Pneumonia Detection using Deep Learning Approach Complex Engineering Problem Digital Image Processing (original) (raw)

Detection of Pneumonia from X-Ray Images Using Deep Learning Techniques

Journal of Scientific Reports-A

X-ray images is one of the most common utilities used by health care specialists for detecting healthy problems in patients’ chest. In this work, deep learning techniques have been adopted for diagnosing and detecting of lung diseases. First, an experimental study has been conducted for selecting the best artificial neural network ANN model that can be used for lung X-Ray image classification. The obtained best model has been used for classifying the lung X-Ray images into three classes (Multi class classification) namely bacterial pneumonia, viral pneumonia, and healthy lung. After that, three well-known CNN architectures, namely ResNet, Inception, and MobileNet have been adopted and used as a feature extractor for the selected best ANN model. Moreover, the above-mentioned ANN model (both with and without the features extraction phase) has been used for classifying the lung X-Ray images as healthy and pneumonia lungs (Binary classification). As a result of the study, the proposed A...

Deep Learning Based Efficient Pneumonia Detection in Chest X-Ray Images

Irish Interdisciplinary Journal of Science & Research (IIJSR), 2023

Medical motion plays an essential role in clinical treatment. The deep neural network is an emerging machine learning method that has proven its potential for different classification tasks. Notably, the convolutional neural network dominates with the best results on varying image classification tasks. However, medical image datasets are hard to collect because it needs a lot of professional expertise to label them. Although it can be detected and treated with very less sophisticated instruments and medication. Therefore, this paper how to apply the Convolutional Neural Network (CNN) based algorithm on a chest X-ray dataset to classify pneumonia. The objective and automated detection of pneumonia represents a serious challenge in medical imaging because the signs of the illness are not obvious in CT or X-ray scans. Further on, it is also an important task, since millions of people die of pneumonia every year. Deep learning-based methods have shown good generalization traits over various problem domains, which prompts researchers around the globe to work tirelessly and come up with more efficient and effective models than earlier. However, this robust nature comes at the cost of high computational resources and, in general, it requires a huge amount of data to train the model efficiently. The latter requirement sometimes cannot be fulfilled, especially in the biomedical field. The main goal is to propose a solution for the above-mentioned problem, using a novel deep neural network architecture. The proposed novelty consists of the use of dropout in the convolutional part of the network. The proposed method was trained and tested on a set of labeled images. This project aims to introduce a deep learning technology based on the computational neural network, which can realize automatic diagnosis of patients with pneumonia in X-ray images.

Pneumonia Detection through X-Ray Using Deep Learning

2020

Pneumonia Detection through X-Ray Using Deep Learning is a web application which is used to detect the presence of Pneumonia from a collection of chest X-ray samples. Remarkable classification performance is achieved using methods that rely solely on transfer learning approaches or traditional handcrafted techniques. We constructed a convolutional neural network (CNN) model that extract features from a given chest X-ray image then it classifies it to determine if a person is infected with pneumonia. Reliability and interpretability challenges can be mitigated by this model that are often faced when dealing with medical imagery Key Word: Pneumonia, Detection, X-ray, Convolutional Neural Network (CNN), infected, Deep Learning and medical -------------------------------------------------------------------------------------------------------------------------------------Date of Submission: 18-02-2020 Date of Acceptance: 02-03-2020 --------------------------------------------------------...

Implementation of Intelligent Model of Pneumonia Detection, using Deep Learning

International Journal for Research in Applied Science & Engineering Technology, 2020

The progression of innovation in the field of man-made brainpower and neural organizations permits us to improve speed and productivity in the finding of different kinds of issues. Pneumonia is viewed as the best reason for youngster fatalities everywhere on the world. Roughly 1.4 million kids pass on of pneumonia consistently, which is 18% of the complete kids kicked the bucket at under five years of age. Pneumonia is a lung disease, which can be brought about by one or the other microscopic organisms or infections. The point of this examination was to build up a model of a keen framework that gets a x-ray picture of the lungs as an info boundary and, in view of the prepared picture, restores the chance of pneumonia as a yield. The usage of this usefulness was actualized through transfer learning, deep learning and image processing methodology based on already defined convolution neural network architectures. This investigation presents a deep CNN-based transfer learning approach for the programmed recognition of pneumonia and its classes. Some deep learning calculations and methods like Kera and CNN models were prepared and tried for arranging ordinary and pneumonia patients utilizing chest x-ray pictures.

Pneumonia Detection on Chest X-ray Using Deep Convolutional Neural Networks

The manual interpretation of medical images in healthcare facilities often delays patient diagnosis. This process is characterized by slow, time-consuming, costly, and laborintensive procedures. Pneumonia, a severe respiratory infection affecting the lungs, poses a significant threat, necessitating prompt detection and treatment to prevent fatalities. This study introduces an automated method utilizing deep learning to diagnose pneumonia. An approach employing a simplified CNN architecture has been devised, requiring less computational power. This approach can be particularly beneficial for healthcare facilities with limited resources. Experimentation conducted on a public image dataset yielded a model accuracy of 0.95. The study's findings demonstrate the proposed technique's efficacy, surpassing existing CNN models' accuracy and computational efficiency. This paper underscores the significance of deep learning in diagnosing and ensuring timely treatment for pneumonia.

