SAUNet++: an automatic segmentation model of COVID-19 lesion from CT slices

The coronavirus disease 2019 (COVID-19) epidemic has spread worldwide and the healthcare system is in crisis. Accurate, automated and rapid segmentation of COVID-19 lesion in computed tomography (CT) images can help doctors diagnose and provide prognostic information. However, the variety of lesions and small regions of early lesion complicate their segmentation. To solve these problems, we propose a new SAUNet++ model with squeeze excitation residual (SER) module and atrous spatial pyramid pooling (ASPP) module. The SER module can assign more weights to more important channels and mitigate the problem of gradient disappearance;the ASPP module can obtain context information by atrous convolution using various sampling rates. In addition, the generalized dice loss (GDL) can reduce the correlation between lesion size and dice loss, and is introduced to solve the problem of small regions segmentation of COVID-19 lesion. We collected multinational CT scan data from China, Italy and Russia and conducted extensive comparative and ablation studies. The experimental results demonstrated that our method outperforms state-of-the-art models and can effectively improve the accuracy of COVID-19 lesion segmentation on the dice similarity coefficient (our: 87.38% vs. U-Net++: 84.25%), sensitivity (our: 93.28% vs. U-Net++: 89.85%) and Hausdorff distance (our: 19.99 mm vs. U-Net++: 26.79 mm), respectively.

Covid-19 imaging: A narrative review.

BACKGROUND: The 2019 novel coronavirus disease (COVID-19) imaging data is dispersed in numerous publications. A cohesive literature review is to be assembled. OBJECTIVE: To summarize the existing literature on Covid-19 pneumonia imaging including precautionary measures for radiology departments, Chest CT's role in diagnosis and management, imaging findings of Covid-19 patients including children and pregnant women, artificial intelligence applications and practical recommendations. METHODS: A systematic literature search of PubMed/med line electronic databases. RESULTS: The radiology department's staff is on the front line of the novel coronavirus outbreak. Strict adherence to precautionary measures is the main defense against infection's spread. Although nucleic acid testing is Covid-19's pneumonia diagnosis gold standard; kits shortage and low sensitivity led to the implementation of the highly sensitive chest computed tomography amidst initial diagnostic tools. Initial Covid-19 CT features comprise bilateral, peripheral or posterior, multilobar ground-glass opacities, predominantly in the lower lobes. Consolidations superimposed on ground-glass opacifications are found in few cases, preponderantly in the elderly. In later disease stages, GGO transformation into multifocal consolidations, thickened interlobular and intralobular lines, crazy paving, traction bronchiectasis, pleural thickening, and subpleural bands are reported. Standardized CT reporting is recommended to guide radiologists. While lung ultrasound, pulmonary MRI, and PET CT are not Covid-19 pneumonia's first-line investigative diagnostic modalities, their characteristic findings and clinical value are outlined. Artificial intelligence's role in strengthening available imaging tools is discussed. CONCLUSION: This review offers an exhaustive analysis of the current literature on imaging role and findings in COVID-19 pneumonia.

COVID-19 Detection using adopted convolutional neural networks and high-performance computing.

The COVID 19 pandemic is highly contagious disease is wreaking havoc on people's health and well-being around the world. Radiological imaging with chest radiography is one among the key screening procedure. This disease contaminates the respiratory system and impacts the alveoli, which are small air sacs in the lungs. Several artificial intelligence (AI)-based method to detect COVID-19 have been introduced. The recognition of disease patients using features and variation in chest radiography images was demonstrated using this model. In proposed paper presents a model, a deep convolutional neural network (CNN) with ResNet50 configuration, that really is freely-available and accessible to the common people for detecting this infection from chest radiography scans. The introduced model is capable of recognizing coronavirus diseases from CT scan images that identifies the real time condition of covid-19 patients. Furthermore, the database is capable of tracking detected patients and maintaining their database for increasing accuracy of the training model. The proposed model gives approximately 97% accuracy in determining the above-mentioned results related to covid-19 disease by employing the combination of adopted-CNN and ResNet50 algorithms.

