Lung Computed Tomography Scans Research Articles

Bronchiolite obliterante post-infettiva (PIBO), chi è costei?

The paper presents the case of a 14-month-old child with a persistent respiratory distress with wheezing and diffuse crackles on chest auscultation. Symptoms appeared after a viral pneumonia caused by Adenovirus. The recent history, the clinical manifestations and the lung CT (Computed Tomography) scans, which showed a diffuse mosaic pattern, with air trapping, bronchiectasis and peribronchial inflammation, led to the diagnosis of Post-infectious Bronchiolitis Obliterans (PIBO). PIBO is a rare chronic paediatric pulmonary disease characterized by irreversible fibrotic narrowing of the small airways. It can present with a broad severity spectrum, and the evolution of this condition is not predictable in the single patient. Adenovirus is by far the most common cause of this lung pathology, and during the post Covid-19 pandemic an unprecedented rise in PIBO cases triggered by Adenovirus lower respiratory infections was observed. The treatment of PIBO is empirical, and a defined protocol does not exist yet. Therapeutic approaches range from nil to methylprednisolone pulse therapy, which would seem effective especially if performed early and if peribronchitis is found on imaging. Some studies evaluated the administration of intravenous immunoglobulins, while in more advanced cases showing fibrotic transformation of the parenchyma, the use of antifibrotic drugs (hydroxychloroquine, nintedanib) may be tried

Pulmonary lesions in early response assessment in pediatric Hodgkin lymphoma: prevalence and possible implications for initial staging

BackgroundDisseminated pulmonary involvement in pediatric Hodgkin lymphoma (pHL) is indicative of Ann Arbor stage IV disease. During staging, it is necessary to assess for coexistence of non-malignant lung lesions due to infection representing background noise to avoid erroneously upstaging with therapy intensification.ObjectiveThis study attempts to describe new lung lesions detected on interim staging computed tomography (CT) scans after two cycles of vincristine, etoposide, prednisolone, doxorubicin in a prospective clinical trial. Based on the hypothesis that these new lung lesions are not part of the underlying malignancy but are epiphenomena, the aim is to analyze their size, number, and pattern to help distinguish true lung metastases from benign lung lesions on initial staging.Materials and methodsA retrospective analysis of the EuroNet-PHL-C1 trial re-evaluated the staging and interim lung CT scans of 1,300 pediatric patients with HL. Newly developed lung lesions during chemotherapy were classified according to the current Fleischner glossary of terms for thoracic imaging. Patients with new lung lesions found at early response assessment (ERA) were additionally assessed and compared to response seen in hilar and mediastinal lymph nodes.ResultsOf 1,300 patients at ERA, 119 (9.2%) had new pulmonary lesions not originally detectable at diagnosis. The phenomenon occurred regardless of initial lung involvement or whether a patient relapsed. In the latter group, new lung lesions on ERA regressed by the time of relapse staging. New lung lesions on ERA in patients without relapse were detected in 102 (7.8%) patients. Pulmonary nodules were recorded in 72 (5.5%) patients, the majority (97%) being<10 mm. Consolidations, ground-glass opacities, and parenchymal bands were less common.ConclusionNew nodules on interim staging are common, mostly measure less than 10 mm in diameter and usually require no further action because they are most likely non-malignant. Since it must be assumed that benign and malignant lung lesions coexist on initial staging, this benign background noise needs to be distinguished from lung metastases to avoid upstaging to stage IV disease. Raising the cut-off size for lung nodules to ≥ 10 mm might achieve the reduction of overtreatment but needs to be further evaluated with survival data. In contrast to the staging criteria of EuroNet-PHL-C1 and C2, our data suggest that the number of lesions present at initial staging may be less important.

