Detecting COVID-19 early may help in devising an appropriate treatment plan and disease containment decisions. In this study, we demonstrate how transfer learning from deep learning models can be used to perform COVID-19 detection using images from three most commonly used medical imaging modes X-Ray, Ultrasound, and CT scan. The aim is to provide over-stressed medical professionals a second pair of eyes through intelligent deep learning image classification models. We identify a suitable Convolutional Neural Network (CNN) model through initial comparative study of several popular CNN models. We then optimize the selected VGG19 model for the image modalities to show how the models can be used for the highly scarce and challenging COVID-19 datasets. We highlight the challenges (including dataset size and quality) in utilizing current publicly available COVID-19 datasets for developing useful deep learning models and how it adversely impacts the trainability of complex models. We also propose an image pre-processing stage to create a trustworthy image dataset for developing and testing the deep learning models. The new approach is aimed to reduce unwanted noise from the images so that deep learning models can focus on detecting diseases with specific features from them. Our results indicate that Ultrasound images provide superior detection accuracy compared to X-Ray and CT scans. The experimental results highlight that with limited data, most of the deeper networks struggle to train well and provides less consistency over the three imaging modes we are using. The selected VGG19 model, which is then extensively tuned with appropriate parameters, performs in considerable levels of COVID-19 detection against pneumonia or normal for all three lung image modes with the precision of up to 86% for X-Ray, 100% for Ultrasound and 84% for CT scans.

/pdf/covid-19-detection-through-transfer-learning-using-3jkti8jq1q.pdf

COVID-19 Detection through Transfer Learning Using Multimodal Imaging Data

Coronavirus (COVID-19) epidemic outbreak has devastating effects on daily lives and healthcare systems worldwide This newly recognized virus is highly transmissible, and no clinically approved vaccine or antiviral medicine is currently available Early diagnosis of infected patients through effective screening is needed to control the rapid spread of this virus Chest radiography imaging is an effective diagnosis tool for COVID-19 virus and followup Here, a novel hybrid multimodal deep learning system for identifying COVID-19 virus in chest X-ray (CX-R) images is developed and termed as the COVID-DeepNet system to aid expert radiologists in rapid and accurate image interpretation First, Contrast-Limited Adaptive Histogram Equalization (CLAHE) and Butterworth bandpass filter were applied to enhance the contrast and eliminate the noise in CX-R images, respectively Results from two different deep learning approaches based on the incorporation of a deep belief network and a convolutional deep belief network trained from scratch using a large-scale dataset were then fused Parallel architecture, which provides radiologists a high degree of confidence to distinguish healthy and COVID-19 infected people, was considered The proposed COVID-DeepNet system can correctly and accurately diagnose patients with COVID-19 with a detection accuracy rate of 99 93%, sensitivity of 99 90%, specificity of 100%, precision of 100%, F1-score of 99 93%, MSE of 0 021%, and RMSE of 0 016% in a large-scale dataset This system shows efficiency and accuracy and can be used in a real clinical center for the early diagnosis of COVID-19 virus and treatment follow-up with less than 3 s per image to make the final decision

/pdf/covid-deepnet-hybrid-multimodal-deep-learning-system-for-3wf9um4po2.pdf

COVID-DeepNet: Hybrid Multimodal Deep Learning System for Improving COVID-19 Pneumonia Detection in Chest X-ray Images

We are concerned with the challenge of coronavirus disease (COVID-19) detection in chestX-ray and Computed Tomography (CT) scans, and the classification and segmentation of relatedinfection manifestations. Even though it is arguably not an established diagnostic tool, using machinelearning-based analysis of COVID-19 medical scans has shown the potential to provide a preliminarydigital second opinion. This can help in managing the current pandemic, and thus has been attractingsignificant research attention. In this research, we propose a multi-task pipeline that takes advantageof the growing advances in deep neural network models. In the first stage, we fine-tuned anInception-v3 deep model for COVID-19 recognition using multi-modal learning, i.e., using X-ray andCT scans. In addition to outperforming other deep models on the same task in the recent literature,with an attained accuracy of 99.4%, we also present comparative analysis for multi-modal learningagainst learning from X-ray scans alone. The second and the third stages of the proposed pipelinecomplement one another in dealing with different types of infection manifestations. The formerfeatures a convolutional neural network architecture for recognizing three types of manifestations,while the latter transfers learning from another knowledge domain, namely, pulmonary nodulesegmentation in CT scans, to produce binary masks for segmenting the regions corresponding tothese manifestations. Our proposed pipeline also features specialized streams in which multiple deepmodels are trained separately to segment specific types of infection manifestations, and we show thesignificant impact that this framework has on various performance metrics. We evaluate theproposed models on widely adopted datasets, and we demonstrate an increase of approximately 4%and 7% for dice coefficient and mean intersection-over-union (mIoU), respectively, while achieving60% reduction in computational time, compared to the recent literature.

