Pneumonia Detection using Deep Learning

IEEE BASE PAPER ABSTRACT:

Pneumonitis is a fatal disease that has an adverse effect on human respiratory system. It makes the air sacs of lungs inflammatory. It can happen due to viral or bacterial infections. It creates difficulty in breathing and causes pain. It can be severe and fatal if not treated at the earliest. So, the detection of pneumonia is needed as soon as possible. Hence the main objective of the project is to make a self-learning model whose training is done on multiple digital X-rays of chest to detect the pneumonia patients. This can help in the quick diagnosis of disease and give the treatment at the earliest. The model is trained on the ResNet and finetuned to give a good accuracy and prediction. The fine-tuned model can accurately classify the disease at 91% of accuracy.

PROJECT OUTPUT VIDEO:

ALGORITHM / MODEL USED:

VGG16 Architecture.

OUR PROPOSED ABSTRACT:

Pneumonia is a severe and prevalent infectious disease that affects millions of people worldwide. It is a leading cause of death, claiming over four million lives annually. Early detection of pneumonia is critical for prompt and effective treatment, which can greatly improve patient outcomes. Unfortunately, accurately diagnosing pneumonia can be challenging, especially in resource-limited settings where access to trained medical professionals is limited.

In recent years, deep learning has emerged as a powerful tool for medical image analysis. It has the potential to greatly improve the accuracy and efficiency of pneumonia detection, which can ultimately save lives. Deep learning algorithms can analyze large amounts of data quickly and accurately, allowing medical professionals to make more informed decisions.

The main objective of this paper is to propose a solution to this important public health problem. Specifically, we propose the development of a deep learning model for pneumonia detection using chest X-ray images. The proposed model will be based on VGG16 architecture. It will be trained on a large dataset of chest X-ray images, both with and without pneumonia, to enable the model to accurately differentiate between normal and infected lungs.

The proposed model has the potential to significantly improve the speed and accuracy of pneumonia detection, which can enable medical professionals to diagnose and treat patients more efficiently and effectively. The outcome of this project will be a deep learning model that can be easily deployed in hospitals and clinics, providing a valuable tool for medical professionals to aid in pneumonia detection. Ultimately, this can lead to more timely and accurate diagnoses, which can help save lives and reduce the burden of pneumonia on individuals and communities.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

System : Pentium i3 Processor.
Hard Disk : 500 GB.
Monitor : 15’’ LED
Input Devices : Keyboard, Mouse
Ram : 4 GB

SOFTWARE REQUIREMENTS:

Operating System : Windows 10 / 11.
Coding Language : Python 3.8.
Web Framework : Flask.
Frontend : HTML, CSS, JavaScript.

REFERENCE:

Shreyas Mishra, Aniket Hazra, U.M. Prakash, “Pneumonia Detection using Deep Learning”, 2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), IEEE Conference, 2022.

Python IEEE Projects

Pneumonia Detection using Deep Learning