Covid-19 Chest CT Scan Image Classification Using LCKSVD and Frozen Sparse Coding

WHO (World Health Organization) classified COVID-19 (Corona virus Disease 2019) as a pandemic after a substantial number of individuals died from an illness. This virus has infected millions and continues to infect new victims every day. Traditional RT-PCR tests to identify COVID-19 are prohibitively expensive and time-consuming, thus researchers are turning to deep learning (DL)-based algorithms that utilize medical imagery such as computed tomography (CT) scans. This helps automate the scanning process. All areas of COVID-19 research targeted at halting the current epidemic are currently being conducted using deep learning. We looked at some of the newest DL-based models for detecting COVID-19 in CT lung images in this work. During our investigation, we gathered information on the many research resources that were accessible. This survey may serve as a starting point for a novice/beginner level researcher working on COVID-19 categorization. The COVID-19 and its rapid detection technique are described in full in this study. This is followed by a discussion of computed tomography (CT) and a review of deep learning and its different covid detection methods, such as RNN, CNNLSTM as well as DNN. Deep learning approaches have been used in several recent research on the identification of COVID-19 patients. To identify COVID-19, we reviewed the most recent DL approaches used in conjunction with CT scans. A DL system for disease detection during the COVID-19 epidemic is discussed in this study, as are many authors' methodologies and the relevance of their research efforts, as well as possible difficulties and future developments.

Controlling the spread of Coronavirus Disease 2019 (COVID-19) and reducing its impact on public health need prompt identification and treatment. To improve diagnostic accuracy, this study attempts to create and assess a Multi-Modality COVID-19 Diagnosis System that integrates X-ray, Electrocardiogram (ECG), and Computed Tomography (CT) images utilizing Convolutional Neural Network (CNN) algorithms. To increase the accuracy of COVID-19 diagnosis, the suggested system incorporates data from many imaging modalities in a novel way, including cardiac symptoms identified by ECG data. This approach has not been thoroughly studied in the literature to date. The system analyses CT, ECG, and X-ray images using CNN algorithms, including Visual Geometry Group 19 (VGG19) and Deep Convolutional Networks (DCNN). While ECG data helps detect related cardiac symptoms, CT and X-ray images offer precise insights into lung abnormalities indicative of COVID-19 pneumonia. Noise reduction and image smoothing are accomplished through the implementation of Gaussian filtering algorithms. After extracting characteristics suggestive of either bacterial or viral pneumonia, a deep neural network refines them for accurate COVID-19 identification. Python software is employed throughout the system's implementation. A thorough evaluation of the trained CNN model using separate datasets revealed an amazing 99.12% accuracy rate in COVID-19 detection from chest imaging data. The diagnostic accuracy of the suggested DCNN model was much higher than that of the current models, including Random Forest and Linear Ridge. The Multi-Modality COVID-19 Diagnosis System uses cutting-edge CNN algorithms to seamlessly combine ECG, X-ray, and CT imaging data to provide a highly accurate diagnosis tool. With the implementation of this approach, medical personnel could potentially be able to diagnose COVID-19 more quickly and accurately, which would improve the disease's treatment and control.

Pre-Hematopoietic Stem Cell Transplantation Lung Computed Tomography as an Alternative to the Pulmonary Function Test during the COVID-19 Pandemic

A UK-wide British Society of Thoracic Imaging COVID-19 imaging repository and database: design, rationale and implications for education and research

COVID-19 in Kidney Transplantation: Outcomes, Immunosuppression Management, and Operational Challenges.

A trial of pirfenidone in hospitalized adult patients with severe coronavirus disease 2019

Magnetic Resonance Imaging (MRI) provides a non-invasive manner to aid clinical diagnosis, while its limitation is the slow scanning speed. Recently, due to the high costs of health care and taking account of patient comfort, some methods such as Parallel MRI (pMRI) and compressed sensing MRI have been developed to reduce the MR scanning duration under the sampling process. It is almost unavoidable to accept some doses of X-rays in computed tomography (CT scans). If one could find a more efficient way to represent the required visual information, the tasks of image processing and medical imaging would become easier and less troublesome. In this paper, first, we used pMRI on complex double data of brain magnetic resonance image. pMRI significantly reduces the number of measurements in the Fourier domain because each coil only acquires a small fraction of the whole measurements. It is important to reconstruct the original MR image efficiently and precisely for better diagnosis. In this research, we proposed a new super resolution and deblurring algorithm with dictionary learning, based on assuming a local Sparse-Land model on image patches, serving as regularization, then we validated the proposed method by using another one called the adaptive selection of sub dictionaries- adaptive reweighted sparsity regularization. Visual comparison and significant difference in psnr calculation (0.8111db) and time complexity showed that the proposed method had much better results.

