Pancreatic Cyst Classification via Neural Network Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for classifying pancreatic cysts on CT images lack precision and accuracy, making it difficult to predict the likelihood of pancreatic cancer, as they rely on visual analysis and do not effectively utilize advanced image processing techniques.

Innovation Solution

A computer-implemented method using CT images that performs filtering, segmentation with a neural network, and morphological analysis to classify pancreatic cysts based on shape, position, and demographic data, enabling precise localization and characterization of cysts and their potential classification into specific types.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If visual analysis methods are used for pancreatic cyst classification, then the process is simple and easy to operate, but the measurement precision and classification accuracy are insufficient

Engineering Contradiction:
Improveclassification accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary system consisting of a neural network model and image processing algorithms that act as a mediator between the CT images and the final classification. This intermediary automatically extracts morphological features and performs classification, resolving the contradiction by providing high measurement precision through automated analysis while managing system complexity through modular software architecture.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical/manual visual analysis system with an automated computational system using neural networks and image processing algorithms. This substitution transforms the classification process from manual observation to automated digital analysis, achieving superior measurement precision while the software-based system maintains operational simplicity through automated workflows.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If advanced image processing techniques are implemented, then the measurement precision improves, but the ease of operation decreases

Engineering Contradiction:
Improvelocalization precisionVSAvoidoperational simplicity
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent implements a self-service system where the image processing algorithms and neural network automatically perform feature extraction, segmentation, and classification without requiring manual intervention. The system serves itself by autonomously processing CT images, calculating morphological parameters, and generating classifications, thereby achieving high localization precision while maintaining ease of operation through automated workflows.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent performs preliminary actions by pre-training the neural network model with labeled data and pre-programming the image processing algorithms to automatically extract relevant features. This preliminary preparation enables the system to achieve high measurement precision during actual operation without requiring complex manual configuration or intervention, thus maintaining operational simplicity.

Inventive Principle:
Principle #10Preliminary action

3Productivity

If manual classification methods are used, then the device complexity is low, but the productivity and efficiency are reduced

Engineering Contradiction:
Improveclassification efficiencyVSAvoidprocessing system complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent implements continuous automated processing where the neural network and image processing algorithms continuously analyze CT images without interruption. The system processes multiple images and cysts in sequence, maintaining continuous useful action that significantly improves productivity compared to manual classification. The automated workflow eliminates idle time between analyses while the modular software architecture manages system complexity effectively.

Inventive Principle:
Principle #20Continuity of useful action

Solution Approach 2:

The patent changes the operational parameters from manual assessment to automated computational analysis by adjusting the processing mode to use neural networks and algorithmic feature extraction. This parameter change enables high-speed processing of multiple images and cysts, dramatically improving classification efficiency while the systematic approach to parameter management keeps the processing system complexity controllable.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4396769B1Method and computer program for the automatic classification of pancreatic cysts
Publication Date: 2024.11.20 SYCAI TECH SL
  • EP4396769B1 patent drawingFigure 1
  • EP4396769B1 patent drawingFigure 2
  • EP4396769B1 patent drawing

AI summary

A method and computer program product for the automatic classification of pancreatic cysts using CT images are proposed. The method comprises accessing a set of CT images of a patient; performing a filtering operation on the set of CT images, and defining a ROI within the filtered set of CT images; performing a segmentation operation of the defined ROI using a neural network, obtaining a segmented image representing values of a first value for the pixels occupied by a pancreatic cyst and values of at least a second value for the pixels not occupied by a pancreatic cyst; performing a morphological analysis of the pancreatic cyst by means of using an image processing algorithm that processes the pixels with the first value; and classifying the pancreatic cyst based on the morphological analysis and demographic data of the patient, the demographic data including the gender and age of the patient.