Radiological Differences in COVID-19 Related Lung Manifestations Between Smokers and Non-smokers: A Single-Center Retrospective Study in Jordan.

Introduction Despite the fact that smoking has been identified as a risk factor for respiratory diseases and lung infections, the relationship between smoking and coronavirus severity remains ambiguous. It is believed that smoking is a risk factor for pulmonary infections. However, the effect of smoking on COVID-19 patients is still controversial. Objective The aim of the study was to identify and analyze the distinct radiological features in COVID-19 patients with different smoking statuses. Additionally, the study sought to examine the association between smoking and the severity of pulmonary changes. Methods A retrospective cohort study of 111 patients who were referred to Al-Salt/Hussein Hospital, Al-Salt, Jordan, from January to June 2021, with a confirmed COVID-19 diagnosis and smoking status recorded. Patients' demographics, medical history, age, gender, comorbidity, and length of hospitalization were obtained from their medical records. Results Study groups were similar in median age, prevalence of chosen chronic diseases, and median length of hospital stay. Based on the median scores of the radiological findings in each lung lobe, no statistically significant differences were found between the scores and smoking status (p-values of >0.05; Mann-Whitney test). Conclusion Smoking is an independent risk factor for the severity of COVID-19. Smoking has no noticeable impact on interstitial manifestation in COVID-19 patients.

Covid-19 or Viral Pneumonia Detection Using AI Tools

Viral pneumonia is a disease which occurs in lungs due to bacterial infection. Since middle of December 2019, many cases of pneumonia with unknown cause were found in Wuhan City, China;at present, it has been confirmed that it is a new respiratory disorder caused due to coronavirus infection. Lungs abnormality is highly risky condition in humans;the reduction of the risk is done by enabling quick and efficient treatment. The Covid-19 pneumonia is mimicking viral pneumonia, that is, their symptoms are undistinguished. Lung's abnormality is detected by Computed Tomography (CT) scan images or X-ray images. By viewing the X-rays or CT scan images, even for a well-trained radiologist, it is difficult to detect Covid-19/viral pneumonia. For quick and efficient treatment, it is necessary that proper detection must take place and during this epidemic situation, late detection can lead to doubling of cases;hence, there is a need of proper tool for quick detection of Covid-19/viral pneumonia. This chapter is discussing various AI tools for quick detection as a part of our contribution for quick detection and cure of Covid-19 to front line corona worriers and safety of viral pneumonia patients from Covid-19. The two AI tools are from deep learning (DL), that is, Convolutional Neural Networks (CNN) and Recurrent Neural Network (RNN), which are used for the detection of Covid-19/viral pneumonia. The algorithm is trained using available X-ray images of health lungs, viral pneumonia-affected lungs, and Covid-19-affected lungs available through Kaggle and nondisclosed local hospitals or Covid-19 wards. Also transfer learning method is also used for long-lasting validation of the model. The results give us an accuracy for CNN 83.2 to 94.1% results which are also matched with practically tested positive Covid-19 patients using swab tests by doctors. After testing the various models, we also came through that every model of DL has its own specialty. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

Study of Deep Learning Approaches for Diagnosing Covid-19 Disease using Chest CT Images