Neurologic Involvement in COVID-19: Radiologists’ Perspective

Purpose: Prove that Computed Tomography (CT) is a more effective diagnostic tool for diagnosing Coronavirus Disease 2019 (COVID-19) in comparison with Reverse Transcription Polymerase Chain Reaction (RT-PCR) due to its higher sensitivity. Methods and materials: A total of 200 cases that had records of chest CT scans and RT-PCR tests were collected from Palestinian governmental hospitals from September to November 2020. Results: CT indicated COVID-19 in 62.5% of sample population (125 of 200) whereas RT-PCR indicated COVID-19 in 37.5% (75 of 200) cases. A P-value of 0.028 signifies the existence of a relationship between gender and CT sensitivity. Conclusion: High resolution computed tomography (HRCT) of the chest is a more rapid, sensitive, and effective tool than the current gold standard (RT-PCR); therefore, should be considered a primary diagnostic method for COVID-19.

Objective To investigate the computed tomography (CT) features of the coronavirus disease 2019 (COVID-19) and the clinical significance, so as to improve our understanding of CT imaging of this disease. Methods The chest CT features of seven COVID-19 patients, who were diagnosed by virus nucleic acid test from Jan. 25 to Feb. 15, 2020 in Changhai Hospital of Naval Medical University (Second Military Medical University), were analyzed retrospectively. There were six males and one female, aged (51.1±18.8) years (range 29-75 years). All the seven patients received chest CT plain scan examimation. The CT images were interpreted by two experienced senior radiologists, and the distribution, location and density of lesions, number of involved lobes, air bronchogram, mediastinal lymphadenopathy and pleural effusion were analyzed. Results The average time from onset of symptoms to CT examination was 3.6 d (range 1-9 d) in the seven COVID-19 patients. The lesions were distributed in single lung in one case and bilateral lungs in six cases. The lesions involved middle and lateral fields of lungs in five cases and the whole field of lungs in two cases. The lesions showed ground-glass opacity in four cases and mixed shadow in three cases. The lesions involved two or less lobes in four cases and five lobes in three cases. One case had air bronchogram. No mediastinal lymphadenopathy or pleural effusion were found. Conclusion COVID-19 patients have characteristic CT findings, which has important clinical significance for the diagnosis and treatment of COVID-19. However, the diagnosis should be confirmed based on the patient's epidemic history, clinical symptoms and laboratory indicators.

