Automated CT Scanning Field Selection via Local Feature Voting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current CT imaging techniques rely on manual selection of scanning fields by human operators, which is time-consuming, prone to inconsistencies, and may result in exposure to unnecessary radiation due to the need for wide margins to account for patient movement, making it difficult to accurately capture desired structural data and compare follow-up studies.

Innovation Solution

An automated method using local feature candidates detected from preliminary scans, such as topograms, where the accuracy of each candidate is assessed through voting groups to identify and remove the least accurate features, ultimately determining a precise scanning field based on remaining candidates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual field selection is used, then operator expertise can be applied, but the process is time-consuming and inconsistent

Engineering Contradiction:

Improvefield selection accuracyVSAvoidfield selection time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical process of field selection with an automated computer-based system that uses algorithms to detect anatomical landmarks and determine scanning fields automatically, eliminating human operator variability and time consumption

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-service by automatically detecting anatomical features and determining scanning fields without requiring operator intervention, allowing the imaging system to autonomously complete the field selection process

Inventive Principle:

Principle #25Self-service

2Reliability

If wide scanning fields are used to account for patient movement, then completeness of structural data is improved, but radiation exposure increases

Engineering Contradiction:

Improvedata completenessVSAvoidradiation exposure

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary detection of anatomical landmarks and prediction of optimal scanning fields before the actual CT scan, allowing the field to be precisely defined based on detected features rather than using wide margins to account for potential movement

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses feedback from detected anatomical features to dynamically adjust and optimize the scanning field boundaries, ensuring the field is precisely sized based on actual anatomy rather than using fixed wide margins

Inventive Principle:

Principle #23Feedback

3Adaptability or versatility

If manual field selection is used, then operator judgment is applied, but consistency across multiple scans deteriorates

Engineering Contradiction:

Improveoperator adaptabilityVSAvoidscan consistency

Core Design Contradiction:

Adaptability or versatilityVSStability of the object's composition

Solution Approach 1:

The patent replaces manual operator judgment with automated computer algorithms that consistently apply the same detection and prediction rules across all scans, eliminating variability introduced by different operators or operators' varying judgment

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS8160341B2Systems and methods for automatic robust anatomy detection through local voting and prediction

Publication Date: 2012.04.17 SIEMENS HEALTHCARE GMBH

AI summary

A method for performing a medical imaging study includes acquiring a preliminary scan. A set of local feature candidates is automatically detected from the preliminary scan. The accuracy of each local feature candidate is assessed using multiple combinations of the other local feature candidates and removing a local feature candidate that is assessed to have the lowest accuracy. The assessing and removing steps are repeated until only a predetermined number of local feature candidates remain. A region of interest (ROI) is located from within the preliminary scan based on the remaining predetermined number of local feature candidates. A medical imaging study is performed based on the location of the ROI within the preliminary scan.