Lifetime Attributable Breast Cancer Risk Related to Lung CT Scan in Women with Covid19

Abstract&#x0D; Purpose: Organ, effective dose, and Lifetime Attributable Risk (LAR) of breast cancer incidence related to lung Computed Tomography (CT) scans were evaluated. Seven hundred thirty-five female patients (20-50 years old) with Coronavirus (COVID-19) in four medical imaging centers in Tehran, Iran, were surveyed. Patients’ data, including age, sex, and exposure information (Kilovoltage (KVp), milliampere-second (mAs), pitch factor, Computed Tomography Dose Index (CTDIvol), and Dose Length Product (DLP)) were extracted from dose report pages in picture archiving and communication systems (PACS).&#x0D; Materials and Methods: Patients were divided into six age groups of 20-25, 25-30, 30-35, 35–40, 40-45, and 45–50 years. Breast, thyroid, lung, and heart absorbed doses, and also effective doses, were calculated by National Cancer Institute (NCICT) software, and LAR of breast cancer incidence has been evaluated by the Biological Effect of Ionizing Radiation (BEIR) VII in phase 2 report.&#x0D; Results: The average doses of breast, thyroid, lung, the heart were 3.97, 4.75, 4.10, and 3.37 mGy, respectively. Also, the average effective dose was 2.56 mSv. The average LAR of breast cancer in female patients was 7.45 per 100,000 exposures, decreasing dramatically with age. It was clear that exposure parameters and organ absorbed dose were significantly different between medical imaging centers (P value&lt;0.05).&#x0D; Conclusion: Although the CT scan is a useful instrument in the diagnosis of Corona disease, it should be suggested with caution due to the increased risk of breast cancer, especially in younger women and pediatrics. Also, low-dose CT scan protocols are recommended to minimize radiation effective and absorbed doses.

A Novel Air Trapping Segment Score Identifies Opposing Effects of Obesity and Eosinophilia on Air Trapping in Asthma.

Rationale: Density thresholds in computed tomography (CT) lung scans quantify air trapping (AT) at the whole-lung level but are not informative for AT in specific bronchopulmonary segments. Objectives: To apply a segment-based measure of AT in asthma to investigate the clinical determinants of AT in asthma. Methods: In each of 19 bronchopulmonary segments in CT lung scans from 199 patients with asthma, AT was categorized as present if lung attenuation was less than -856 Hounsfield units at expiration in ⩾15% of the lung area. The resulting AT segment score (0-19) was related to patient outcomes. Measurements and Main Results: AT varied at the lung segment level and tended to persist at the patient and lung segment levels over 3 years. Patients with widespread AT (⩾10 segments) had more severe asthma (P < 0.05). The mean (±SD) AT segment score in patients with a body mass index ⩾30 kg/m2 was lower than in patients with a body mass index <30 kg/m2 (3.5 ± 4.6 vs. 5.5 ± 6.3; P = 0.008), and the frequency of AT in lower lobe segments in obese patients was less than in upper and middle lobe segments (35% vs. 46%; P = 0.001). The AT segment score in patients with sputum eosinophils ⩾2% was higher than in patients without sputum eosinophilia (7.0 ± 6.1 vs. 3.3 ± 4.9; P < 0.0001). Lung segments with AT more frequently had airway mucus plugging than lung segments without AT (48% vs. 18%; P ⩽ 0.0001). Conclusions: In patients with asthma, air trapping is more severe in those with airway eosinophilia and mucus plugging, whereas those who are obese have less severe trapping because their lower lobe segments are spared.

Abnormalities of brain imaging in COVID-19 patients with neurological symptoms.

Background: Coronavirus disease 2019 (COVID-19) is a multisystem disease, manifested by several symptoms of various degrees. Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) can affect the central nervous system (CNS) through several mechanisms and brain imaging plays an essential role in the diagnosis and evaluation of the neurological involvement of COVID-19. Moreover, brain imaging of patients with COVID-19 would result in a better understanding of SARS-CoV-2 neuro-pathophysiology. In this study, we evaluated the brain imaging findings of patients with COVID-19 in Shohada-e Tajrish Hospital, Tehran, Iran. Methods: This was a single-center, retrospective, and observational study. The hospital records and chest and brain computed tomography (CT) scans of patients with confirmed COVID-19 were reviewed. Results: 161 patients were included in this study (39.1% women, mean age: 60.84). Thirteen patients (8%) had ischemic strokes identified by brain CT. Subdural hematoma, subdural effusion, and subarachnoid hemorrhage were confirmed in three patients. Furthermore, there were four cases of intracranial hemorrhage (ICH) and intraventricular hemorrhage (IVH). Patients with and without abnormal brain CTs had similar average ages. The rate of brain CT abnormalities in both genders did not differ significantly. Moreover, abnormal brain CT was not associated with increased death rate. There was no significant difference in lung involvement (according to lung CT scan) between the two groups. Conclusion: Our experience revealed a wide range of imaging findings in patients with COVID-19 and these findings were not associated with a more severe lung involvement or increased rate of mortality.

