Smartphone Ophthalmic Imaging Attachment for Remote Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing ophthalmic imaging systems are expensive and difficult to handle, making it challenging to capture diagnostic images in regions with limited resources, such as developing countries or remote areas, where equipment and specialized personnel are scarce.
Innovation Solution
A diagnosis support device equipped with a mobile communication terminal featuring a close-up imaging device that includes an observation light irradiating member and a convex lens member, allowing users to capture images of the examined eye using a smartphone-like device, even without specialized knowledge.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If an advanced ophthalmic imaging device is used, then measurement precision of information parameter values is improved, but device complexity and cost increase
Solution Approach 1:
The patent creates a simplified copy of the advanced ophthalmic imaging system using a mobile communication terminal device. The close-up imaging device replicates the essential imaging function without requiring the complex infrastructure of traditional ophthalmic equipment, making the system accessible in resource-limited regions while maintaining diagnostic capability through AI processing.
Solution Approach 2:
The patent replaces the mechanical and optical complexity of traditional ophthalmic imaging devices with a mobile communication terminal device equipped with a simple close-up imaging device. The complex image processing and diagnostic functions are substituted by AI-based estimation algorithms that process images captured by the simplified imaging system.
2Reliability
If a specialized ophthalmic imaging device is used, then reliability of diagnosis support information is improved, but ease of operation deteriorates
Solution Approach 1:
The system enables self-service imaging where users can capture eye images themselves using the mobile communication terminal device without requiring specialized operators. The AI-based estimation automatically processes the captured images to generate diagnosis support information, eliminating the need for trained ophthalmic imaging specialists while maintaining reliable diagnostic output.
Solution Approach 2:
The patent introduces an AI-based estimation system as an intermediary between the simple image capture and the diagnostic interpretation. This intermediary automatically extracts meaningful information from user-captured images, bridging the gap between ease of operation and diagnostic reliability without requiring specialized human operators.
3Reliability
If traditional ophthalmic imaging systems are deployed, then quality of diagnosis support information is improved, but loss of time for image capture increases
Solution Approach 1:
The system performs preliminary AI-based estimation and image quality assessment automatically during the image capture process. The extraction unit identifies usable frame images in real-time, and the estimation unit generates preliminary diagnosis support information without requiring lengthy post-processing or specialized imaging procedures, significantly reducing the time from capture to diagnostic output.
Solution Approach 2:
The patent replaces time-consuming manual imaging procedures with automated AI-based processing. The system automatically captures, processes, and interprets eye images using machine learning algorithms, eliminating the need for specialized imaging techniques and manual analysis that characterize traditional ophthalmic systems, thereby dramatically reducing the time required for diagnosis support.
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 enables the reliable generation and distribution of diagnosis support information, including health state assessments and information parameter values, even in regions with limited resources, by automatically extracting diagnosable frame images and estimating health states using machine learning algorithms.
Implementation Method 1
a convex lens member that concentrates, of the observation light, light including reflected light in the tissue to be observed, on the imaging camera lens
Implementation Method 2
an observation light irradiating member that irradiates tissue to be observed of the examined eye with, as observation light, any one of slit light, blue light, and linearly polarized light
Data Source
AI summary
A close-up imaging device that generates slit light on the basis of light-source light emitted from a light source built into a mobile communication terminal device. The close-up imaging device is mounted onto the mobile communication terminal device, and a moving image of the tissue to be observed of the examined eye is captured by a camera module built into the mobile communication terminal device. Then, in a diagnosis support server device, a diagnosable frame image included in the captured moving image is extracted, at least one of a heath state of the examined eye and any one or more of a distance, an angle, and an area in some tissue of the examined eye is estimated on the basis of the diagnosable frame image extracted, and diagnosis support information is generated and distributed to the corresponding mobile communication terminal device.