GI Tract Anatomical Location Detection From Endoscopy Images

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing endoscopic procedures lack efficient methods for accurately determining anatomical locations within the gastrointestinal tract, leading to inefficiencies in diagnosis, treatment planning, and patient care.

Innovation Solution

A data processing system that extracts features from endoscopy images and videos, using machine learning modules to detect and label anatomical locations, enabling precise location data for features like polyps and strictures, and integrating this information into electronic medical records.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional endoscopic procedures are used without automated feature extraction, then manual analysis time increases, but diagnostic accuracy and efficiency improve with automated machine learning-based feature detection and anatomical location labeling

Engineering Contradiction:

Improvediagnostic efficiencyVSAvoidprocedure time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical analysis of endoscopic images with an automated machine learning system. The system uses trained models to automatically detect features, extract anatomical locations, and label endoscopic data, substituting the physician's manual visual inspection and measurement processes with computational algorithms that process images and videos efficiently.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The machine learning system performs self-service by automatically analyzing endoscopic data without requiring continuous human intervention. The trained models independently detect features, determine anatomical locations, and generate labels, enabling the system to serve itself in the diagnostic process while providing assistance to physicians.

Inventive Principle:

Principle #25Self-service

2Measurement precision

If manual feature analysis is performed without automated systems, then system complexity remains low, but measurement precision of anatomical locations improves with machine learning-based detection

Engineering Contradiction:

Improveanatomical location accuracyVSAvoiddata processing system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces machine learning models as intermediary components between the raw endoscopic data and the final diagnostic conclusions. These models act as mediators that process images and videos, detect features, and provide structured output data that assists physicians in making accurate diagnoses, thereby improving measurement precision while managing complexity through modular architecture.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The data processing system is segmented into multiple independent machine learning modules, each responsible for specific tasks such as feature detection, anatomical location determination, and data labeling. This segmentation allows the complex system to be broken down into manageable components that can be developed, trained, and maintained independently, reducing overall system complexity while maintaining high measurement precision.

Inventive Principle:

Principle #1Segmentation

3Loss of information

If comprehensive feature extraction is performed on all endoscopic data, then diagnostic information completeness improves, but data processing time and computational resources increase

Engineering Contradiction:

Improvediagnostic information completenessVSAvoiddata processing time

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The system applies partial action by focusing feature extraction and analysis on the most diagnostically relevant portions of endoscopic data. Rather than uniformly processing all data with equal depth, the machine learning models identify and prioritize key features and anatomical locations that are most critical for diagnosis, thereby maintaining information completeness while reducing overall processing time and computational resource requirements.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12569129B2Anatomical location detection of features of a gastrointestinal tract of a patient

Publication Date: 2026.03.10 ITERATIVE SCOPES INC

AI summary

Generating a structured medical record from endoscopy data includes obtaining image data including endoscopic images representing portions of a gastrointestinal tract (GI) of a patient; determining features to extract from the image data, the features each representing a physical parameter of the GI tract; extracting the features from the image data; generating anatomical location data specifying a location within the GI tract of a portion of the GI tract represented in the image data; associating the anatomical location data with images that represent the portion of the GI tract; storing, in a node of a data store, data entries including the anatomical location data and the associated one or more images. The data store is configured to receive structured queries for the data entries in the data store and provide the data entries including the transformed features in response to receiving the structured queries.