Pulmonary Invasive Fungal Disease: Ultrasound and Computed Tomography Scan Findings.

The importance of ultrasound in diagnosing pulmonary invasive fungal diseases (IFD) has yet to be assessed. Thus, this study aimed to evaluate the frequency of sonographic findings in patients suspected of an invasive pulmonary fungal infection. This prospective longitudinal study examined all patients with lung lesions in imaging modalities and suspected IFDs referred to Dr. Sheikh and Akbar pediatric hospitals from 2019 to 2022. Considered variables were the halo sign in the computed tomography (CT) scan; the target sign in the ultrasound and contrast-enhanced CT scan; the cavity; wedge-shaped consoli- dation; and pleuritis and extrapulmonary invasion to the chest wall or subdiaphragmatic invasion in both modalities. All patients who underwent lung CT scans and ultrasounds until the final diagnosis were followed up. The degree of agreement between ultrasound and CT scan findings and the sensitivity, specificity, and diagnostic accuracy of these signs were assessed. This study involved 40 patients with an average age of 7.16 ± 4.23 years. Acute leukemia was the commonest underlying dis- ease detected in 17 (42.5%) cases. The target sign in ultrasound (61.9%) and the halo sign in CT scan (71.4%) had the highest frequency among the variables in patients with IFD. Cohen's kappa coefficient agreement in both modalities was 0.5 for the cavity, with significant relation (P = .02). The Cohen's kappa was less than .17 for other findings (P > .05). The diagnostic criteria in the simultaneous examina- tion of the fungus target in ultrasound and halo in CT scan showed a sensitivity of 82.4% and specificity of 76.5%, respectively. Combining the characteristic findings of ultrasound and CT-scan provides a higher value in diagnosing pulmonary invasive fungal disease.

Investigating the Compatibility of Lung CT Scan Findings and Molecular Diagnosis Test of Patients With COVID-19 in Shahid Beheshti Hospital in Hamedan

Background: This study aimed to investigate the diagnostic value of computed tomography (CT) scan based on the results of reverse transcription polymerase chain reaction (RT-PCR) molecular diagnosis test in the diagnosis of COVID-19 diseases. Methods: In this study, 451 files related to hospitalized patients with initial diagnosis of COVID-19 were examined. Demographic information, symptoms, and results of both tests were extracted from the files. After collecting information by sampling method, the data were analyzed by SPSS software. In order to describe the data, mean and standard deviation statistics were used for qualitative data. Moreover, the Kappa test was used to measure the compatibility of the three methods. Results: The concordance rate of PCR and CT scan was calculated at 66%, of which 55.3% were positive, and 10.7% were negative. The results were obtained with an accuracy of 68.9%, a precision of 91.5%, a sensitivity of 69.1%, a specificity of 68%, and an F1-score of 95.10%. In general, based on the statistical criteria, the calculated percentage is an acceptable value. Conclusion: According to the appropriate matching percentage of CT scan and RT-PCR molecular diagnosis test, both techniques can be used as a diagnosis criterion according to the patient’s symptoms.

Angiopoietin-like 4 Is a Critical Regulator of Fibroblasts during Pulmonary Fibrosis Development.

