Smartphone Ferning Pattern Detection for Ovulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current ovulation detection methods based on salivary ferning are manual and highly subjective, leading to misinterpretation by lay consumers and requiring costly, non-reusable urine-based tests.
Innovation Solution
A smartphone-based automated optical system using a microfluidic device and computer vision model, specifically a convolutional neural network, to detect ferning patterns in air-dried saliva samples for accurate ovulation prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual salivary ferning analysis is used, then cost is reduced, but measurement precision and reliability deteriorate due to high subjectivity and misinterpretation
Solution Approach 1:
The patent replaces manual visual inspection with an automated optical system using a smartphone camera and computer vision algorithms. The mechanical/visual process of manual ferning pattern analysis is substituted with digital image capture and automated image processing, eliminating human subjectivity while maintaining simplicity through the use of a common smartphone device.
Solution Approach 2:
The patent creates a digital copy of the salivary ferning pattern through smartphone camera imaging. Instead of direct human observation of the physical sample, the system captures a digital image copy that can be processed by computer vision algorithms, preserving the diagnostic information while enabling automated analysis.
2Measurement precision
If automated optical system with computer vision is implemented, then measurement precision improves to 99.5%, but device complexity increases
Solution Approach 1:
The system performs self-service through automated image capture and processing. Once the sample is placed on the device, the smartphone automatically captures the image and the convolutional neural network automatically analyzes it without requiring user intervention in the complex analysis steps, making the operation simple despite the sophisticated underlying technology.
Solution Approach 2:
The patent utilizes a smartphone, which is a universal device already possessed by most users, to perform multiple functions including image capture, image processing, and result display. This eliminates the need for specialized dedicated equipment, maintaining ease of operation while achieving high measurement precision through multi-functional use of a common device.
3Reliability
If urine-based tests are used, then reliability improves, but cost increases and the tests are non-reusable
Solution Approach 1:
The system recovers and reuses the same saliva sample for multiple analyses. Unlike disposable urine tests that consume the sample, the optical system can capture multiple images of the same dried saliva sample on the microfluidic device, allowing repeated measurements without consuming additional biological material.
Solution Approach 2:
The patent uses a low-cost microfluidic device that can be discarded after a single use, replacing expensive reusable urine test kits. The microfluidic device itself is inexpensive to manufacture, making the overall system cost-effective even though the sample analysis capability is reusable.
Data Source
AI summary
Systems and methods are provided for determining if a subject has a biological condition from a dried fluid sample. A fluid sample from a subject is dried in a microfluidic device to provide a dried fluid sample. The dried fluid sample is imaged at a camera to provide a sample image, and the sample image is provided to a computer vision mode. At the computer vision model, it is determined if the sample image contains a ferning pattern indicative of a biological condition of the subject.