A multi-task pipeline with specialized streams for classification and segmentation of infection manifestations in COVID-19 scans

Image fusion can be performed on images either in spatial domain or frequency domain methods. Frequency domain methods will be most preferred because these methods can improve the quality of edges in an image. In image fusion, the resultant fused images will be more informative than individual input images, thus more suitable for classification problems. Artificial intelligence (AI) algorithms play a significant role in improving patient's treatment in the health care industry and thus improving personalized medicine. This research work analyses the role of image fusion in an improved brain tumour classification model, and this novel fusion-based cancer classification model can be used for personalized medicine more effectively. Image fusion can improve the quality of resultant images and thus improve the result of classifiers. Instead of using individual input images, the high-quality fused images will provide better classification results. Initially, the contrast limited adaptive histogram equalization technique preprocess input images such as MRI and SPECT images. Benign and malignant class brain tumor images are applied with discrete cosine transform-based fusion method to obtain fused images. AI algorithms such as support vector machine classifier, KNN classifier, and decision tree classifiers are tested with features obtained from fused images and compared with the result obtained from individual input images. Performances of classifiers are measured using the parameters accuracy, precision, recall, specificity, and F1 score. SVM classifier provided the maximum accuracy of 96.8%, precision of 95%, recall of 94%, specificity of 93%, F1 score of 91%, and performed better than KNN and decision tree classifiers when extracted features from fused images are used. The proposed method results are compared with existing methods and provide satisfactory results.

Investigating the Role of Image Fusion in Brain Tumor Classification Models Based on Machine Learning Algorithm for Personalized Medicine

Pneumonia is an infection that inflames the air sacs in one or both lungs. The air sacs may fill with fluid or pus, causing cough with phlegm or pus, fever, chills, and difficulty in breathing. Pneumonia can be caused by a variety of organisms such as bacteria, viruses, and fungi. Apart from causing difficulty in respiration, pneumonia can cause other complications such as bacteremia, lung abscess, and pleural effusion, among countless others. This paper presents a novel automated method for efficient and accurate pneumonia diagnosis from chest X-ray(CXR) images. Also, this model utilizes an efficient technique for noise reduction using bilateral filtering for edge preservation and optimum enhancement of the images using contrast-limited adaptive histogram equalization(CLAHE) to aid the detection of pneumonia clouds in the CXR images. The proposed model explores the benefits of deep residual learning along with separable convolution algorithm to achieve a classification accuracy of \(98.82\%\) and AUROC score of 0.99726 for diagnosing the disease. For cross-validation of the model, gradient-weighted class activation map(Grad-CAM) and saliency map visualization are used as a measure to verify the performance of the model along with localization of the affected regions in the CXR images.

A Novel Method for Pneumonia Diagnosis from Chest X-Ray Images Using Deep Residual Learning with Separable Convolutional Networks

Digital chest radiography offers many advantages over filmbased radiography, such as immediate image display, no film processing and room storage, wider dynamic range and lower radiation dose. In general, a raw X-ray image acquired directly from a digital flat detector contains poor quality of image, which may not be suitable for diagnosis and treatment planning. Therefore, a pre-processing technique is usually required to enhance image quality. This paper presents an improved image enhancement on digital chest radiography using the so-called N-CLAHE method, which is based on global and local enhancement. The proposed technique consists of two main steps. Firstly, intensity correction of the raw image is encountered by the log-normalization function which adjusts the intensity contrast of the image dynamically. Secondly, the Contrast Limited Adaptive Histogram Equalization (CLAHE) method is used for enhancing small details, textures and local contrast of the images. The proposed approach was tested using a radiographic survey phantom and a radiographic chest phantom and compared with conventional enhancement methods, such as histogram equalization, unsharp masking, CLAHE. The results show that the proposed N-CLAHE method yields great improvement on the pre-processing correction for digital chest radiography.

Kitti Koonsanit

Papers

Image enhancement on digital x-ray images using N-CLAHE