Idiopathic pulmonary fibrosis (IPF) is a chronic, progressive, and irreversible interstitial pneumonia caused by the excessive production and deposition of extracellular matrix components, including type I collagen. Activated fibroblasts, called α-SMA (α-smooth muscle actin)-expressing myofibroblasts, are the major source of type I collagen in pulmonary fibrosis (PF), but the mechanisms underlying disease progression have not been fully elucidated. Here, we obtained lung fibroblasts from patients with IPF from both nonfibrotic and fibrotic areas as determined by a lung computed tomography scan and compared gene expression between these areas by DNA microarray. We found that ANGPTL4 (angiopoietin-like 4) was highly expressed only in fibroblasts from the fibrotic area. ANGPTL4 was selectively expressed in the fibroblastic area of IPF lungs, where the myofibroblast marker α-SMA was also expressed. ANGPTL4 also regulates the gene expression of fibrosis-related markers, cell migration, and proliferation. In addition, ANGPTL4 expression in a murine model of PF induced by treatment with bleomycin was significantly induced in the lungs from the acute to the chronic phase. Single-cell transcriptome analysis during the course of bleomycin-induced PF revealed that Angptl4 was predominantly expressed in the activated fibroblasts and myofibroblasts. Moreover, the administration of recombinant ANGPTL4 to the bleomycin-induced fibrosis model significantly increased collagen deposition and exacerbated the PF. In contrast, the pathogenesis of PF in Angptl4-deficient mice was improved. These results indicate that ANGPTL4 is critical for the progression of PF and might be an early diagnostic marker and therapeutic target for IPF.

Immunity due to COVID-19 vaccination and its correlation with lung involvement severity as an indicator of disease severity

Introduction: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic is a worldwide challenge; regarding the lack of an effective and efficient drug. It seems that the vaccine is the only modality to save the world from this pandemic. Objectives: This study was conducted to assess the effect of vaccination on preventing pulmonary involvement and the disease severity of COVID-19 patients. Patients and Methods: This descriptive-analytical study was conducted on 247 people with coronavirus disease 2019 infection. Demographic characteristics and vaccination status information were collected. Patients’ lung computed tomography scan findings were scored based on the pulmonary involvement percentage, and then according to this score, they were graded into severe, moderate, mild, and without lung involvement. The association between pulmonary involvement and vaccination status were evaluated by Fisher’s exact test and logistic regression. Results: Most participants were male, with a mean age of 53.74 ± 10.96 years. Most people (42.9%) were partial-vaccinated. Lungs in 53.3% were with lung involvement and in 46.6% were without. The correlation between pulmonary involvement and vaccination was significant (P&lt;0.001). Conclusion: Vaccination is an effective and efficient method in preventing coronavirus disease 2019 severity.

Assessment of lung injury severity using ultrasound in critically ill COVID-19 patients in resource limited settings

BackgroundLung ultrasound is a non-invasive tool available at the bedside for the assessment of critically ill patients. The objective of this study was to evaluate the usefulness of lung ultrasound in assessing the severity of SARS-CoV-2 infection in critically-ill patients in a low-income setting.MethodsWe conducted a 12-month observational study in a university hospital intensive care unit (ICU) in Mali, on patients admitted for COVID-19 as diagnosed by a positive polymerase chain reaction for SARS-CoV-2 and/or typical lung computed tomography scan findings.ResultsThe inclusion criteria was met by 156 patients with a median age of 59 years. Almost all patients (96%) had respiratory failure at admission and many needed respiratory support (121/156, 78%). The feasibility of lung ultrasound was very good, with 1802/1872 (96%) quadrants assessed. The reproducibility was good with an intra-class correlation coefficient of elementary patterns of 0.74 (95% CI 0.65, 0.82) and a coefficient of repeatability of lung ultrasound score < 3 for an overall score of 24. Confluent B lines were the most common lesions found in patients (155/156). The overall mean ultrasound score was 23 ± 5.4, and was significantly correlated with oxygen saturation (Pearson correlation coefficient of − 0.38, p < 0.001). More than half of the patients died (86/156, 55.1%). The factors associated with mortality, as shown by multivariable analysis, were: the patients’ age; number of organ failures; therapeutic anticoagulation, and lung ultrasound score.ConclusionLung ultrasound was feasible and contributed to characterize lung injury in critically-ill COVID-19 patients in a low income setting. Lung ultrasound score was associated with oxygenation impairment and mortality.

