Diagnosis of Pulmonary Diseases from Chest X-ray Using Deep Learning Approaches

In recent years, a severe pandemic has struck worldwide with the utmost shutter, enforcing a lot of stress in the medical industry. Moreover, the increasing population has brought to light that the work bestowed upon the healthcare specialists needs to be reduced. Medical images like chest X-rays are of utmost importance for the diagnosis of diseases such as pneumonia, COVID-19, thorax, and many more. Various manual image analysis techniques are time-consuming and not always efficient. Deep learning models for neural networks are capable of finding hidden patterns, assisting the experts in specified fields. Therefore, collaborating these medical images with deep learning techniques has paved the path for enormous applications leading to the reduction of pressure embarked upon the health industry. This paper demonstrates an approach for automatic lung diagnosing of COVID-19 (coronavirus) and thorax diseases from given CXR images, using deep learning techniques. The previously proposed model uses the concept of ResNet-18, ResNet-50, and Xception algorithms. This model gives the highest accuracy of 98% without segmentation and 95% with segmentation. Whereas, the proposed model uses CNN and CLAHE algorithms which achieves an accuracy of 99.22% without segmentation and 98.39% with segmentation. Therefore, this model will be able to provide assistance to health workforces and minimize manual errors precisely. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Lung disease detection using Self-Attention Generative Adversarial Capsule network optimized with sun flower Optimization Algorithm

Lung cancer is the uncontrolled growth of abnormal cells in one or both lungs. This is one of the dangerous diseases. A lot of feature extraction with classification methods were discussed previously regarding this disease, but none of the methods give sufficient results, not only that, those methods have high over fitting problem, as a result, the detection accuracy was minimizing. Therefore, to overcome these issues, a Lung Disease Detection using Self-Attention Generative Adversarial Capsule Network optimized with Sun flower Optimization Algorithm (SA-Caps GAN-SFOA-LDC) is proposed in this manuscript. Initially, NIH chest X-ray image dataset is gathered through Kaggle repository to diagnose the lung disease. Then, the chests X-ray images are pre-processed by using the contrast limited adaptive histogram equalization (CLAHE) filtering method to eliminate the noise and to enhance the image quality. These pre-processed outputs are fed to feature extraction process. In the feature extraction process, the empirical wavelet transform method is used. These extracted features are given into Self-Attention based Generative Adversarial Capsule classifier for detecting the lung disease. The hyper parameters of SA-Caps GAN classifier is optimized using Sun flower Optimization Algorithm. The simulation is implemented in MATLAB. The proposed SA-Caps GAN-SFOA-LDC method attains higher accuracy 21.05%, 33.28%, 30.27%, 29.68%, 32.57% and 44.28%, Higher Precision 30.24%, 35.68%, 32.08%, 41.27%, 28.57% and 34.20%, Higher F-Score 32.05%, 31.05%, 36.24%, 30.27%, 37.59% and 22.05% analyzed with the existing methods, SVM-SMO-LDC, CNN-MOSHO-LDC, XGboost-PSO-LDC respectively. © 2022 Elsevier Ltd

Efficient Grad-Cam-Based Model for COVID-19 Classification and Detection

Corona Virus (COVID-19) is a novel virus that crossed an animal-human barrier and emerged in Wuhan, China. Until now it has affected more than 119 million people. Detection of COVID-19 is a critical task and due to a large number of patients, a shortage of doctors has occurred for its detection. In this paper, a model has been suggested that not only detects the COVID-19 using X-ray and CT-Scan images but also shows the affected areas. Three classes have been defined;COVID-19, normal, and Pneumonia for X-ray images. For CT-Scan images, 2 classes have been defined COVID-19 and non-COVID-19. For classification purposes, pre-trained models like ResNet50, VGG-16, and VGG19 have been used with some tuning. For detecting the affected areas Gradient-weighted Class Activation Mapping (GradCam) has been used. As the X-rays and ct images are taken at different intensities, so the contrast limited adaptive histogram equalization (CLAHE) has been applied to see the effect on the training of the models. As a result of these experiments, we achieved a maximum validation accuracy of 88.10% with a training accuracy of 88.48% for CT-Scan images using the ResNet50 model. While for X-ray images we achieved a maximum validation accuracy of 97.31% with a training accuracy of 95.64% using the VGG16 model. © 2023 CRL Publishing. All rights reserved.

