On the Use of Conventional Neural Networks for COVID-19 Detection in CT-Scan Images: A Comparative Study and Performance Analysis

This paper presents a comprehensive study on deep learning for COVID-19 detection using CT-scan images. The proposed study investigates several Conventional Neural Networks (CNN) architectures such as AlexNet, ZFNet, VGGNet, and ResNet, and thus proposed a hybrid methodology base on merging the relevant optimized architectures considered for detecting COVID-19 from CT-scan images. The proposed methods have been assessed on real datasets, and the experimental results conducted have shown the effectiveness of the proposed methods, allowing achieving a higher accuracy up to 99%. © 2022 IEEE.

Exploring the Capabilities of a Lightweight CNN Model in Accurately Identifying Renal Abnormalities: Cysts, Stones, and Tumors, Using LIME and SHAP

Kidney abnormality is one of the major concerns in modern society, and it affects millions of people around the world. To diagnose different abnormalities in human kidneys, a narrow-beam x-ray imaging procedure, computed tomography, is used, which creates cross-sectional slices of the kidneys. Several deep-learning models have been successfully applied to computer tomography images for classification and segmentation purposes. However, it has been difficult for clinicians to interpret the model's specific decisions and, thus, creating a "black box” system. Additionally, it has been difficult to integrate complex deep-learning models for internet-of-medical-things devices due to demanding training parameters and memory-resource cost. To overcome these issues, this study proposed (1) a lightweight customized convolutional neural network to detect kidney cysts, stones, and tumors and (2) understandable AI Shapely values based on the Shapley additive explanation and predictive results based on the local interpretable model-agnostic explanations to illustrate the deep-learning model. The proposed CNN model performed better than other state-of-the-art methods and obtained an accuracy of 99.52 ± 0.84% for K = 10-fold of stratified sampling. With improved results and better interpretive power, the proposed work provides clinicians with conclusive and understandable results.

CAE-UNet: An Effective Automatic Segmentation Model for CT Images of COVID-19

Since December 2019, COVID-19 has ravaged the world, severely affecting the quality of life and physical health of human society. Computed tomography (CT) imaging is an effective way to detect solid lung lesions as well as pulmonary ground-glass nodules and is an effective way to diagnose COVID-19. The automatic and accurate segmentation of COVID-19 lesion areas from CT images can determine the severity of the disease, which is essential for the diagnosis and treatment of COVID-19. A new model CAE-UNet(Combine-ASPP-ECA-UNet) is proposed in this paper for COVID-19 CT image segmentation based on UNet. The coding structure of UNet is replaced with the improved ResNet50 and incorporated with ECA attention module and atrous spatial pyramid pooling(ASPP). Fusing different sensory fields, global, local and spatial features to enhance the detail segmentation effect of the network. The experimental results on the CC-CCII show that the mIoU of the proposed CAE-UNet reaches 79.53%, which is better than some other mainstream methods. The proposed method achieves automatic and efficient segmentation of COVID-19 CT images. © 2022 IEEE.

A comparative analysis of chronic obstructive pulmonary disease using machine learning, and deep learning

Chronic obstructive pulmonary disease (COPD) is a general clinical issue in numerous countries considered the fifth reason for inability and the third reason for mortality on a global scale within 2021. From recent reviews, a deep convolutional neural network (CNN) is used in the primary analysis of the deadly COPD, which uses the computed tomography (CT) images procured from the deep learning tools. Detection and analysis of COPD using several image processing techniques, deep learning models, and machine learning models are notable contributions to this review. This research aims to cover the detailed findings on pulmonary diseases or lung diseases, their causes, and symptoms, which will help treat infections with high performance and a swift response. The articles selected have more than 80% accuracy and are tabulated and analyzed for sensitivity, specificity, and area under the curve (AUC) using different methodologies. This research focuses on the various tools and techniques used in COPD analysis and eventually provides an overview of COPD with coronavirus disease 2019 (COVID-19) symptoms.