Quantitative analysis of lung parenchymal involvement in Behçet's disease by the novel automatic program

We aimed to quantitatively analyze lung parenchymal changes in Behçet's patients and to detect early parenchymal quantitative changes that occur in the absence of positive visual radiological findings. In our study, a total of 31 patients with Behçet's disease, 17 with positive radiological findings and 14 patients without positive radiological findings, and a control group of 33 individuals were evaluated. The automatic program determined lung volumes, lung densities, and opacity volume percentages by evaluating the contrast-enhanced lung computed tomography scans. The total lung volume was 3632.98± 1100.53 mL in the Behçet's disease patient group and 4925.70 ± 1098.88 mL in the control group, and there was a significant decrease in the total lung volume in Behçet's disease patients (P< 0.0001). The mean lung density was -723.73 ± 65.16 in the Behçet's disease patient group and -767.35 ± 41.17 in the control group, and there was a significant increase in the mean density in the Behçet's patients (P= 0.0023). A significantly higher correlation was observed between lung density and lung volume in Behçet's patients (P< 0.0001, r= -0.795). The lung volume of Behçet's disease patients with negative radiological findings was significantly lower than that of the control group (P= 0.0342). Lung volumetric changes in Behçet's disease patients are the quantitative data most affected by the disease. In addition, lung volume decreases in Behçet's patients who do not have visual parenchymal involvement.

The Effect of Short-term Methylprednisolone on Clinical Outcome and Lung CT Scan in Severe COVID-19: In-hospital and Six Weeks Later Follow-up

Background: The severe coronavirus disease 2019 (COVID-19) induces widespread inflammatory responses that are attempted to be managed by the administration of anti-inflammatory drugs, along with antiviral drugs and respiratory support. This clinical trial study investigated the effect of short-term and low-dose methylprednisolone on the clinical outcome and radiological improvement of admitted patients with severe COVID-19. Methods: In this randomized clinical trial, two strains of patients with severe pneumonia of COVID-19 were evaluated before and after the use of corticosteroids. Inclusion criteria were age over 18 years, definitive case of COVID-19 based on positive reverse transcription polymerase chain reaction (RT-PCR) for severe acute respiratory syndrome coronavirus 2 (SARS-COV-2), and arterial oxygen saturation (SaO2 )&lt;93%; furthermore, at least 7 days and 5 days should be passed since the onset of symptoms and antiviral treatment, respectively. Exclusion criteria were similar to contraindications to the administration of methylprednisolone for short-term injections and pregnancy. Patients received intravenous methylprednisolone succinate (1-1.75 mg/kg/day) for 5 days in addition to treatment based on the World Health Organization (WHO) approved protocol for COVID-19. Finally, demographic characteristics, dyspnea, peripheral oxygen saturation (SpO2), number of lymphocytes, and computed tomography (CT) scan of the patient’s chest before and after taking corticosteroids were evaluated. Results: The average oxygen saturation of patients increased significantly after taking methylprednisolone succinate (P&lt;0.001). Moreover, dyspnea and pulmonary insufficiency in CT scans improved significantly (P&lt;0.001), and among hematological parameters, only lymphocytes increased significantly (P=0.01). Furthermore, methylprednisolone succinate use had no effect on mortality and length of hospitalization. Conclusion: Methylprednisolone succinate use during the treatment period of COVID-19 improves clinical conditions, CT scan findings, and hematological parameters affected by inflammation, but it does not affect the mortality and length of hospitalization of patients.