Since March 2020, the World Health Organization (WHO) has declared COVID-19 a pandemic. An evolving viral infection with respiratory tropism causes atypical pneumonia. Experts believe that detecting COVID-19 early stage is crucial. Early diagnosis and tracking techniques have become increasingly important to ensure an accelerated treatment process and avoid virus spread. Images from Computed Tomography (CT) scans can provide quick and precise COVID-19 screening. A subdivision of Machine Learning (ML) called Deep Learning (DL) can improve diagnostic accuracy and speed by automating screening via medical imaging in collaborative efforts with radiologists and physicians This study aims to investigate the recently popularized and extensively discussed deep learning algorithms for COVID-19 diagnosis in connection to the sequence phases involved in image processing. Getting rid of the noise in these images requires some preprocessing. Histogram equalization, fuzzy histogram equalisation, Adaptive Histogram Equalization (AHE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) are used to improve the image quality and therefore increase the identification of the image. Afterwards, necessary features for disease detection are segmented using various deep models like U-Net, U-Net + FPN (Feature Pyramid Network), COVID-SegNet and Dense GAN. Once these distinct deep characteristics have been identified, they are extracted using a variety of different deep models. Finally, an illness is diagnosed using popular models such as SVM, ResNet-50, AlexNet, VGG16, DenseNet, and SqueezeNet. The deep learning models with a better optimization algorithm to be effective in the diagnosis of COVID-19 and also obtain a reduced and efficient feature set for image classification and feature extraction. © 2023 IEEE.

Analysis of Malfunctions & Injuries Attributed to CT Scanners Before and After the Pandemic

Given the stresses placed on healthcare during the COVID-19 pandemic, and the critical role of computed tomography (CT) scanners in diagnosing cancers and other disorders, this project is designed to investigate the impact of the COVID-19 pandemic on reported malfunctions, injuries (and deaths) attributed to CT scans. Data were extracted from the Food and Drug Administration (FDA) Manufacturer and User Facility Device Experience (MAUDE) database. Yearly numbers of adverse event (AE) reports attributed to CT scanners including malfunctions, injuries, and deaths were recorded for the last 10 years (2012 to 2021). Monthly numbers of reports were also recorded for the 12 months immediately preceding the pandemic (2019/03 to 2020/03), as well as all the months after WHO declared COVID-19 a global pandemic (since 2020/03). It was found that the reported rates of injuries and malfunctions for CT scanners increased during the COVID-19 pandemic. The analysis also revealed unusual trends such as spikes in the malfunction rates from 2015 to 2018 compared to the preceding years, as well as in injuries and deaths. Manufacturers most responsible for these AE spikes included Philips, Superdimension, GE, Siemens, etc. The FDA Recall Database was further mined, and similar trends were identified in the yearly recalls over 2015- 2018, which correlated well with the malfunction rates (less apparent for injuries and deaths). While this project was originally centered around adverse pandemic-related effects on CT scanners, the important pre-pandemic findings warrant further research. These results might help prevent future AEs caused not only by CT scans but also by other medical devices. © 2022, Avestia Publishing. All rights reserved.

A Global Review of the Impacts of the Coronavirus (COVID-19) Pandemic on Radiology Practice, Finances, and Operations.

The Coronavirus Disease 2019 (COVID-19) pandemic ushered in rapid changes in healthcare, including radiology, globally. This review discusses the impact of the pandemic on various radiology departments globally. We analyze the implications of the COVID-19 pandemic on the imaging volumes, finances, and clinical operations of radiology departments in 2020. Studies from health systems and outpatient imaging centers were analyzed, and the activity throughout 2020 was compared to the pre-pandemic activity, including activity during similar timeframes in 2019. Imaging volumes across modalities, including MRI and CT scans, were compared, as were the Relative Value Units (RVUs) for imaging finances. Furthermore, we compared clinical operations, including staffing and sanitation procedures. We found that imaging volumes in private practices and academic centers decreased globally. The decreases in volume could be attributed to delayed patient screenings, as well as the implementation of protocols, such as the deep cleaning of equipment between patients. Revenues from imaging also decreased globally, with many institutions noting a substantial decline in RVUs and revenue compared with pre-COVID-19 levels. Our analysis thus found significant changes in the volumes, finances, and operations of radiology departments due to the COVID-19 pandemic.

Dual attention fusion UNet for COVID-19 lesion segmentation from CT images.

