Lung Cancer Detection System

Project Title

Project Area of Specialization

Computer Science

Project Summary

Our purpose is to develop a complete solution (system) for the detection of lung cancer using a machine learning algorithm (using exhaled breath-prints of the lung cancer patients and digital lung auscultation sounds). the reason for building this system is that it can detect lung cancer at early stages and it also is an invasive way to find it out. we will be using already trained models for VOCs and lung auscultation sounds and then we will be applying ensemble learning for making these models one.

Project Objectives

Our project is to develop a complete solution (system) for the detection of lung cancer by means of a machine learning algorithm (using exhaled breath-prints of lung cancer patients and digital lung auscultation sounds). The first phase comprises data collection, and training and the second phase is testing, tuning, and implementation. We aim to develop a system for the detection of lung cancer based on an ensemble learning model and e-nose and lung auscultation sounds

Project Implementation Method

This system required some technological objectives such as compatibility with Desktop. Also, the hardware that should be used is the one that can give the highest accuracy. The backend interfaces are planned to be developed using MERN stack and an anaconda navigator (Spyder) would be used for training the system. Cloud databases are preferred for database implementation. User interfaces are planned to develop using React.
According to the software development methodology (Waterfall), this implementation is proposed to process in the linear sequential flow. In the waterfall model, each phase is completed before starting any other phase in this way overlapping of phases can be avoided. The advantage of using this model is that it can be easy to Handle.

Benefits of the Project

This project aims to detect lung cancer by breath samples for volatile organic compounds and lung auscultation sounds. Our goal is to develop a system that is based on an ensemble learning model. Creating such a system will benefit in such a way that it may give early detection, low-cost solution, easy to implement, lesser lab equipment setup, and single-unit architecture.