SVD-CLAHE boosting and balanced loss function for Covid-19 detection from an imbalanced Chest X-Ray dataset.

Covid-19 disease has had a disastrous effect on the health of the global population, for the last two years. Automatic early detection of Covid-19 disease from Chest X-Ray (CXR) images is a very crucial step for human survival against Covid-19. In this paper, we propose a novel data-augmentation technique, called SVD-CLAHE Boosting and a novel loss function Balanced Weighted Categorical Cross Entropy (BWCCE), in order to detect Covid 19 disease efficiently from a highly class-imbalanced Chest X-Ray image dataset. Our proposed SVD-CLAHE Boosting method is comprised of both oversampling and under-sampling methods. First, a novel Singular Value Decomposition (SVD) based contrast enhancement and Contrast Limited Adaptive Histogram Equalization (CLAHE) methods are employed for oversampling the data in minor classes. Simultaneously, a Random Under Sampling (RUS) method is incorporated in major classes, so that the number of images per class will be more balanced. Thereafter, Balanced Weighted Categorical Cross Entropy (BWCCE) loss function is proposed in order to further reduce small class imbalance after SVD-CLAHE Boosting. Experimental results reveal that ResNet-50 model on the augmented dataset (by SVD-CLAHE Boosting), along with BWCCE loss function, achieved 95% F1 score, 94% accuracy, 95% recall, 96% precision and 96% AUC, which is far better than the results by other conventional Convolutional Neural Network (CNN) models like InceptionV3, DenseNet-121, Xception etc. as well as other existing models like Covid-Lite and Covid-Net. Hence, our proposed framework outperforms other existing methods for Covid-19 detection. Furthermore, the same experiment is conducted on VGG-19 model in order to check the validity of our proposed framework. Both ResNet-50 and VGG-19 model are pre-trained on the ImageNet dataset. We publicly shared our proposed augmented dataset on Kaggle website (https://www.kaggle.com/tr1gg3rtrash/balanced-augmented-covid-cxr-dataset), so that any research community can widely utilize this dataset. Our code is available on GitHub website online (https://github.com/MrinalTyagi/SVD-CLAHE-and-BWCCE).

Efficient Grad-Cam-Based Model for COVID-19 Classification and Detection

Corona Virus (COVID-19) is a novel virus that crossed an animal-human barrier and emerged in Wuhan, China. Until now it has affected more than 119 million people. Detection of COVID-19 is a critical task and due to a large number of patients, a shortage of doctors has occurred for its detection. In this paper, a model has been suggested that not only detects the COVID-19 using X-ray and CT-Scan images but also shows the affected areas. Three classes have been defined;COVID-19, normal, and Pneumonia for X-ray images. For CT-Scan images, 2 classes have been defined COVID-19 and non-COVID-19. For classification purposes, pre-trained models like ResNet50, VGG-16, and VGG19 have been used with some tuning. For detecting the affected areas Gradient-weighted Class Activation Mapping (GradCam) has been used. As the X-rays and ct images are taken at different intensities, so the contrast limited adaptive histogram equalization (CLAHE) has been applied to see the effect on the training of the models. As a result of these experiments, we achieved a maximum validation accuracy of 88.10% with a training accuracy of 88.48% for CT-Scan images using the ResNet50 model. While for X-ray images we achieved a maximum validation accuracy of 97.31% with a training accuracy of 95.64% using the VGG16 model. © 2023 CRL Publishing. All rights reserved.

CapsCovNet: A Modified Capsule Network to Diagnose COVID-19 From Multimodal Medical Imaging.

Since the end of 2019, novel coronavirus disease (COVID-19) has brought about a plethora of unforeseen changes to the world as we know it. Despite our ceaseless fight against it, COVID-19 has claimed millions of lives, and the death toll exacerbated due to its extremely contagious and fast-spreading nature. To control the spread of this highly contagious disease, a rapid and accurate diagnosis can play a very crucial part. Motivated by this context, a parallelly concatenated convolutional block-based capsule network is proposed in this article as an efficient tool to diagnose the COVID-19 patients from multimodal medical images. Concatenation of deep convolutional blocks of different filter sizes allows us to integrate discriminative spatial features by simultaneously changing the receptive field and enhances the scalability of the model. Moreover, concatenation of capsule layers strengthens the model to learn more complex representation by presenting the information in a fine to coarser manner. The proposed model is evaluated on three benchmark datasets, in which two of them are chest radiograph datasets and the rest is an ultrasound imaging dataset. The architecture that we have proposed through extensive analysis and reasoning achieved outstanding performance in COVID-19 detection task, which signifies the potentiality of the proposed model.

