Neural Network Abnormal Shape Estimation via Outline Extraction

Solution Overview

Problem

The existing techniques for processing images of biological organs using neural networks face challenges due to the large amount of data, which can lead to reduced accuracy when compressing pixel information to reduce data volume.

Innovation Solution

An image processing apparatus that extracts the outline of body tissue, converts the coordinate sequence into a value sequence, and uses neural network processing to estimate abnormal shapes, thereby reducing the computational load while maintaining accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the number of pixels in the image is compressed to reduce data amount, then data processing efficiency is improved, but judgment accuracy is reduced

Engineering Contradiction:

Improvedata processing efficiencyVSAvoidjudgment accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent extracts only the essential outline information from the full image, separating the critical diagnostic features from the redundant pixel data. This extraction process removes unnecessary information while preserving the key characteristics needed for accurate cancer detection, thereby reducing data volume without compromising judgment accuracy.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent segments the image processing task into distinct stages: first extracting the outline of the biological organ, then processing only this outline data through the neural network. This segmentation allows the system to focus computational resources on the most relevant features rather than processing the entire high-resolution image.

Inventive Principle:

Principle #1Segmentation

2Measurement precision

If the full image data is processed by neural network, then judgment accuracy is maintained, but data processing load is excessive

Engineering Contradiction:

Improvejudgment accuracyVSAvoidcomputational complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts only the essential outline information from the full image, separating the critical diagnostic features from the redundant pixel data. This extraction process removes unnecessary information while preserving the key characteristics needed for accurate cancer detection, thereby reducing data volume without compromising judgment accuracy.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent segments the image processing task into distinct stages: first extracting the outline of the biological organ, then processing only this outline data through the neural network. This segmentation allows the system to focus computational resources on the most relevant features rather than processing the entire high-resolution image.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS10366488B2Image processing used to estimate abnormalities

Publication Date: 2019.07.30 MERATIVE US LP

AI summary

An image processing apparatus includes a computer system comprising an image acquiring section that acquires an image of body tissue. An extracting section of the computer system extracts an outline of the body tissue from the image, and a converting section of the computer system converts a coordinate sequence of the outline into a value sequence. An estimating section of the computer system estimates an abnormal shape of the body tissue by performing neural network processing on the value sequence. In addition, present invention embodiments include a computer program product used by the image processing apparatus and an image processing method performed by the image processing apparatus.