Automated Lymph Node Identification via Template Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current techniques for identifying sentinel lymph nodes, such as ICG fluorescence, face challenges in patients with high BMI and in areas with fatty tissue, as lymph drainage channels and nodes are difficult to visualize due to signal absorption, and distinguishing lymph nodes from other sources is error-prone.
Innovation Solution
An automated system that uses template matching techniques and machine learning, including neural networks, to identify lymph nodes in fluorescence images by comparing template images with acquired fluorescence images, enhancing visualization, and indicating the shape and depth of located nodes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ICG fluorescence technique is used to detect sentinel lymph nodes, then detection capability is improved, but visualization is insufficient in patients with high BMI and in areas with fatty tissue due to signal absorption
Solution Approach 1:
The patent introduces an automated image analysis system as an intermediary between the fluorescence imaging and surgical decision-making. This system processes fluorescence images to enhance visualization and automatically identify lymph nodes, compensating for the insufficient signal penetration in high BMI patients and fatty tissue areas where direct visual inspection fails
Solution Approach 2:
The patent replaces the surgeon's manual visual inspection and subjective judgment with an automated computer-based image analysis system. This substitution transforms the mechanical/visual process into an automated computational process that can objectively detect and identify lymph nodes even when fluorescence signals are weak or obscured by tissue absorption
2Productivity
If fluorescence imaging is used to identify lymph nodes, then detection speed is improved, but identification accuracy deteriorates because it is hard to distinguish lymph nodes from other sources
Solution Approach 1:
The patent introduces an automated image analysis system as an intermediary that bridges the gap between rapid fluorescence imaging and accurate lymph node identification. This system maintains the speed advantage of fluorescence imaging while adding computational analysis to accurately distinguish lymph nodes from other fluorescent sources in the body
Solution Approach 2:
The patent implements feedback mechanisms where the automated system analyzes fluorescence patterns, compares them against known lymph node characteristics, and provides identification results that can be verified or adjusted. This feedback loop enables rapid detection while maintaining high identification accuracy through iterative analysis and validation
3Device complexity
If manual identification of lymph nodes is performed by surgeons, then system complexity is reduced, but identification accuracy deteriorates due to error-prone subjective judgment
Solution Approach 1:
The patent enables the imaging system to perform self-analysis and automatic identification of lymph nodes without requiring extensive surgeon intervention or expertise in interpreting fluorescence images. The automated system independently processes images, identifies nodes, and provides results, making the complex analysis capability accessible to all surgeons regardless of experience level
Solution Approach 2:
The patent replaces the surgeon's subjective manual identification process with an automated computer-based analysis system. This substitution eliminates human error and variability while maintaining operational simplicity for the surgeon, who only needs to review the automated results rather than perform complex visual analysis
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system accurately identifies lymph nodes even in challenging cases, such as high BMI patients, and determines the likelihood of nodes being metastatic or benign, improving surgical precision and reducing errors.
Implementation Method 1
the indocyanine green (ICG) fluorescence technique for the detection of SLN
Implementation Method 2
The lymphatic system collects fluid that escapes from the cells, arteries, and veins, and returns the fluid, called lymph, back to the heart
Data Source
AI summary
The present disclosure relates generally to medical imaging, and more specifically to techniques for identifying at least one lymph node of a subject using fluorescence images. An exemplary method comprises obtaining a fluorescence image of a field of view including the at least one lymph node of the subject; obtaining a template image; comparing the template image with the fluorescence image to obtain one or more similarity values; and identifying at least one portion of the fluorescence image that corresponds to a location of the at least one lymph node based on the one or more similarity values.