Automated Fatty Liver Detection via CT Hounsfield Unit Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for analyzing computed tomography (CT) scans lack efficiency in automatically detecting fatty liver conditions, requiring manual radiologist review and specialized imaging settings, which can be time-consuming and expose patients to additional radiation.

Innovation Solution

A computer-implemented method and system that automatically segment liver regions from CT imaging data using binary segmentation and Hounsfield unit (HU) values, allowing for the detection of fatty liver without requiring dedicated scan settings or additional hardware, by analyzing liver parameters relative to spleen parameters.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual radiologist review is used for fatty liver detection, then detection accuracy is maintained, but time consumption and operational complexity increase

Engineering Contradiction:

Improvedetection accuracyVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system enables automated self-detection of fatty liver by processing CT scan images through algorithms that automatically segment the liver, calculate HU values, and determine fatty liver presence without requiring manual radiologist intervention for the detection process itself

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The manual mechanical review process by radiologists is replaced with an automated computational system that uses image processing algorithms, HU value calculations, and rule-based detection logic to perform fatty liver detection

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If specialized imaging settings are used for fatty liver detection, then detection accuracy is improved, but device complexity and radiation exposure increase

Engineering Contradiction:

Improvedetection accuracyVSAvoidimaging settings complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system enables fatty liver detection using standard CT scan settings that are already widely deployed, making the detection capability universal and accessible without requiring specialized or additional imaging equipment

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system changes the analysis parameter from visual assessment to quantitative HU value measurement, allowing fatty liver detection to be performed on existing standard CT images by simply analyzing the density values rather than requiring specialized imaging protocols

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If additional dedicated scans are performed for fatty liver detection, then detection accuracy is improved, but radiation exposure increases

Engineering Contradiction:

Improvedetection accuracyVSAvoidradiation exposure

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The system enables fatty liver detection as a byproduct of routine CT scans, allowing the same imaging data to serve multiple purposes (diagnostic imaging plus fatty liver screening) without requiring additional scans

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The fatty liver detection is performed automatically on existing scan data without requiring the patient to undergo additional radiation exposure from dedicated fatty liver scans

Inventive Principle:

Principle #25Self-service

4Measurement precision

If manual radiologist review is used for fatty liver detection, then detection thoroughness is maintained, but productivity decreases

Engineering Contradiction:

Improvedetection thoroughnessVSAvoiddetection throughput

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The manual review process is replaced with automated computational processing that can analyze multiple images simultaneously, dramatically increasing detection throughput while maintaining consistency

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs automated detection without requiring radiologist time for each case, enabling high-volume processing while radiologists are freed to focus on complex diagnostic decisions

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS9940711B2Systems and methods for detecting a fatty liver from a computed tomography (CT) scan

Publication Date: 2018.04.10 ZEBRA MEDICAL VISION

AI summary

There is provided a computer-implemented method for detecting a fatty liver, comprising: receiving imaging data of a computed tomography (CT) scan performed using a single source CT Scanner with settings selected for imaging of non-fatty-liver pathology, segmenting a region of the liver by creating a binary image by applying binary segmentation to a sub-set of pixels of the imaging data according to a first set-of-rules, and mapping the region of liver of the binary image to the segmented region of the portion of the liver of the imaging data, calculating liver parameter(s) for the segmented region of the liver from Hounsfield unit (HU) value(s), and detecting the presence of a fatty liver by analyzing the calculated liver parameter(s) according to a second set-of-rules.