A new method for detecting COVID-19 combining deep learning with improved histogram equalization and median filter

The new coronavirus (COVID-2019) epidemic outbreak has devastating impacts on people's daily lives and public healthcare systems. The chest X-ray image is an effective tool for diagnosing new coronavirus diseases. This paper proposes a new method to identify the new coronavirus from chest X-ray images to assist radiologists in fast and accurate image reading. We first enhance the contrast of X-ray images by using adaptive histogram equalization and eliminating image noise by using a median filter. Then, the X-ray image is fed to a sophisticated deep neural network (FAC-DPN-SENet) proposed by us to train a classifier, which is used to classify an X-ray image as usual or COVID-2019 or other pneumonia. Applying our method to a standard dataset, we achieve a classification accuracy of 93%, which is significantly better performance than several other state-of-the-art models, such as ResNet and DenseNet. This shows that the proposed method can be used as an effective tool to detect COVID-2019. © 2021 IEEE.

Stacked Dark COVID-Net: A Multi-class Multi-label Classification Approach for Diagnosing COVID-19 Using Chest X-Ray Images

Most challenging yet, the need of the hour is accurate diagnosis of COVID-19, as the Coronavirus cases are increasing drastically day-by-day. Ceaseless efforts by the researchers and innovators have led to the development of several diagnostic models based on Deep Learning for effective diagnosis of COVID-19. However, the Deep Learning techniques that have been developed so far, fail to address major challenges such as overfitting, stability, computation overhead due to the usage of the massive volume of parameters and problems associated with the multi-class classification. Also in the medical perspective, researchers often suffer to identify the infinitesimal difference that exists in the radiographic images among the several lung diseases which makes the decision-making process difficult. Thus, to curb the crisis and to provide promising solutions & expertise for accurate diagnosis, this paper presents a novel lightweight multi-class multi-label COVID-19 detection model to assist physicians with greater ease to fight against this pandemic situation. Radiographic images are pre-processed using Contrast Limited Adaptive Histogram Equalization (CLAHE) and classified using novel Stacked Dark COVID-Net. The proposed model is validated using chest X-ray images and the results confirm the efficacy of the proposed model in terms of classification accuracy, sensitivity, specificity and stability. © 2022, Springer Nature Switzerland AG.

A Comparative Study of Image Enhancement Methods for Human Skin Image

A person's skin serves as a primary line of protection against harmful chemical exposure. During the Covid 19 out-break, customer-provider interactions on social media increased, leading to improvements of the intelligent system for accurate skin type analysis. However, optimizing image quality before further analysis is an important step for training and testing data. As a result, image enhancement technologies contribute to the improvement of image quality. In this paper, we presets a study of four image enhancement techniques for improving the image contrast and detail of facial skin images required for further skincare analysis and treatment. The techniques of image enhancement include Histogram Equalization (HE), Contrast Limited Adaptive Histogram Equalization (CLAHE), Brightness Preserving Dynamic Fuzzy Histogram Equalization (BPDFHE), and Min-Max Contrast Stretching. The experimental results demonstrate that the CLAHE technique delivers the highest quality of clarity and also facilitates further image processing. © 2022 IEEE.

Diagnostic Decision Support for Medical Imaging and COVID-19 Image Classification on ARM Mali GPU

