Git Product home page Git Product logo

marisa-lim / nus-fyp Goto Github PK

View Code? Open in Web Editor NEW
0.0 1.0 1.0 1.44 GB

A lightweight 3D-printed device was built to solve the problem of infrequent testing for angle closure, which often lead to the unsuspected development of the disease and irreversible blindness. The device runs a Python code on a microprocessor to capture images of a patient’s eye with a camera and a light source. Thereafter, a deep learning algorithm built with PyTorch segments the iris and determines the grading of primary angle closure suspect. The result is displayed to the patient through the device.

Jupyter Notebook 91.21% Python 0.01% HTML 8.76% OpenSCAD 0.01%

nus-fyp's Introduction

A low-cost device to detect angle closure glaucoma

This repository was created as part of my final year project at the National University of Singapore under the Department of Biomedical Engineering.

In this project, the development of a device using low-cost materials was explored to facilitate the Standard Flashlight Test (SFT), a simple test done that checks for primary angle closure glaucoma (PACG) in patients. This device was created with the intention of independent use by users regardless of technological skills as majority of the target audience are elderly.

About the Project

A lightweight 3D-printed device (CAD_files) was built to solve the problem of infrequent testing for angle closure, which often lead to the unsuspected development of the disease and irreversible blindness. The device runs a Python code on a Raspberry Pi Zero (startup_code_fyp.py) to capture images of a patient’s eye with a camera and a light source. Thereafter, a deep learning algorithm built with PyTorch (segmentation_code.ipynb) segments the iris and determines the grading of primary angle closure suspect. The result is displayed to the patient through the device.

About the Repository

In this repository, you will find the device code (startup_code_fyp.py), segmentation code (segmentation_code) and the CAD files used to print the device (CAD_files). Both are written in Python.

The data for the segmentation code is not provided. Please request it if necessary from [email protected].

Segmentation Code

In the segmentation_code folder, you will find the models and Python notebook used. The .html and .pdf versions of the Python notebook are also included.

The necessary outputs are kept within for a better understanding of the notebook.

Start-up Code

This Python code is run on a Raspberry Pi Zero in the device to automate the Standard Flashlight Test. The Raspberry Pi GPIO library was used.

CAD Files

There are three components to the 3D-printed device: box top, box bottom, and LED holder. These are found in the CAD_files folder, which contains both the .stl and original SolidWorks files. An assembly file is also included within to visualise the three components together, with an additional eye cup to simulate the silicon eye cup that is attached later on.

nus-fyp's People

Contributors

marisa-lim avatar

Watchers

 avatar

Forkers

beatrix2402

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.