To the Editor: Chronic subdural hematomas (CSDHs) are encapsulated collections of blood breakdown products and fluid between the dura mater and the arachnoid.1 Their global incidence is estimated to be about 5/100 000/yr in patients younger than 65 yr,2 increasing to 58/100 000/yr in patients over 65 yr.1 Surgery usually allows a good outcome even in elderly. The clinical outcome of CSDH is conditioned by comorbidities including pulmonary diseases. Nowadays, we are facing a new possible condition related to coronavirus disease 2019 (COVID-19) that could affect the outcome. The spread of this infection started in 2019, December 31st when China alerted WHO about cases of unusual amount of interstitial pneumonia (IP) in Wuhan. After 7 d, on January 7th, scientists announced they had identified a new virus named COVID-19 similar to SARS-CoV. Italy is dealing with pandemic spread of COVID-19. As a matter of fact, on 19th March, it became the country with the highest number of confirmed deaths in the world. On March 23rd 2020 Italy was the world's centre of the epidemic with 69.176 confirmed cases, 6.820 deaths, and 21.137 recoveries.3 Clinically COVID-19 could lead to a severe IP and acute respiratory distress syndrome (ARDS), especially in older patients with multiple comorbidities.4 No studies about surgery in COVID-19 patients have been reported so far. We aim to describe our surgical experience with CSDH in a COVID-19 neurosurgical center. We admitted 5 patients with CSDH to the Neurosurgical Department of Brescia University Hospital between February 21, 2020 (first COVID-19 case reported in Italy) and March 23, 2020. The patients were positive for COVID-19 real-time polymerase chain reaction obtained by nasopharyngeal swab.5,6 We gathered the following data for each patient: age and sex, Cumulative Illness Rating Scale,7 antithrombotic therapy and perioperative mortality (within 30 d). All the patients had signed a consent form approved by the Local Ethic Committee regarding the use of their clinical data. We compared the mortality rate of this new cohort with the data extracted from our pre-COVID-19 CSDH case series. All the patients underwent pre-operative chest X-Ray (CXR) or computed tomography (CT) and routine blood test. An anesthesiological evaluation was performed for each patient. We cohortized our neurosurgical ward to separate COVID-19 positive from negative cases. COVID-19 positive patients started anti-retroviral therapy with lopinavir/ritonavir and hydroxychloroquine. Daily arterial blood gas analysis and CXR were performed. Surgery or endovascular treatment were indicated when the CSDH was symptomatic (presence of focal neurological deficits or mental status changes) and the maximum thickness was greater than 1 cm (Figures 1-4). One case did not present severe neurological impairment and was treated conservatively (Figure 5). No preoperative respiratory impairment was observed.FIGURE 1.: A and B, Head CT scan, axial view: pre- and postoperative CDSH. C, CXR showing bilateral and diffuse IP.FIGURE 2.: A, Head CT scan, axial view: bilateral CSDH. B, CXR showing bilateral and diffuse IP. C and D, MMA embolization procedure.FIGURE 3.: A, Head CT scan, axial view: preoperative CSDH. B, Head CT scan, axial view: postoperative CSDH with signs of recent rebleeding. C, CXR showing bilateral and IP. D, Chest CT scan, axial view, showing ground glass opacity.FIGURE 4.: A, Head CT scan, axial view: preoperative left CSDH. B, Head CT scan, axial view: postoperative CSDH with signs of recent rebleeding. C, CXR showing bilateral IP.FIGURE 5.: A, Head CT scan, axial view: left CSDH. B, normal CXR.We treated all the CSDH patients under general anesthesia. Three patients were operated (2 through craniotomy and 1 with a burr hole). Endovascular occlusion of the middle meningeal artery (MMA) was performed in 1 case (Figure 2). In the surgical cases we placed a subdural drainage for 48 h. After its removal patients underwent a CT head scan (Figures 1, 3, and 4). Afterwards the patients started low-molecular-weight heparin at prophylactic dose before mobilization. The cases are reported in the supplementary material section (Supplemental Digital Content). CSDHs mostly occur in elderly, with an average age of 63.1 Head trauma is the major risk factor, identified in less than 50% (often minor head trauma).8 Other risk factors are described like alcohol abuse, seizures, CSF shunts and coagulopathies, including therapeutic anticoagulation. CSDHs are bilateral in 20% to 25% of cases.9 At present there is no scientific experience regarding surgical outcome of COVID-19 patients. We compared the recent cohort of COVID-19 CSDH patients with our historical series. Between May 2018 and September 2019, we operated 142 patients for CSDH and we observe 5 death at our Institution. Our mortality rate was 3.7% according to the literature.10 In our recent experience, we observed 4 death in 5 COVID-19 patients suffering from CSDH. Therefore, we observed a mortality rate of 80% about 21,6 times greater than our control data. HEMATOLOGICAL DISORDERS We observed 2 cases of mild thrombocytopenia (Table). In these cases, we observed a re-bleeding (Figures 3 and 4) that led from a rapid neurological worsening to death within 5 d. This condition could be related to COVID-19 infection, as reported in literature.11 Independently from the hemorrhagic risk, Lippi et al12 showed that low platelet count is associated with increased risk of severe disease and mortality in patients with COVID-19, and this should serve as clinical indicator of worsening illness during hospitalization.12 In our series, we suppose that thrombocytopenia led to re-bleeding and was associated with poor outcome. TABLE. - Clinical Features of our Cohort Sex Age CIRS AT Side COVID-19 IP TP* Surgery Time to death(d) M 82 13 Yes Left + + No Burr-hole 14 M 86 18 No Bilateral + + No MMA embolization 10 M 77 20 No Right + + Yes Craniotomy 5 M 85 22 Yes Left + + Yes Burr-hole 5 M 78 19 Yes Left + – No NO Alive *TP (Thrombocytopenia): 100.000<PLTs<150.000All patients developed IP after surgery. Thrombocytopenia was observed in 2 cases (40%). The patients suffered rebleeding and showed a shorter time to death. CIRS (Cumulative Illness Rating Scale), AT (antithrombotic drugs), IP (Interstitial Pneumonia), COVID-19 (Coronavirus Disease 2019). INTERSTITIAL PNEUMONIA Dyspnoea and fatigue occurred in all our patients within 48 hours from surgery. CXR revealed severe IP (Figures 1-4). Ground glass opacity and bilateral patchy shadowing were observed on the chest CT (Figure 3).5,13 All our patients had COVID-19 infection without pre-operative respiratory symptoms. Immune system could be impaired following surgical procedures and this may have unmasked a subclinical infection.14,15 On the other hand no respiratory failure was observed in the conservative-treated case (Figure 5). In our experience IP occurred in all cases after treatment and worsened the outcome. This evenience represents a possible complication, often fatal, of COVID-19 infection.5 HEALTH EMERGENCY Nowadays, Italian health care system is the most afflicted in the pandemic scenario.16 The overload of the intensive care units in Lombardy, despite the efforts made, has necessarily influenced the resuscitation possibilities of elderly patients.17 Therefore, we cannot exclude that our results could be affected by the health emergency status. Seung et al. reported good bleeding control from CSDH membrane with MMA embolization, prevention of further growth of hematoma and even spontaneous resolution without surgery.18 Anyway our endovascular treated patient showed the same poor outcome of the surgical cases. Although statistical analysis of these preliminary data is not possible, COVID-19 patients appear to suffer from a negative surgical outcome. It is our belief that conservative treatment should be preferred whenever surgery could be postponed. Disclosures The authors have no personal, financial, or institutional interest in any of the drugs, materials, or devices described in this article.