The abrupt rise in Coronavirus cases has led to shortage of rapid and highly sensitive reverse transcriptase polymerase chain reaction (RT-PCR) testing kits for the diagnosis of coronavirus disease 2019 (COVID-19). Radiologists have found X-ray images could be useful for diagnosis of COVID. In this work, Diagnostic Decision Support for Medical Imaging (DDSM)++ is introduced to detect the different abnormal conditions in lung including COVID. The scarcity of COVID dataset is handled by using various spatial transform augmentation techniques, such as power law transformation, Gaussian blur, and sharpening. Also, to get the benefit of inference accelerators, an android mobile application is developed which is quantized and optimized for ARM Mali GPU. The DDSM++ model is an extended version of DDSM model (inspired from Densenet-121), and the X-ray images are preprocessed with Contrast Limited Adaptive Histogram Equalization (CLAHE) to improve the quality of X-ray images. The COVID X-ray images are obtained from the open source and the proposed method has obtained almost 98.47% accuracy for COVID detection. Further, the model is quantized to FP-16 using TFLITE and is utilized to benchmark the inference acceleration on Edge devices with ARM Mali GPU. About 30% and 80% reduction in inference time was observed for FP-32 and FP-16 models when run on ARM Mali GPU. Post quantization, about 5% drop in accuracy is observed for COVID detection. © 2021 IEEE.

Comparative Analysis of CLAHE and AHE on Application of CNN Algorithm in the Detection of Covid-19 Patients

In 2021, Covid-19 is no longer a new threat for people in Indonesia and the world. The virus that has spread since December 2019 has created many transformation in many aspects for society. Various detection tools are emerged continuously to support government in overcoming the Covid-19 pandemic. Numerous cases that continue to grow in community, certainly, also requires detection tools with the best performance to handle this pandemic. In the field of informatics, many researchers use chest X-ray images to detect Covid-19, as a practitioner in informatics, authors attempt to apply several algorithms to get the best performance from Covid-19 detection. The objective of this study is to apply the Contrast Limited Adaptive Histogram Equalization (CLAHE) and Adaptive Histogram Equalization (AHE) algorithms in the detection of Covid-19 using Convolutional Neural Network (CNN) algorithm with VGG19 model. The dataset used in this study was a total of 1000 chest X-ray images and 1000 normal chest X-ray images obtained through Kaggle. The results of this study show that application of CLAHE has the highest accuracy of 99% for Covid-19 detection using VGG19. It is proved that the application of Histogram Equalization is able to improve the detection performance. © 2021 IEEE

Texture Analysis of Ultrasound Images to Differentiate Pneumonia and Covid-19

Lung ultrasound can potentially diagnose lung abnormalities such as pneumonia and covid-19, but it requires high experience. Covid-19, as a global pandemic, has similar common symptoms as pneumonia. The proper diagnosis of covid-19 and pneumonia necessitates clinicians' high expertise and skill to classify Covid-19 disease. This paper presents an approach to differentiate pneumonia and covid-19 based on texture analysis of ultrasound images. The proposed scheme is based on the Gray Level Co-occurrence Matrix (GLCM) features computing with Contrast Limited Adaptive Histogram Equalization (CLAHE) and gamma transformation for image enhancement. The results of the feature extraction analysis for lung ultrasound images suggest that differentiating pneumonia and Covid-19 is possible based on image texture features. © 2021 IEEE.

Multi-Channel Based Image Processing Scheme for Pneumonia Identification.

Pneumonia is a prevalent severe respiratory infection that affects the distal and alveoli airways. Across the globe, it is a serious public health issue that has caused high mortality rate of children below five years old and the aged citizens who must have had previous chronic-related ailment. Pneumonia can be caused by a wide range of microorganisms, including virus, fungus, bacteria, which varies greatly across the globe. The spread of the ailment has gained computer-aided diagnosis (CAD) attention. This paper presents a multi-channel-based image processing scheme to automatically extract features and identify pneumonia from chest X-ray images. The proposed approach intends to address the problem of low quality and identify pneumonia in CXR images. Three channels of CXR images, namely, the Local Binary Pattern (LBP), Contrast Enhanced Canny Edge Detection (CECED), and Contrast Limited Adaptive Histogram Equalization (CLAHE) CXR images are processed by deep neural networks. CXR-related features of LBP images are extracted using shallow CNN, features of the CLAHE CXR images are extracted by pre-trained inception-V3, whereas the features of CECED CXR images are extracted using pre-trained MobileNet-V3. The final feature weights of the three channels are concatenated and softmax classification is utilized to determine the final identification result. The proposed network can accurately classify pneumonia according to the experimental result. The proposed method tested on publicly available dataset reports accuracy of 98.3%, sensitivity of 98.9%, and specificity of 99.2%. Compared with the single models and the state-of-the-art models, our proposed network achieves comparable performance.