Detection of Pneumonia in Patients Using Chest X-Ray Images Based on Convolutional Neural Networks

International Journal of Medical and Biomedical Studies, 2022

Pneumonia is a respiratory disease which inflames one or both lungs, and lungs may fill up with fluid. This can cause fever, chills, cough with phlegm or pus. It is a harmful disease that can be fatal in some cases. It is critical to detect pneumonia early, with a model which could help doctors reduce workload and bring in more accuracy in detection of pneumonia. In this work, we propose a model which is designed for the diagnosis of pneumonia that is trained on digital chest X-ray images to accurately diagnose pneumonic lungs. In the author’s opinion, this could benefit the medical field in the near future. Keywords: CNN, Keras, Pneumonia

Pneumonia Disease Detection Using Deep Learning Methods from Chest X-Ray Images: Review

International Journal of Advanced Trends in Computer Science and Engineering , 2021

Pneumonia is an infection-related condition under which the bronchi get damaged and clogged, decreasing oxygen diffusion and causing coughing and difficulty breathing. It can cause a range of symptoms, but it is more common in vulnerable populations. Pneumonia is the leading risk factor for mortality around the globe. Annually, pneumonia kills a significant percentage of youngsters around the globe. In 2016, an estimated one million cases of bronchitis were confirmed in kids under the age of five, with 880,000 deaths. The causes and symptoms of pneumonia are explained in this paper. There are several challenges occurs during detection of pneumonia from x-ray images. Some challenges are explained in this paper. The comparison of existing method of pneumonia detection and classification is depicted with limitations. Various deep learning based architectures are discussed in this paper. The pre-trained models based on deep learning framework such as InceptionV-4, CNN, ResNet50, VGG16, VGG19.

Determination of Pneumonia in X-ray Chest Images by Using Convolutional Neural Network

TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES, 2021

Pneumonia is one of the major diseases that cause a lot of deaths all over the world. Determining pneumonia from chest X-ray (CXR) images is an extremely difficult and important image processing problem. The discrimination of whether pneumonia is of bacterium or virus origin has also become more important during the pandemic. Automatic determination of the presence and origin of pneumonia is crucial for speeding up the treatment process and increasing the patient's survival rate. In this study, a convolutional neural network (CNN) framework is proposed for detection of pneumonia from CXR images. Two different binary CNNs and a triple CNN are used for determining: (i) normal or pneumonia, (ii) pneumonia of bacterium or virus origin, and (iii) normal or bacterial pneumonia or viral pneumonia. In this approach, CNNs are trained with Walsh functions to extract the features from CXR images, and minimum distance classifier instead of a fully connected neural network is employed for classification purpose. Training with Walsh functions maintains the within-class scattering to be low, and between-class scattering to be high. Preferring the minimum distance classifier reduces the number of nodes used and also allows the network to be controlled with fewer hyperparameters. These approaches bring some advantages to the system designed for the classification process: (i) easy determination of hyperparameters, (ii) achieving higher classification performance, and (iii) use of fewer neurons. The proposed smallsize CNN model was applied to CXR images from 1-to 5-year-old children provided by the Guangzhou Women's and Children's Medical Center (GWCMC). Three experiments have been conducted to improve the classification performance: (i) the effect of different sizes of input images on the performance of the network was investigated, (ii) training set was augmented by randomly flipping left to right or down to up, by adding Gaussian noise to the images, by creating negative images randomly, and by changing image brightness randomly (iii) instead of RGB CXR images, gray component of the original image and four 2D wavelet images were given as input to the network. In these experiments, no major changes were observed in the classification results obtained by using the proposed CNNs. The proposed method has achieved 100% accuracy for normal or pneumonia, 92% for pneumonia of bacterium or virus origin, and 90% for normal or bacterial pneumonia or viral pneumonia. It is observed that higher classification performances were obtained with approximately five times less parameters compared to the networks that gave the best results in the literature. Thus, the applied CNN model is promising in medicine and can help experts make quick and accurate decisions.

Review on Pneumonia Detection from Chest X-Ray using Deep Learning Approach

International Journal for Research in Applied Science and Engineering Technology IJRASET, 2020

Machine Learning (ML) provides various techniques and tools that can help solving diagnostic and prognostic problems in a variety of medical fields. Machine learning is being used for the analysis of the importance of clinical parameters and their combinations for diagnosis, e.g. prediction of disease progression, extracting medical information for outcome analysis, therapy planning and support, and for the patient management. ML is often used for data processing, such as data regularity identification by careful handling of imperfect data, continuous data analysis used in the Intensive Care Unit, and smart alarming resulting in accurate and efficient monitoring.ML can detect patterns of certain diseases in patient electronic healthcare records, and inform physicians of any anomalies. Chest X-rays are used to diagnose various diseases. Multiple diseases can be diagnosed from pneumonia to lung nodules using Deep Learning. A pre-trained ResNet-50 model is retrained with the use of different datasets of chest x-ray images. Notwithstanding major differences in datasets, ResNet-50 based diagnostic model is considered useful for pneumonia diagnosis. The trained model has achieved a 96.76 % accuracy. RSNA dataset, containing five times as many images as the Chest X-ray Image dataset, took very little time to prepare. In addition, both models were able to learn the significant features of pneumonia with a data set size of just % preparation, due to the use of the Transfer Learning technique. Still using deeper networks, the model can be improvised. The research may be expanded to identify and diagnose pneumonia with X-ray images.

PNEUMONIA DETECTION USING OF DEEP LEARNING CLASSIFIER IN MATLAB

IAEME PUBLICATION, 2024

Effective diagnosis and treatment planning of chest X-ray cancers depend on accurate tumor segmentation. In this research, we present an automated segmentation method on JPEG-formatted DICOM pictures utilizing adaptive thresholding. By utilizing the understanding of the structure and limits of the chest Xray, the technique seeks to distinguish between chest Xray malignancies. There are two primary processes in the segmentation process: first, grayscale pictures are converted to binary format, and then the resulting binary masks of CT images are subjected to adaptive Thresholding. We test our method on abdominal CT datasets, showing encouraging tumor segmentation outcomes. By developing reliable and effective methods for analyzing tumors seen on chest X-rays, our research helps to ensure that patients receive the right diagnosis and course of therapy