Semantic context‐aware attention UNET for lung cancer segmentation and classification

AbstractLung cancer is a serious type of cancer, leading to increased mortality to death in both men and women as the symptoms are noticed only at later stages. Life span of individuals' may be extended if lung cancer is detected in its early stages. One of the imaging modalities used to diagnose lung cancer is computed tomography (CT). A nodule or mass is a small abnormal growth observed in a lung CT scan that, in most cases, may turn out to be benign. A computer‐aided system is essential to help physicians in precisely diagnosing the disease. The main objective of this work is to detect and classify the nodules in the lung CT scan images as benign or malignant. A context‐aware attention UNET architecture is proposed to segment the nodule from the lung CT scan image. Further, the segmented nodule is classified as benign or malignant using a Convolutional Neural Network architecture. The experiments are performed using the LUNA 16 and LIDC‐IDRI lung CT scan image datasets. From the results obtained, it is observed that the context‐aware attention UNET shows a noteworthy improvement in the following metrics: Dice Score, Sensitivity, Specificity, and F‐Measure. A significant improvement is obtained compared to the existing systems in detecting the lesion as a benign nodule or malignant nodule. Further, an ablation study is performed to validate the significance of each component in the architecture. The experimental results have reported 98.81% and 99.15% for specificity and sensitivity, respectively, and therefore the proposed system has potential clinical value in the detection of lung cancer.

Multi-Perspective Hierarchical Deep-Fusion Learning Framework for Lung Nodule Classification.

Lung cancer is the leading cancer type that causes mortality in both men and women. Computer-aided detection (CAD) and diagnosis systems can play a very important role for helping physicians with cancer treatments. This study proposes a hierarchical deep-fusion learning scheme in a CAD framework for the detection of nodules from computed tomography (CT) scans. In the proposed hierarchical approach, a decision is made at each level individually employing the decisions from the previous level. Further, individual decisions are computed for several perspectives of a volume of interest. This study explores three different approaches to obtain decisions in a hierarchical fashion. The first model utilizes raw images. The second model uses a single type of feature image having salient content. The last model employs multi-type feature images. All models learn the parameters by means of supervised learning. The proposed CAD frameworks are tested using lung CT scans from the LIDC/IDRI database. The experimental results showed that the proposed multi-perspective hierarchical fusion approach significantly improves the performance of the classification. The proposed hierarchical deep-fusion learning model achieved a sensitivity of 95% with only 0.4 fp/scan.

Quantitative Assessment and Comparative Analysis of Longitudinal Lung CT Scans of Chest-Irradiated Nonhuman Primates.

Computed tomography (CT) imaging has been used to diagnose radiation-induced lung injury for decades. However, histogram-based quantitative tools have rarely been applied to assess lung abnormality due to radiation-induced lung injury (RILI). Here, we used first-order summary statistics to derive and assess threshold measures extracted from whole lung histograms of CT radiodensity in rhesus macaques. For the present study, CT scans of animals exposed to 10 Gy of whole thorax irradiation were utilized from a previous study spanning 2-9 months postirradiation. These animals were grouped into survivors and non-survivors based on their clinical and experimental endpoints. We quantified the change in lung attenuation after irradiation relative to baseline using three density parameters; average lung density (ALD), percent change in hyper-dense lung volume (PCHV), hyperdense volume as a percent of total volume (PCHV/TV) at 2-month intervals and compared each parameter between the two irradiated groups (non-survivors and survivors). We also correlated our results with histological findings. All the three indices (ALD, PCHV, PCHV/TV) obtained from density histograms showed a significant increase in lung injury in non-survivors relative to survivors, with PCHV relatively more sensitive to detect early RILI changes. We observed a significant positive correlation between histologic pneumonitis scores and each of the three CT measurements, indicating that CT density is useful as a surrogate for histologic disease severity in RILI. CT-based three density parameters, ALD, PCHV, PCHV/TV, may serve as surrogates for likely histopathology patterns in future studies of RILI disease progression.

A mask-guided attention deep learning model for COVID-19 diagnosis based on an integrated CT scan images database

The global extent of COVID-19 mutations and the consequent depletion of hospital resources highlighted the necessity of effective computer-assisted medical diagnosis. COVID-19 detection mediated by deep learning models can help diagnose this highly contagious disease and lower infectivity and mortality rates. Computed tomography (CT) is the preferred imaging modality for building automatic COVID-19 screening and diagnosis models. It is well-known that the training set size significantly impacts the performance and generalization of deep learning models. However, accessing a large dataset of CT scan images from an emerging disease like COVID-19 is challenging. Therefore, data efficiency becomes a significant factor in choosing a learning model. To this end, we present a multi-task learning approach, namely, a mask-guided attention (MGA) classifier, to improve the generalization and data efficiency of COVID-19 classification on lung CT scan images. The novelty of this method is compensating for the scarcity of data by employing more supervision with lesion masks, increasing the sensitivity of the model to COVID-19 manifestations, and helping both generalization and classification performance. Our proposed model achieves better overall performance than the single-task (without MGA module) baseline and state-of-the-art models, as measured by various popular metrics.

