Endoscopic Swallowing Frame Classification With Temporal Block Integration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video endoscopic examinations for swallowing function evaluation face challenges in accurately determining the progression of swallowing movements, leading to oversight and increased user burden due to the need to review large volumes of images, with existing methods struggling to differentiate similar images or values across frames.
Innovation Solution
An image processing device that classifies each frame as either swallowing-in-progress or swallowing-not-in-progress, integrates adjacent frames within a specific temporal threshold as a swallowing block, and applies threshold values to determine the duration and accuracy of swallowing phases, using deep learning and motion recognition techniques to enhance precision.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If each frame is classified individually as swallowing-in-progress or swallowing-not-in-progress, then measurement precision is improved, but reliability deteriorates due to false positives from similar images
Solution Approach 1:
The patent merges multiple adjacent frames that are classified as swallowing-in-progress into a single swallowing block. This combination approach reduces the impact of false positives from individual frame classifications by requiring temporal consistency across multiple frames, thereby improving overall determination reliability while maintaining measurement precision at the frame level.
2Reliability
If all acquired images are reviewed to prevent oversight, then reliability is improved, but loss of time increases due to user burden
Solution Approach 1:
The patent extracts and integrates only the essential swallowing-in-progress frames into compact swallowing blocks, separating the critical information from the entire video sequence. This allows users to focus on a reduced set of integrated blocks rather than reviewing all individual frames, maintaining examination reliability while significantly reducing time loss.
3Productivity
If temporal interval threshold is set low to integrate more frames, then productivity is improved, but measurement precision deteriorates due to inclusion of non-swallowing frames
Solution Approach 1:
The patent dynamically adjusts the temporal interval threshold for frame integration based on the classification results. By adaptively selecting frames to integrate based on their classification status and temporal relationships, the system optimizes the balance between productivity (comprehensive integration) and measurement precision (accurate swallowing phase identification), avoiding both over-integration and under-integration.
Data Source
AI summary
An image acquisition unit acquires an examination image. A first frame classification unit classifies each frame of the examination image into any one of a swallowing-in-progress frame in which swallowing is in progress or a swallowing-not-in-progress frame in which the swallowing is not in progress. A swallowing block generation unit integrates, in a case in which a temporal interval between the swallowing-in-progress frames temporally adjacent to each other is equal to or less than a first threshold value, at least the adjacent swallowing-in-progress frames as a swallowing block.