International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 05 | May 2024
p-ISSN: 2395-0072
www.irjet.net
Pneumonia Disease Detection using Deep Learning Srikantha L1, Kumaraswamy S2 1Student, Computer Science and Engineering, University of Visvesvaraya College of Engineering
2Assistent Professor, Computer Science and Engineering, University Visvesvaraya College of Engineering
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Pneumonia is a serious lung sickness, usually
mortality [4]. Delayed diagnosis or misdiagnosis can lead to progression of the infection, worsening of symptoms, and increased likelihood of severe complications, including respiratory failure and sepsis. Timely identification of pneumonia allows for timely intervention with antibiotics or other therapeutic measures, thereby reducing the severity of the illness and minimizing the risk of adverse outcomes. Additionally, early detection of pneumonia facilitates targeted public health interventions, such as vaccination campaigns and infection control measures, aimed at preventing the spread of the disease within communities [5].
triggered by streptococcus pneumonia bacteria. It affects people worldwide. Right now, doctors check for it by looking at chest X-rays, but this can take a while and might not always be accurate. To address this challenge, we propose an automated system utilizing Convolutional Neural Networks (CNNs), specifically Inception models, trained on chest X-ray images sourced from Kaggle. Our approach aims to provide a costeffective and efficient solution for pneumonia identification, crucial for timely treatment and improved patient outcomes. By harnessing the power of deep learning, our research contributes to advancing pneumonia diagnosis, promising enhanced healthcare delivery and patient care.
1.2 Traditional Pneumonia Diagnosis Methods and Their Limitations
Key Words: Pneumonia Detection, Convolutional Neural Network (CNN), Flask web application chest X-ray images.
Methods for diagnosing pneumonia primarily rely on clinical assessment, physical examination, and radiological imaging, such as chest X-rays [6]. While chest X-rays are widely used for identifying pulmonary abnormalities indicative of pneumonia, their interpretation can be subjective and prone to variability among radiologists. Moreover, manual interpretation of chest X-rays is time consuming and may delay the process of diagnosis, where in resource limited settings, access to expert radiologists is limited. Furthermore, chest X-rays may lack sensitivity and specificity for detecting certain types of pneumonia, such as viral or atypical pneumonia, leading to diagnostic inaccuracies and suboptimal patient care [7].
1.INTRODUCTION Pneumonia is still a big problem for global health, causing a lot of sickness and death. It affects many people and leads to a high number of deaths, Pneumonia is a major worry for health worldwide, especially for those who are more at risk like kids, older adults, and people with weaker immune systems [1]. According to the World Health Organization (WHO), pneumonia causes about 2.5 million deaths every year, effects a leading cause of mortality worldwide [2]. The burden of pneumonia extends beyond its direct health impacts, encompassing economic costs associated with healthcare expenditures and loss of productivity. In developing countries, where access to healthcare resources may be limited, pneumonia poses an even greater threat, exacerbating existing health disparities and socioeconomic challenges [3].
1.3 Pneumonia Detection In response of limitations of traditional pneumonia diagnosis methods, computer assisted diagnostic (CAD) systems have emerged as promising tools for improving diagnostic accuracy and efficiency. CAD systems leverage advanced AI techniques to automate the detection, classification of pneumonia from medical image data [8]. Deep learning models, particularly CNNs, have indicate remarkable success from various image analysis tasks and including medical image interpretation [9]. By training CNN models on large datasets of chest x-ray images, CAD systems able to learn complex patterns, features associated with pneumonia, enabling accurate and rapid diagnosis. The importance of this study lies in its potential to revolutionize pneumonia diagnosis, offering a scalable and cost-effective solution for healthcare providers. By harnessing the power of CNNs, our goal is not only improving diagnostic accuracy but also enhances the efficiency and accessibility in pneumonia detection. The integration of Flask web application
1.1 Importance of Timely and Accurate Diagnosis for Effective Treatment Before you begin to format your paper, first write and save the content as a separate text file. Keep your text and graphic files separate until after the text has been formatted and styled. Do not use hard tabs, and limit use of hard returns to only one return at the end of a paragraph. Do not add any kind of pagination anywhere in the paper. Do not number text heads-the template will do that for youEarly diagnosis of pneumonia is crucial for initiating prompt and appropriate treatment, which can significantly to make better patient health outcomes and reduce the risk of complications and
© 2024, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 956