BACKGROUND: Chest CT scan is an effective way to detect and diagnose COVID-19 infection. However, features of COVID-19 infection in chest CT images are very complex and heterogeneous, which make segmentation of COVID-19 lesions from CT images quite challenging. OBJECTIVE: To overcome this challenge, this study proposes and tests an end-to-end deep learning method called dual attention fusion UNet (DAF-UNet). METHODS: The proposed DAF-UNet improves the typical UNet into an advanced architecture. The dense-connected convolution is adopted to replace the convolution operation. The mixture of average-pooling and max-pooling acts as the down-sampling in the encoder. Bridge-connected layers, including convolution, batch normalization, and leaky rectified linear unit (leaky ReLU) activation, serve as the skip connections between the encoder and decoder to bridge the semantic gap differences. A multiscale pyramid pooling module acts as the bottleneck to fit the features of COVID-19 lesion with complexity. Furthermore, dual attention feature (DAF) fusion containing channel and position attentions followed the improved UNet to learn the long-dependency contextual features of COVID-19 and further enhance the capacity of the proposed DAF-UNet. The proposed model is first pre-trained on the pseudo label dataset (generated by Inf-Net) containing many samples, then fine-tuned on the standard annotation dataset (provided by the Italian Society of Medical and Interventional Radiology) with high-quality but limited samples to improve performance of COVID-19 lesion segmentation on chest CT images. RESULTS: The Dice coefficient and Sensitivity are 0.778 and 0.798 respectively. The proposed DAF-UNet has higher scores than the popular models (Att-UNet, Dense-UNet, Inf-Net, COPLE-Net) tested using the same dataset as our model. CONCLUSION: The study demonstrates that the proposed DAF-UNet achieves superior performance for precisely segmenting COVID-19 lesions from chest CT scans compared with the state-of-the-art approaches. Thus, the DAF-UNet has promising potential for assisting COVID-19 disease screening and detection.

Longitudinal analyses using 18F-Fluorodeoxyglucose positron emission tomography with computed tomography as a measure of COVID-19 severity in the aged, young, and humanized ACE2 SARS-CoV-2 hamster models.

This study compared disease progression of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) in three different models of golden hamsters: aged (≈60 weeks old) wild-type (WT), young (6 weeks old) WT, and adult (14-22 weeks old) hamsters expressing the human-angiotensin-converting enzyme 2 (hACE2) receptor. After intranasal (IN) exposure to the SARS-CoV-2 Washington isolate (WA01/2020), 2-deoxy-2-[fluorine-18]fluoro-D-glucose positron emission tomography with computed tomography (18F-FDG PET/CT) was used to monitor disease progression in near real time and animals were euthanized at pre-determined time points to directly compare imaging findings with other disease parameters associated with coronavirus disease 2019 (COVID-19). Consistent with histopathology, 18F-FDG-PET/CT demonstrated that aged WT hamsters exposed to 105 plaque forming units (PFU) developed more severe and protracted pneumonia than young WT hamsters exposed to the same (or lower) dose or hACE2 hamsters exposed to a uniformly lethal dose of virus. Specifically, aged WT hamsters presented with a severe interstitial pneumonia through 8 d post-exposure (PE), while pulmonary regeneration was observed in young WT hamsters at that time. hACE2 hamsters exposed to 100 or 10 PFU virus presented with a minimal to mild hemorrhagic pneumonia but succumbed to SARS-CoV-2-related meningoencephalitis by 6 d PE, suggesting that this model might allow assessment of SARS-CoV-2 infection on the central nervous system (CNS). Our group is the first to use (18F-FDG) PET/CT to differentiate respiratory disease severity ranging from mild to severe in three COVID-19 hamster models. The non-invasive, serial measure of disease progression provided by PET/CT makes it a valuable tool for animal model characterization.