Object: To evaluate CT Features on serial thin-section computed tomographic (CT) scans in patients with conventional Novel Coronavirus Pneumonia (COVID-19) for the period during which they remained hospitalized. Methods: In this Retrospective study, we collected clinical information including Laboratory investigations and more importantly we focused on collecting imaging data of these 15 selected patients (8 men and 7 women, 22 - 70 years old, average age (45 ± 15)) with COVID-19 disease. The mean time between the initial and repeat thin-section CT scans was 3.3 ± 2.1 days, 7.9 ± 2.1 days, 14.2 ± 1.3 days after onset of symptoms in these 15 patients. Three experienced Radiologists reviewed the CT images independently and also in collaboration with each other for complicated or unique cases, for the Imaging characteristics like number and site of lesions, distribution of lesions whether it is lobular, lobar, unilateral or bilateral, and comparing the severity of disease in relation to the CT findings. The CT features were compared using the χ2 test and Fisher’s exact probability. Results: All of 15 patients had a history of visit to the endemic center i.e. Wuhan city or came in direct contact with an infected individual. Fever (93.3%) was the most common symptom. Majority of patients had a normal white blood cell count, and normal lymphocyte count although there were patients with leucopenia and lymphocytopenia. CT images showed predominate Ground-Glass opacities in the initial and repeat CT scans with a percentage of 90.6%, 53.9%, 44.2% respectively during the three spaced CT examinations; most patients had bilateral lung involvement (60%, 93.3%, 93.3%), the lesions predominantly involved the posterior (87.5%, 71.9%, 76.6%) and peripheral (90.6%, 84.3%, 85.7%) part of the lungs. There were more consolidation and mixed patterns in repeat CT scan Versus initial CT scan, the difference was statistically significant (P-values were ± 2.1 days) 63 (7.9 ± 2.1 days), and 57 (14.2 ± 1.3 days) respectively. The median percentage of pneumonia lesions of the whole lung volume in three times CT scan was 1.69% (4.59), 3.47% (5.46), 2.33% (4.75) respectively. Besides, “Tree-in-bud” sign, lung cavitation, and lymphadenopathy were absent. Conclusion: The Thin-slice Section CT Imaging features show uniquely different characteristics, each time the scans are taken. The most common findings in our study were bilateral multiple peripheral and mostly posterior ground-glass opacities (GGO), however the CT scan images that were taken in a timely manner to follow up demonstrated some remarkable changes, which undoubtedly play an important role in the diagnosis and management of the patient with COVID-19 disease.

