PNEUMONIA IDENTIFICATION USING ORGANIZING MAP ALGORITHM Moh ’ d

Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies, 2019

This article describes a comparison of two neural networks, the multilayer perceptron and Neural Network, for the detection and classification of pneumonia. The database used was the Chest-X-Ray data set provided by (Kermany et al., 2018) with a total of 5840 images, with two classes, normal and with pneumonia. to validate the models used, cross-validation of k-fold was used. The classification models were efficient, resulting in an average accuracy of 92.16% with the Multilayer Perceptron and 94.40% with the Convolution Neural Network.

Indonesian Journal of Electrical Engineering and Computer Science, 2021

This paper proposes efficient models to help diagnose respiratory (SARS-COVID19) infections by developing new data descriptors for standard machine learning algorithms using X-Ray images. As COVID-19 is a significantly serious respiratory infection that might lead to losing life, artificial intelligence plays a main role through machine learning algorithms in developing new potential data classification. Data clustering by K-Means is applied in the proposed system advanced to the training process to cluster input records into two clusters with high harmony. Principle component analysis (PCA), histogram of orientated gradients (HOG) and hybrid PCA and HOG are developed as potential data descriptors. The wrapper model is proposed for detecting the optimal features and applied on both clusters individually. This paper proposes new preprocessed X-Ray images for dataset featurization by PCA and HOG to effectively extract X-Ray image features. The proposed systems have potentially empowered machine learning algorithms to diagnose pneumonia (SARS-COVID19) with accuracy up to %97.

International Conference on Engineering & Technology (ICET-22), 2023

Lung diseases are responsible for many deaths and it is considered as one of the most common type of medical condition around the world [1]. In many occasions infections and genetics are identified as the main factors for lung diseases. Among many lung diseases Pneumonia is responsible for majority among those deaths [1]. From many years Chest radiograph (CXR) is aided by highly trained specialist in diagnosing these medical conditions. However, reviewing these images is a complicated task because, in pneumonia doctors need to consider number of other lung conditions such as fluid overload (pulmonary edema), bleeding and volume loss (atelectasis or collapse) Furthermore, with the limited number of available specialists, time constrain play a major role in this medical image reviewing process. Therefore, availability of an automated supporting system for this kind of tasks would be helpful for experts to quickly diagnose medical states. With the recent development in image processing and computer vision techniques, these techniques can be enabling in diagnosing medical images in a more efficient manner. This study proposes a system to achieve this purpose by providing more accurate results to find out pneumonia using CXR.

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.

Human-Centric Intelligent Systems

This paper surveys and examines how computer-aided techniques can be deployed in detecting pneumonia. It also suggests a hybrid model that can effectively detect pneumonia while using the real-time medical image data in a privacy-preserving manner. This paper will explore how various preprocessing techniques such as X-rays can detect and classify multiple diseases. The survey also examines how different machine learning technologies like convolution neural network (CNN), k-nearest neighbor (KNN), RESNET, CheXNet, DECNET and artificial neural network (ANN) can be used in detecting pneumonia disease. In this article, we have performed a comprehensive review of the literature to find how we can combine hospitals and medical institutions to train the machine learning models from their datasets so that the ML algorithms can detect disease more efficiently and correctly. We have proposed the future work of using transfer learning combined with federated knowledge that could help the medic...

Cornell University - arXiv, 2023

Purpose – This study focuses on the application of a specific subfield of artificial intelligence referred to as computer vision in the analysis of 2-dimensional lung x-ray images for the assisted medical diagnosis of ordinary pneumonia. Method – A convolutional neural network algorithm was implemented in a Python-coded, Flask-based web application that can analyze x-ray images for the detection of ordinary pneumonia. Since convolutional neural network algorithms rely on machine learning for the identification and detection of patterns, a technique referred to as transfer learning was implemented to train the neural network in the identification and detection of patterns within the dataset. Open-source lung x-ray images were used as training data to create a knowledge base that served as the core element of the web application and the experimental design employed a 5-Trial Confirmatory Test for the validation of the web application. Results –The tabulated results of the 5-Trial Confirmatory Test show the calculation of Diagnostic Precision Percentage per Trial, General Diagnostic Precision Percentage, and General Diagnostic Error Percentage while the Confusion Matrix further shows the relationship between the label and the corresponding diagnosis result of the web application on each test images. Conclusion – The successful generation of the h5 knowledge base proved that the CNN algorithm implementation for machine learning can generate patterns based on analyzing open-source datasets. The successful implementation and deployment of the web application to the cloud server proved that such a system can be feasibly deployed in such a platform. The experimental data proved the high precision of the analysis, proved that it can be used in the diagnosis of ordinary pneumonia under the supervision of medical practitioners. Recommendations – In retrospect, the precision of the diagnostic results could be enhanced further by utilizing a much larger training dataset for the machine learning phase. Since machine learning algorithms rely on the probability theory concept of the Law of Large Numbers, a large, high-quality dataset is crucial in yielding high-precision results. A more balanced training dataset is also necessary to avoid any kind of statistical bias during machine learning. A more balanced dataset could negate the use of data augmentation functionalities, thereby improving the efficiency and speed of the machine learning phase. Practical Implications – The developed web application can be used by medical practitioners in A.I.-assisted diagnosis of ordinary pneumonia, and by researchers in the fields of computer science and bioinformatics.