Automatic detection of Covid-19 based on lung CT images using Deep Convolutional Neural Networks (CNN)

In recent years, the COVID-19 pandemic has spread all over the world. Due to its rapid transmission, techniques that automatically detect COVID-19 infections and distinguish it from other forms of pneumonia are crucial. The scientific community has embarked on finding solutions to quick detection of COVID-19 through implementation of deep learning(DL) techniques that can diagnose COVID-19 using computed tomography (CT) lung scans. The use of CT images has been widely accepted in medical imaging and it is a pertinent screening tool due to its higher sensitivity in recognizing early pneumonic changes. Also, most developed DL models developed have been end-to-end from feature extraction to categorization of the COVID19 infected images. The proposed model results showed high accuracy rates on both training and testing of the model in COVID-19 classification. A customised ResNet-50 architecture has the best results in classifying the images and achieved state of art accuracy of 97% on training and testing using the COVID dataset with 200 epochs. This work presented a computationally efficient and highly accurate model for multi-class classification of normal and infected individuals. The model can help in effective early screening of COVID-19 cases hence reducing the burden on healthcare systems. © 2022 IEEE.

Analysis on Chest X-ray and Computed Tomography Images to Detect COVID-19 Based on Deep Learning Techniques

More than 6.3 million individuals have died as a result of the Corona Virus Disease 2019 (COVID-19), which spoiled many more human health globally. Since COVID-19 is a pandemic that is rapidly spreading, early discovery is essential to halting the infection's spread. Images of the lungs are utilised to identify coronavirus infection. For the identification of Corona Virus Disease, chest X-ray (CXR) and computed tomography (CT) images are available. Deep learning methods are proved to be effective and perform better in medical imaging applications. This study examines lung CT pictures, classifies and segments them, and uses the results to identify whether a patient tested is affected by COVID-19 or not using Deep learning techniques. The COVID detection performance of the deep learning architectures GG19, MobileNet, COVID-Net (PEPX), Squeez Net, U-Net, DarkNet and VGG16 are analysed - it was shown that U-Net combined VGG16 (acc98.89%) and VGG19 (acc-98.05%) performs the best, followed by MobileNet and QueezNet. © 2022 IEEE.

Automated quantification of COVID-19 pneumonia severity in chest CT using histogram-based multi-level thresholding segmentation

BackgroundChest computed tomography (CT) has proven its critical importance in detection, grading, and follow-up of lung affection in COVID-19 pneumonia. There is a close relationship between clinical severity and the extent of lung CT findings in this potentially fatal disease. The extent of lung lesions in CT is an important indicator of risk stratification in COVID-19 pneumonia patients. This study aims to explore automated histogram-based quantification of lung affection in COVID-19 pneumonia in volumetric computed tomography (CT) images in comparison to conventional semi-quantitative severity scoring. This retrospective study enrolled 153 patients with proven COVID-19 pneumonia. Based on the severity of clinical presentation, the patients were divided into three groups: mild, moderate and severe. Based upon the need for oxygenation support, two groups were identified as follows: common group that incorporated mild and moderate severity patients who did not need intubation, and severe illness group that included patients who were intubated. An automated multi-level thresholding histogram-based quantitative analysis technique was used for evaluation of lung affection in CT scans together with the conventional semi-quantitative severity scoring performed by two expert radiologists. The quantitative assessment included volumes, percentages and densities of ground-glass opacities (GGOs) and consolidation in both lungs. The results of the two evaluation methods were compared, and the quantification metrics were correlated.ResultsThe Spearman's correlation coefficient between the semi-quantitative severity scoring and automated quantification methods was 0.934 (p < 0.0001).ConclusionsThe automated histogram-based quantification of COVID-19 pneumonia shows good correlation with conventional severity scoring. The quantitative imaging metrics show high correlation with the clinical severity of the disease.

