly or in combination.

### Claim 25 (depends on 23)

The method of claim 23, wherein plaque is classified as either pathologic or within normal variation.

### Claim 26 (depends on 2)

The method of claim 2, wherein the pathology is related to the vasculature, wherein the machine learned model provides for high risk plaque classification of plaque.

### Claim 27

(canceled)

### Claim 28

(canceled)

### Claim 29

(canceled)

### Claim 30 (depends on 2)

The method of claim 2, wherein the pathology is related to the vasculature, wherein the machine learned classification approach provides for time to event classification of pathology.

### Claim 31

(canceled)

### Claim 32 (depends on 2)

The method of claim 2, wherein the machine learned classification approach provides for cancer subtype classification of subtypes of masses.

### Claim 33

(canceled)

### Claim 34

(canceled)

### Claim 35 (depends on 9)

The method of claim 9, wherein the regions of interest are identified with respect to cross-sections of a focal structure in the radiological dataset.

### Claim 36 (depends on 2)

The method of claim 2, wherein enriching the training set includes both (i) semantic segmentation to identify and classify regions of interest in cross-sections of a focal structure in the radiological data to produce an annotated dataset and (ii) spatially transforming the annotated dataset with respect to the cross-sections of a focal structure to produce a focal dataset.

### Claim 37 (depends on 2)

The method of claim 2, wherein enriching the training set includes spatially transforming cross-sectional segmented images into a ‘focal’ reference frame.

### Claim 38

(canceled)

### Claim 39

(canceled)

### Claim 40 (depends on 23)

The method of claim 23, wherein a ground truth basis used in training fractional flow reserve classification is based on a pressure wire.

### Claim 41

(canceled)