CT Image Tissue Segmentation via Filtering and Masking

Solution Overview

Problem

Existing image generation technologies inaccurately identify pixels representing different body tissues, leading to overestimation of specific body tissue mass, requiring manual visual inspection to correct errors, which is time-consuming and effort-intensive.

Innovation Solution

An image generation apparatus and method that includes a measurement image acquirer, body tissue image generator, and masked body tissue image generator, which execute filtering and masking processes to accurately identify and separate specific body tissues like muscle, bone, and fat in CT images, using techniques such as binarization and masking based on contour identification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If filtering process is used to identify pixels representing specific body tissue based on measurement value range, then identification speed is improved, but measurement precision deteriorates due to erroneous identification of different body tissues

Engineering Contradiction:

Improveidentification speedVSAvoidtissue identification accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent segments the identification process into two distinct stages: first, a filtering process that quickly identifies candidate pixels based on measurement value ranges, and second, a masking process that removes erroneous identifications by excluding regions of different body tissues. This segmentation allows the system to maintain high identification speed while improving accuracy through the additional refinement step.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces a masking process as an intermediary step between the filtering process and final identification. The masking process uses body tissue images of different tissues to create masks that exclude erroneous regions from the specific body tissue identification, thereby improving measurement precision without significantly impacting identification speed.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If manual visual inspection is performed to remove erroneous pixel identifications, then measurement precision is improved, but loss of time increases significantly

Engineering Contradiction:

Improvetissue identification accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent implements an automated masking process that performs the error correction function previously requiring manual visual inspection. The system automatically generates masks based on body tissue images of different tissues and applies them to remove erroneous pixel identifications, thereby maintaining high measurement precision while eliminating the significant time loss associated with manual inspection.

Inventive Principle:

Principle #25Self-service

3Productivity

If filtering process is applied to identify specific body tissue pixels, then productivity is improved, but manufacturing precision deteriorates due to inclusion of different body tissues

Engineering Contradiction:

Improveprocessing efficiencyVSAvoidpixel identification accuracy

Core Design Contradiction:

ProductivityVSManufacturing precision

Solution Approach 1:

The patent segments the identification process into two distinct stages: first, a filtering process that quickly identifies candidate pixels based on measurement value ranges, and second, a masking process that removes erroneous identifications by excluding regions of different body tissues. This segmentation allows the system to maintain high identification speed while improving accuracy through the additional refinement step.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces a masking process as an intermediary step between the filtering process and final identification. The masking process uses body tissue images of different tissues to create masks that exclude erroneous regions from the specific body tissue identification, thereby improving measurement precision without significantly impacting identification speed.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11751834B2Image generation apparatus, image generation method, and information storage medium

Publication Date: 2023.09.12 RAKUTEN GROUP INC

AI summary

A measurement image acquisition unit 72 acquires a measurement image indicating a measurement value of a predetermined physical quantity for a measurement target including a plurality of types of body tissues. A body tissue image generation unit 74 generates a body tissue image associated with each of the plurality of types of body tissues by executing, for the each of the plurality of types of body tissues, a filtering process corresponding to the each of the plurality of types of body tissues with respect to the measurement image. A masked body tissue image generation unit 78 generates a masked body tissue image associated with a specific type of body tissue by executing, with respect to the body tissue image associated with the specific type of body tissue, a masking process which is based on the body tissue image associated with a different type of body tissue.