2016 IEEE 36th Central American and Panama Convention (CONCAPAN XXXVI)

Pneumonia is one of the major causes of child mortality. Unfortunately, in developing countries there is a lack of infrastructure and medical experts in rural areas to provide the required diagnostics opportunely. Lung ultrasound echography has proved to be an important tool to detect lung consolidates as evidence of pneumonia. This paper presents a method for automatic diagnostics of pneumonia using ultrasound imaging of the lungs. The approach presented here is based on the analysis of patterns present in rectangular segments from the ultrasound digital images. Specific features from the characteristic vectors were obtained and classified with standard neural networks. A training and testing set of positive and negative vectors were compiled. Vectors obtained from a single patient were included only in the testing or in the training set, but never in both. Our approach was able to correctly classify vectors with evidence of pneumonia, with 91.5% sensitivity and 100% specificity.

Pneumonia is the most dangerous disease and it is very difficult to detect the pneumonia due to lack of experts of this disease. This paper focus on the detection of lungs that are effected by pneumonia disease with the help of computer aided program. In this paper we also discuss the different techniques that can improve the efficiency of our system. In this paper we will convert raw x-ray image into a standard format for analysis and detection and then apply machine learning techniques such as convolution neural network (CNN) which plays a crucial role in the detection of pneumonia.

An approach to early diagnosis of pneumonia on individual radiographs based on the CNN information technology, 2021

Aim: This study investigates the topology of convolutional neural networks and proposes an information technology for the early detection of pneumonia in X-rays. Background: For the past decade, pneumonia has been one of the most widespread respiratory diseases. Every year, a significant part of the world's population suffers from pneumonia, which leads to millions of deaths worldwide. Inflammation occurs rapidly and usually proceeds in severe forms. Thus, early detection of the disease plays a critical role in its successful treatment. Objective: The most operating means of diagnosing pneumonia is the chest X-ray, which produces radiographs. Automated diagnostics using computing devices and computer vision techniques have become beneficial in X-ray image analysis, serving as an ancillary decision-making system. Nonetheless, such systems require continuous improvement for individual patient adjustment to ensure a successful, timely diagnosis. Methods: Nowadays, artificial neural networks serve as a promising solution for identifying pneumonia in radiographs. Despite the high level of recognition accuracy, neural networks have been perceived as black boxes because of the unclear interpretation of their performance results. Altogether, an insufficient explanation for the early diagnosis can be perceived as a severe negative feature of automated decision-making systems, as the lack of interpretation results may negatively affect the final clinical decision. To address this issue, we propose an approach to the automated diagnosis of early pneumonia, based on the classification of radiographs with weakly expressed disease features. Results: An effective spatial convolution operation with several dilated rates, combining various receptive feature fields, was used in convolutional layers to detect and analyze visual deviations in the X-ray image. Due to applying the dilated convolution operation, the network avoids significant losses of objects' spatial information providing relatively low computational costs. We also used transfer training to overcome the lack of data in the early diagnosis of pneumonia. An image analysis strategy based on class activation maps was used to interpret the classification results, critical for clinical decision making. Conclusion: According to the computational results, the proposed convolutional architecture may be an excellent solution for instant diagnosis in case of the first suspicion of early pneumonia.

arXiv (Cornell University), 2022

With the advancement in AI, deep learning techniques are widely used to design robust classification models in several areas such as medical diagnosis tasks in which it achieves good performance. In this paper, we have proposed the CNN model (Convolutional Neural Network) for the classification of Chest X-ray images for Radiological Society of North America Pneumonia (RSNA) datasets. The study also tries to achieve the same RSNA benchmark results using the limited computational resources by trying out various approaches to the methodologies that have been implemented in recent years. The proposed method is based on a non-complex CNN and the use of transfer learning algorithms like Xception, InceptionV3/V4, EfficientNetB7. Along with this, the study also tries to achieve the same RSNA benchmark results using the limited computational resources by trying out various approaches to the methodologies that have been implemented in recent years. The RSNA benchmark MAP score is 0.25, but using the Mask RCNN model on a stratified sample of 3017 along with image augmentation gave a MAP score of 0.15. Meanwhile, the YoloV3 without any hyperparameter tuning gave the MAP score of 0.32 but still, the loss keeps decreasing. Running the model for a greater number of iterations can give better results.