CAE-UNet: An Effective Automatic Segmentation Model for CT Images of COVID-19

Since December 2019, COVID-19 has ravaged the world, severely affecting the quality of life and physical health of human society. Computed tomography (CT) imaging is an effective way to detect solid lung lesions as well as pulmonary ground-glass nodules and is an effective way to diagnose COVID-19. The automatic and accurate segmentation of COVID-19 lesion areas from CT images can determine the severity of the disease, which is essential for the diagnosis and treatment of COVID-19. A new model CAE-UNet(Combine-ASPP-ECA-UNet) is proposed in this paper for COVID-19 CT image segmentation based on UNet. The coding structure of UNet is replaced with the improved ResNet50 and incorporated with ECA attention module and atrous spatial pyramid pooling(ASPP). Fusing different sensory fields, global, local and spatial features to enhance the detail segmentation effect of the network. The experimental results on the CC-CCII show that the mIoU of the proposed CAE-UNet reaches 79.53%, which is better than some other mainstream methods. The proposed method achieves automatic and efficient segmentation of COVID-19 CT images. © 2022 IEEE.

Self-Supervised Contrastive Learning for Covid-19 Classification from Computed Tomography Images

Computer-aided diagnosis (CAD) emerges as an exhaustive diagnostic tool in the Covid-19 pandemic outbreak and is enormously investigated for automatic and more accurate detections. Artificial intelligence (AI) based radiographic images (Computed Tomography, X-Ray, Lung Ultrasound) interpretation improves the overall diagnosis efficiency of Covid-19 infections. In this paper, CAD based deep meta learning approach has been discussed for automatically quick analysis of chest computed tomography (CT) images regarding the early detection of corona virus (Covid-19) presence inside a subject. We incorporated a self-supervised contrastive-learning neural network for unbiased feature representation and classifications using fine-tuned pre-trained Inception module on 28203 chest CT images. This trainable multi-shot end-to-end deep learning architecture is validated on public dataset of normal and covid-19 CT images obtaining normalized accuracy of 0.9708. Results verify our model to be able enough to assist radiologists and specialists in screening and correct diagnosis of Covid-19 patients in less span of time. © 2022 IEEE.

A comparative analysis of chronic obstructive pulmonary disease using machine learning and deep learning

Chronic obstructive pulmonary disease (COPD) is a general clinical issue in numerous countries considered the fifth reason for inability and the third reason for mortality on a global scale within 2021. From recent reviews, a deep convolutional neural network (CNN) is used in the primary analysis of the deadly COPD, which uses the computed tomography (CT) images procured from the deep learning tools. Detection and analysis of COPD using several image processing techniques, deep learning models, and machine learning models are notable contributions to this review. This research aims to cover the detailed findings on pulmonary diseases or lung diseases, their causes, and symptoms, which will help treat infections with high performance and a swift response. The articles selected have more than 80% accuracy and are tabulated and analyzed for sensitivity, specificity, and area under the curve (AUC) using different methodologies. This research focuses on the various tools and techniques used in COPD analysis and eventually provides an overview of COPD with coronavirus disease 2019 (COVID-19) symptoms. © 2023 Institute of Advanced Engineering and Science. All rights reserved.

DEA-UNet: a dense-edge-attention UNet architecture for medical image segmentation

Classical UNet with an encoder and decoder structure and its variants perform very well in the field of medical image segmentation. They have a key similarity of a skip-connection, which combines deep, semantic, and coarse-grained feature maps from the decoder subnetwork with shallow, low-level, and fine-grained feature maps from the encoder subnetwork. We noted that, in many cases in medical image segmentation, the boundary of the segmentation target is fuzzy and complex. Traditional UNet cannot accurately segment these details. The main purpose is to solve the fuzzy boundary problem in medical image segmentation. To solve this problem, we combine the advantages of previous models and improve them and propose a new dense edge attention U-type network (DEA-UNet) for medical image segmentation. Starting from the traditional UNet, we modified the concat and skip-connection operations in the latter part. We designed an edge guidance module that fused the features of all layers. Starting from the upsample at the deepest layer, the reverse attention module was used step by step to extract features from high to low, and the edge guidance module was combined with it, so each layer could fully extract boundary details that were difficult to be noticed by previous models, thus solving the problem of the fuzzy boundary of the lesion region. We conducted experiments on two kinds of medical datasets (chest CT and colonoscopic polyp) and compared them with the traditional network. The experimental results showed that our DEA-UNet performed better in multiple indicators. In the segmentation of coronavirus disease-19 images, the results indicate that DEA-UNet has a Dice of 74.6%, sensitivity (Sen) of 70.8%, specificity (Spe) of 96.7%, structural measure (S-alpha) of 0.766%, enhanced-alignment measure (E-phi) of 0.910%, and mean absolute error (MAE) of 0.062%. Our DEA-UNET is 31%, 16%, 3%, and 0.7 and higher than the traditional medical segmentation model UNet, UNet++, the last model Few-shot UNet, and Inf-Net in Dice. In the segmentation of colonoscopic polyp dataset Kvasir, the results indicate that DEA-UNet has a Dice of 95%, structural measure (S-alpha) of 0.953%, enhanced-alignment measure (E-phi) of 0.974%, and MAE of 0.015%. Our DEA-UNet is 13%, 13%, 23%, and 5% higher than the traditional medical segmentation model UNet, UNet++, the last model SFA, and PraNet in Dice. In other evaluation metrics, our DEA-UNet also performed better. When designing DEA-UNet, we also consider the balance between model size and prediction accuracy. Experiments show that, by proper pruning, we can greatly reduce the number of model parameters while maintaining the accuracy of prediction results with little change. This proves that our DEA-UNET has great potential in the field of medical image segmentation.