Using a 3D ResNet for Detecting the Presence and Severity of COVID-19 from CT Scans

Deep learning has been used to assist in the analysis of medical imaging. One use is the classification of Computed Tomography (CT) scans for detecting COVID-19 in subjects. This paper presents Cov3d, a three dimensional convolutional neural network for detecting the presence and severity of COVID-19 from chest CT scans. Trained on the COV19-CT-DB dataset with human expert annotations, it achieves a macro f1 score of 87.87 on the test set for the task of detecting the presence of COVID-19. This was the ‘runner-up' for this task in the ‘AI-enabled Medical Image Analysis Workshop and Covid-19 Diagnosis Competition' (MIA-COV19D). It achieved a macro f1 score of 46.00 for the task of classifying the severity of COVID-19 and was ranked in fourth place. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Automatic detection of novel corona virus (SARS-CoV-2) infection in computed tomography scan based on local adaptive thresholding and kernel-support vectors

The recent studies have indicated the requisite of computed tomography scan analysis by radiologists extensively to find out the suspected patients of SARS-CoV-2 (COVID-19). The existing deep learning methods distribute one or more of the subsequent bottlenecks. Therefore, a straight forward method for detecting COVID-19 infection using real-world computed tomography scans is presented. The detection process consists of image processing techniques such as segmentation of lung parenchyma and extraction of effective texture features. The kernel-based support vector machine is employed over feature vectors for classification. The performance parameters of the proposed method are calculated and compared with the existing methodology on the same dataset. The classification results are found outperforming and the method is less probabilistic which can be further exploited for developing more realistic detection system.

COVID-19 Related Lung Disease Detection and Classification USING a Deep Learning System

COVID-19 is one of the worst illnesses in history is a pandemic. The virus is known as SARS-COVID-2 because researchers have shown that it mostly affects the respiratory system and resembles the SARS variation. In some circumstances, it might cause pneumonia and a collapse of the respiratory system. To diagnose the patients' conditions and ascertain whether lung illness was involved, doctors used X-rays or Computed Tomography (CT) scans. In this study, pulmonary conditions associated with COVID-19 are identified and described using a deep learning method. To diagnose conditions including COV-19, lung cancer, and bacterial pneumonia, the suggested method makes use of CT scan pictures. A 2D picture from a CT scan offers more trustworthy results. The 50 layers of this method are organized into a ResNet-50 convolutional neural network (CNN). Comparing the experimental results to the current methods, a higher yield accuracy is predicted. © 2022 IEEE.

Computed tomography-based COVID-19 triage through a deep neural network using mask-weighted global average pooling.

Background: There is an urgent need to find an effective and accurate method for triaging coronavirus disease 2019 (COVID-19) patients from millions or billions of people. Therefore, this study aimed to develop a novel deep-learning approach for COVID-19 triage based on chest computed tomography (CT) images, including normal, pneumonia, and COVID-19 cases. Methods: A total of 2,809 chest CT scans (1,105 COVID-19, 854 normal, and 850 non-3COVID-19 pneumonia cases) were acquired for this study and classified into the training set (n = 2,329) and test set (n = 480). A U-net-based convolutional neural network was used for lung segmentation, and a mask-weighted global average pooling (GAP) method was proposed for the deep neural network to improve the performance of COVID-19 classification between COVID-19 and normal or common pneumonia cases. Results: The results for lung segmentation reached a dice value of 96.5% on 30 independent CT scans. The performance of the mask-weighted GAP method achieved the COVID-19 triage with a sensitivity of 96.5% and specificity of 87.8% using the testing dataset. The mask-weighted GAP method demonstrated 0.9% and 2% improvements in sensitivity and specificity, respectively, compared with the normal GAP. In addition, fusion images between the CT images and the highlighted area from the deep learning model using the Grad-CAM method, indicating the lesion region detected using the deep learning method, were drawn and could also be confirmed by radiologists. Conclusions: This study proposed a mask-weighted GAP-based deep learning method and obtained promising results for COVID-19 triage based on chest CT images. Furthermore, it can be considered a convenient tool to assist doctors in diagnosing COVID-19.

COVID-19 diagnosis utilizing wavelet-based contrastive learning with chest CT images.