Background:Early differentiation between emergency department (ED) patients with and without coronavirus disease 2019 (COVID-19) is very important. The diagnosis of COVID-19 depends on real-time reverse transcriptase polymerase chain reaction (RT-PCR). On imaging, computed tomography (CT) manifestations resemble those seen in viral pneumonias, with multifocal ground-glass opacities and consolidation in a peripheral distribution being the most common findings. Although these findings lack specificity for COVID-19 diagnosis on imaging grounds, CT could be used to provide objective assessment about the extension of the lung opacities, which could be used as an imaging surrogate for disease burden. We set out to investigate the diagnostic accuracy of chest CT scanning in detecting COVID-19 in a population with suspected COVID-19 patients.Materials and Methods:In this cross-sectional single-center study performed on 348 cases with clinical suspicion of COVID-19, all adult symptomatic ED patients had both a CT scan and a PCR upon arrival at. CT results were compared with PCR test (s) and diagnostic accuracy was calculated.Results:Between February 15, 2020, and June 30, 2020, 348 symptomatic patients were included. In total, 62.3% of patients had a positive PCR and 69.8% had a positive CT, resulting in a sensitivity of 94.2%, specificity of 76.7%, likelihood ratio (LR) of +2.94 and (LR) −0.18. The sensitivity of the CT tended to be higher in those with acute respiratory distress syndrome (100.0%, P = 0.017) and severe COVID-19 (98.5%, P = 0.027) than in patients with mild (82.5%, P = 0.047) and moderate COVID-19 (89.3%, P = 0.039). The diagnostic ability of chest CT was found to be high with 86.3% concordance between findings of CT and PCR. In 48 (13.7%) patients, discordant findings between CT and PCR were observed. In most cases, the CT scan was considered suspicious for COVID-19, while the PCR was negative (37/48, 77.0%). In the majority of these, the diagnosis at discharge was pulmonary infection (n = 26; 54.1%).Conclusion:The accuracy of chest CT in symptomatic COVID suspect patients is high, but when used as a single diagnostic test, CT cannot accurately diagnose or exclude COVID-19. Therefore, we recommend a combination of both CT and RT-PCR for future follow-up, management, and medical surveillance.

Medical image classification technology, preferably which is based on the deep learning, is not only a key auxiliary diagnosis and treatment method in clinical medicine but also an important direction of scientific research. With the intensification of social aging, the incidence of viral elderly pneumonia has been on the rise and needs dedication from the research community. Doctors rely on personal theories and experience to use traditional methods to check the computed tomography (CT) images of the lungs of elderly patients one by one, which is likely to cause diagnosis errors. The accuracy of the traditional method certainly meets the clinical needs, but it has higher requirements on the theory and experience of medical staff, and the classification efficiency is low. Constructing an accurate and fast auxiliary system can effectively save medical resources. In response to the above problems, we have proposed a viral pneumonia diagnosis method for lung CT images, which is based on the convolutional neural networks. The main research work is carried out around the following aspects: First, in the lung CT image classification task, the traditional methods are inefficient and effective for doctors. The basic quality requirements of the model are high, or, in the model training, the effective training data are small, and so forth, causing problems such as model overfitting. A lung CT classification model based on the improved Inception-ResNet is proposed. In this model, first the overall architecture of the network model is designed, and then the Contrast-Limited Adaptive Histogram Equalization (CLAHE) algorithm is used to perform the same image enhancement processing on the dataset and data needed in this article, and then the pictures pass through three different network models. A binary classification study was carried out on viral pneumonia and normal lung images, and finally the accuracy, sensitivity, and specificity of the three models were compared. The experimental results show that the accuracy of the three models for the judgment of viral pneumonia is more than 95%. Among these, the model proposed in this article has better classification effect and fit, the highest accuracy rate, and less parameters and can be used for rapid screening of viral senile pneumonia. Objective. To complete the classification of lung CT images of the elderly with viral pneumonia based on the improved Inception-ResNet network architecture. Methods. (1) Find and study domestic and foreign medical literature, understand the diagnosis and treatment methods of viral pneumonia, and study lung CT imaging; compare the pattern classifications of deep learning in lung imaging at home and abroad, and further study the application of convolutional neural networks in the medical field application. (2) Study various models and technologies of convolutional neural networks, summarize them separately, and have in-depth understanding of convolutional neural networks, including architecture, methods, and related system frameworks, experimental environments, and so forth. Results. This paper proposes an optimized Inception-ResNet network architecture for image classification. The control experimental model uses two network models, GoogLeNet and ResNet, and selects the viral pneumonia dataset for training and testing. The experimental results are as follows: the sensitivity and specificity are superior to those in the other two models, which can be used for actual medical screening and diagnosis. Conclusion. The improved Inception-ResNet network model method in this paper performs better in terms of accuracy, sensitivity, and specificity. Every metric is higher than those in the ResNet model and the GoogLeNet model, improving the classification effect. In addition, it can be seen from the experimental results that the model used in this paper has a very good classification effect in the classification of new coronary pneumonia CT image data.

X-ray computed tomography (CT) imaging plays an essential role in disease diagnosis due to its noninvasive, painless mode and superior penetration depth. However, the resolution of the soft tissue ...