Semi-Supervised Multi-Scale Dense Based Encoder-Decoder Architecture for Lung Computed Tomography Image Segmentation

Covid-19 pandemic continues to threat health of the global population, an efficient way to restrain the Covid-19 outbreak is timely screening suspected cases for quarantine and treatment. Despite of pathogenic laboratory testing is the gold standard to screen suspected cases, but it may obtain false negative results and consuming a lot of time. Computed tomography of chest can be an alternative diagnostic method to screen suspected cases that is based on radio graphical changes in lung area of Covid-19 confirmed case. Precisely delineate the lung area that is first and critical step for screening computed tomography image of chest by using deep learning method. In this paper, several related previous works will be introduced at first. Then, an improved encoder-decoder based segmentation framework is proposed, which is integrated with multi-scale densely connection-based convolution block and skip connection path. Moreover, in model training process, a semi-supervised manner is applied to train model which can reduce the demand of labeled training data. Finally, the proposed method is tested with a dataset of public X-ray image of chest. The experiment test proposed model in this paper with varieties of segmentation methods and result demonstrates promising performance of proposed model that against several other deep learning models. © 2022 SPIE

A Lightweight CNN Based on Transfer Learning for COVID-19 Diagnosis

The key to preventing the COVID-19 is to diagnose patients quickly and accurately. Studies have shown that using Convolutional Neural Networks (CNN) to analyze chest Computed Tomography (CT) images is helpful for timely COVID-19 diagnosis. However, personal privacy issues, public chest CT data sets are relatively few, which has limited CNN's application to COVID-19 diagnosis. Also, many CNNs have complex structures and massive parameters. Even if equipped with the dedicated Graphics Processing Unit (GPU) for acceleration, it still takes a long time, which is not conductive to widespread application. To solve above problems, this paper proposes a lightweight CNN classification model based on transfer learning. Use the lightweight CNN MobileNetV2 as the backbone of the model to solve the shortage of hardware resources and computing power. In order to alleviate the problem of model overfitting caused by insufficient data set, transfer learning is used to train the model. The study first exploits the weight parameters trained on the ImageNet database to initialize the MobileNetV2 network, and then retrain the model based on the CT image data set provided by Kaggle. Experimental results on a computer equipped only with the Central Processing Unit (CPU) show that it consumes only 1.06 s on average to diagnose a chest CT image. Compared to other lightweight models, the proposed model has a higher classification accuracy and reliability while having a lightweight architecture and few parameters, which can be easily applied to computers without GPU acceleration. Code:github.com/ZhouJie-520/paper-codes. © 2022 Tech Science Press. All rights reserved.

COVID-19 Lung CT Images Recognition: A Feature-Based Approach

The SARS-CoV-2 is quickly spreading worldwide resulting in millions of infection and death cases. As a consequence, it is increasingly important to diagnose the presence of COVID-19 infection regardless of the technique applied. To this end, this work deals with the problem of COVID-19 classification using Computed Tomography (CT) images. Precisely, a new feature-based approach is proposed by exploiting axial CT lung acquisitions in order to differentiate COVID-19 versus healthy Computed Tomography (CT) images. In particular, first-order statistical measures as well as numerical quantities extracted from the autocorrelation function are investigated with the aim to provide an efficient classification process ensuring satisfactory performance results. © 2021, Springer Nature Switzerland AG.

Fully automatic pipeline of convolutional neural networks and capsule networks to distinguish COVID-19 from community-acquired pneumonia via CT images.

