Optical Transfer Diagnosis for Melanoma Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for discriminating between malignant and benign tissue lesions, such as melanoma, face limitations in accuracy and reliability, especially for less experienced users, and existing automated devices often rely on digitalized dermoscopy features analyzed by artificial neural networks or support vector machine learning systems, which may not effectively account for variations in measurement and data processing errors.
Innovation Solution
A method utilizing Optical Transfer Diagnosis (OTD) to generate morphologic and physiologic maps from spectral reflectance images, which records 30 images at different wavelengths and angles, deriving parameters like hemoglobin percentage and melanosome concentration, and applying an optimization procedure with a cost function to derive optimal weights for diagnosis, ensuring robustness against measurement errors and variations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated devices use digitalized dermoscopy features analyzed by artificial neural networks or support vector machine learning systems, then productivity of lesion screening is improved, but measurement precision and reliability deteriorate due to inability to effectively account for variations in measurement and data processing errors
Solution Approach 1:
The patent applies preliminary action by performing optimization procedures to derive optimal weights for different input parameters before final diagnosis. The system pre-calculates weight factors that account for measurement errors and data processing variations, ensuring that these corrections are already in place before the actual classification decision is made, thereby improving both efficiency and accuracy
Solution Approach 2:
The patent implements parameter changes by transforming raw dermoscopy features into optimized weighted parameters. The system dynamically adjusts the weight of different input parameters based on their reliability and error characteristics, converting multiple imperfect measurements into a set of optimized parameters that collectively provide more accurate and reliable diagnosis than individual features alone
2Ease of operation
If visual detection is used even with dermoscopy assistance, then ease of operation is maintained, but measurement precision and reliability worsen especially for less experienced users
Solution Approach 1:
The patent introduces an intermediary layer between the user and the complex analysis of dermoscopy images. The automated device serves as a mediator that processes multiple parameters with optimized weighting, translating complex medical image analysis into reliable diagnostic support while keeping the user interface simple and easy to operate
Solution Approach 2:
The patent replaces the mechanical system of human visual inspection with an automated optical and computational system. Instead of relying on human eyes and brain processing, the system uses automated image analysis with optimized parameter weighting to detect and classify lesions, thereby improving precision while maintaining ease of operation through automation
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 method achieves high sensitivity and specificity in distinguishing between malignant and benign lesions, with a sensitivity of 100% for specificity above 91.4%, and reduces false positives, demonstrating improved accuracy and robustness in melanoma detection.
Implementation Method 1
a method utilizing Optical Transfer Diagnosis (OTD) to generate morphologic and physiologic maps from spectral reflectance images, which records 30 images at different wavelengths and angles
Data Source
Figure 1
Figure 2
AI summary
An embodiment of the present invention includes a method for discriminating between benign and malignant tissue lesions. The method includes the steps of using a plurality of maps of physiology and morphology parameters generated from reflectance measurements and pure morphology parameters generated from reflectance measurements. The method also includes calculating entropies and cross entropies of the plurality of maps, and calculating a plurality of pure morphology parameters. Further, the method includes assigning a weight to each entropy and a weight to a logarithm of each entropy, a weight to each cross entropy and a weight to a logarithm of each cross entropy, and a weight to each pure morphology parameter and a weight to a logarithm of each pure morphoiogy parameter. The method further includes computing a diagnostic index, defining a cost function, defining a proper threshold value for a diagnostic index and solving an optimization problem to determine a set of weights from the assigned weights to maximize specificity for 100% sensitivity. Further, the method uses calculations, the cost function and the diagnostic index to determine whether the tissue lesion is benign or malignant.