The pandemic caused by the coronavirus disease 2019 (COVID-19) has continuously wreaked havoc on human health. Computer-aided diagnosis (CAD) system based on chest computed tomography (CT) has been a hotspot option for COVID-19 diagnosis. However, due to the high cost of data annotation in the medical field, it happens that the number of unannotated data is much larger than the annotated data. Meanwhile, having a highly accurate CAD system always requires a large amount of labeled data training. To solve this problem while meeting the needs, this paper presents an automated and accurate COVID-19 diagnosis system using few labeled CT images. The overall framework of this system is based on the self-supervised contrastive learning (SSCL). Based on the framework, our enhancement of our system can be summarized as follows. 1) We integrated a two-dimensional discrete wavelet transform with contrastive learning to fully use all the features from the images. 2) We use the recently proposed COVID-Net as the encoder, with a redesign to target the specificity of the task and learning efficiency. 3) A new pretraining strategy based on contrastive learning is applied for broader generalization ability. 4) An additional auxiliary task is exerted to promote performance during classification. The final experimental result of our system attained 93.55%, 91.59%, 96.92% and 94.18% for accuracy, recall, precision, and F1-score respectively. By comparing results with the existing schemes, we demonstrate the performance enhancement and superiority of our proposed system.

Grayscale Image Statistical Attributes Effectively Distinguish the Severity of Lung Abnormalities in CT Scan Slices of COVID-19 Patients.

Grayscale statistical attributes analysed for 513 extract images taken from pulmonary computed tomography (CT) scan slices of 57 individuals (49 confirmed COVID-19 positive; eight confirmed COVID-19 negative) are able to accurately predict a visual score (VS from 0 to 4) used by a clinician to assess the severity of lung abnormalities in the patients. Some of these attributes can be used graphically to distinguish useful but overlapping distributions for the VS classes. Using machine and deep learning (ML/DL) algorithms with twelve grayscale image attributes as inputs enables the VS classes to be accurately distinguished. A convolutional neural network achieves this with better than 96% accuracy (only 18 images misclassified out of 513) on a supervised learning basis. Analysis of confusion matrices enables the VS prediction performance of ML/DL algorithms to be explored in detail. Those matrices demonstrate that the best performing ML/DL algorithms successfully distinguish between VS classes 0 and 1, which clinicians cannot readily do with the naked eye. Just five image grayscale attributes can also be used to generate an algorithmically defined scoring system (AS) that can also graphically distinguish the degree of pulmonary impacts in the dataset evaluated. The AS classification illustrated involves less overlap between its classes than the VS system and could be exploited as an automated expert system. The best-performing ML/DL models are able to predict the AS classes with better than 99% accuracy using twelve grayscale attributes as inputs. The decision tree and random forest algorithms accomplish that distinction with just one classification error in the 513 images tested.

COVID-19 lung infection segmentation from chest CT images based on CAPA-ResUNet.

Coronavirus disease 2019 (COVID-19) epidemic has devastating effects on personal health around the world. It is significant to achieve accurate segmentation of pulmonary infection regions, which is an early indicator of disease. To solve this problem, a deep learning model, namely, the content-aware pre-activated residual UNet (CAPA-ResUNet), was proposed for segmenting COVID-19 lesions from CT slices. In this network, the pre-activated residual block was used for down-sampling to solve the problems of complex foreground and large fluctuations of distribution in datasets during training and to avoid gradient disappearance. The area loss function based on the false segmentation regions was proposed to solve the problem of fuzzy boundary of the lesion area. This model was evaluated by the public dataset (COVID-19 Lung CT Lesion Segmentation Challenge-2020) and compared its performance with those of classical models. Our method gains an advantage over other models in multiple metrics. Such as the Dice coefficient, specificity (Spe), and intersection over union (IoU), our CAPA-ResUNet obtained 0.775 points, 0.972 points, and 0.646 points, respectively. The Dice coefficient of our model was 2.51% higher than Content-aware residual UNet (CARes-UNet). The code is available at https://github.com/malu108/LungInfectionSeg.