BACKGROUND: Chest computed tomography (CT) is crucial in the diagnosis of coronavirus disease 2019 (COVID-19). However, the persistent pandemic and similar CT manifestations between COVID-19 and community-acquired pneumonia (CAP) raise methodological requirements. METHODS: A fully automatic pipeline of deep learning is proposed for distinguishing COVID-19 from CAP using CT images. Inspired by the diagnostic process of radiologists, the pipeline comprises four connected modules for lung segmentation, selection of slices with lesions, slice-level prediction, and patient-level prediction. The roles of the first and second modules and the effectiveness of the capsule network for slice-level prediction were investigated. A dataset of 326 CT scans was collected to train and test the pipeline. Another public dataset of 110 patients was used to evaluate the generalization capability. RESULTS: LinkNet exhibited the largest intersection over union (0.967) and Dice coefficient (0.983) for lung segmentation. For the selection of slices with lesions, the capsule network with the ResNet50 block achieved an accuracy of 92.5% and an area under the curve (AUC) of 0.933. The capsule network using the DenseNet121 block demonstrated better performance for slice-level prediction, with an accuracy of 97.1% and AUC of 0.992. For both datasets, the prediction accuracy of our pipeline was 100% at the patient level. CONCLUSIONS: The proposed fully automatic deep learning pipeline of deep learning can distinguish COVID-19 from CAP via CT images rapidly and accurately, thereby accelerating diagnosis and augmenting the performance of radiologists. This pipeline is convenient for use by radiologists and provides explainable predictions.

Classifying chest CT images as COVID-19 positive/negative using a convolutional neural network ensemble model and uniform experimental design method.

BACKGROUND: To classify chest computed tomography (CT) images as positive or negative for coronavirus disease 2019 (COVID-19) quickly and accurately, researchers attempted to develop effective models by using medical images. RESULTS: A convolutional neural network (CNN) ensemble model was developed for classifying chest CT images as positive or negative for COVID-19. To classify chest CT images acquired from COVID-19 patients, the proposed COVID19-CNN ensemble model combines the use of multiple trained CNN models with a majority voting strategy. The CNN models were trained to classify chest CT images by transfer learning from well-known pre-trained CNN models and by applying their algorithm hyperparameters as appropriate. The combination of algorithm hyperparameters for a pre-trained CNN model was determined by uniform experimental design. The chest CT images (405 from COVID-19 patients and 397 from healthy patients) used for training and performance testing of the COVID19-CNN ensemble model were obtained from an earlier study by Hu in 2020. Experiments showed that, the COVID19-CNN ensemble model achieved 96.7% accuracy in classifying CT images as COVID-19 positive or negative, which was superior to the accuracies obtained by the individual trained CNN models. Other performance measures (i.e., precision, recall, specificity, and F1-score) obtained bythe COVID19-CNN ensemble model were higher than those obtained by individual trained CNN models. CONCLUSIONS: The COVID19-CNN ensemble model had superior accuracy and excellent capability in classifying chest CT images as COVID-19 positive or negative.

An integrated feature frame work for automated segmentation of COVID-19 infection from lung CT images.

The novel coronavirus disease (SARS-CoV-2 or COVID-19) is spreading across the world and is affecting public health and the world economy. Artificial Intelligence (AI) can play a key role in enhancing COVID-19 detection. However, lung infection by COVID-19 is not quantifiable due to a lack of studies and the difficulty involved in the collection of large datasets. Segmentation is a preferred technique to quantify and contour the COVID-19 region on the lungs using computed tomography (CT) scan images. To address the dataset problem, we propose a deep neural network (DNN) model trained on a limited dataset where features are selected using a region-specific approach. Specifically, we apply the Zernike moment (ZM) and gray level co-occurrence matrix (GLCM) to extract the unique shape and texture features. The feature vectors computed from these techniques enable segmentation that illustrates the severity of the COVID-19 infection. The proposed algorithm was compared with other existing state-of-the-art deep neural networks using the Radiopedia and COVID-19 CT Segmentation datasets presented specificity, sensitivity, sensitivity, mean absolute error (MAE), enhance-alignment measure (EMφ), and structure measure (S m) of 0.942, 0.701, 0.082, 0.867, and 0.783, respectively. The metrics demonstrate the performance of the model in quantifying the COVID-19 infection with limited datasets.