PAM-DenseNet: A Deep Convolutional Neural Network for Computer-Aided COVID-19 Diagnosis.

Currently, several convolutional neural network (CNN)-based methods have been proposed for computer-aided COVID-19 diagnosis based on lung computed tomography (CT) scans. However, the lesions of pneumonia in CT scans have wide variations in appearances, sizes, and locations in the lung regions, and the manifestations of COVID-19 in CT scans are also similar to other types of viral pneumonia, which hinders the further improvement of CNN-based methods. Delineating infection regions manually is a solution to this issue, while excessive workload of physicians during the epidemic makes it difficult for manual delineation. In this article, we propose a CNN called dense connectivity network with parallel attention module (PAM-DenseNet), which can perform well on coarse labels without manually delineated infection regions. The parallel attention module automatically learns to strengthen informative features from both channelwise and spatialwise simultaneously, which can make the network pay more attention to the infection regions without any manual delineation. The dense connectivity structure performs feature maps reuse by introducing direct connections from previous layers to all subsequent layers, which can extract representative features from fewer CT slices. The proposed network is first trained on 3530 lung CT slices selected from 382 COVID-19 lung CT scans, 372 lung CT scans infected by other pneumonia, and 200 normal lung CT scans to obtain a pretrained model for slicewise prediction. We then apply this pretrained model to a CT scans dataset containing 94 COVID-19 CT scans, 93 other pneumonia CT scans, and 93 normal lung scans, and achieve patientwise prediction through a voting mechanism. The experimental results show that the proposed network achieves promising results with an accuracy of 94.29%, a precision of 93.75%, a sensitivity of 95.74%, and a specificity of 96.77%, which is comparable to the methods that are based on manually delineated infection regions.

Point-of-care Lung Ultrasound, Lung CT and NEWS to Predict Adverse Outcomes and Mortality in COVID-19 Associated Pneumonia.

Introduction: The appraisal of disease severity and prediction of adverse outcomes using risk stratification tools at early disease stages is crucial to diminish mortality from coronavirus disease 2019 (COVID-19). While lung ultrasound (LUS) as an imaging technique for the diagnosis of lung diseases has recently gained a leading position, data demonstrating that it can predict adverse outcomes related to COVID-19 is scarce. The main aim of this study is therefore to assess the clinical significance of bedside LUS in COVID-19 patients who presented to the emergency department (ED). Methods: Patients with a confirmed diagnosis of SARS-CoV-2 pneumonia admitted to the ED of our hospital between March 2021 and May 2021 and who underwent a 12-zone LUS and a lung computed tomography scan were included prospectively. Logistic regression and Cox proportional hazard models were used to predict adverse events, which was our primary outcome. The secondary outcome was to discover the association of LUS score and computed tomography severity score (CT-SS) with the composite endpoints. Results: We assessed 234 patients [median age 59.0 (46.8-68.0) years; 59.4% M), including 38 (16.2%) in-hospital deaths for any cause related to COVID-19. Higher LUS score and CT-SS was found to be associated with ICU admission, intubation, and mortality. The LUS score predicted mortality risk within each stratum of NEWS. Pairwise analysis demonstrated that after adjusting a base prediction model with LUS score, significantly higher accuracy was observed in predicting both ICU admission (DBA -0.067, P = .011) and in-hospital mortality (DBA -0.086, P = .017). Conclusion: Lung ultrasound can be a practical prediction tool during the course of COVID-19 and can quantify pulmonary involvement in ED settings. It is a powerful predictor of ICU admission, intubation, and mortality and can be used as an alternative for chest computed tomography while monitoring COVID-19-related adverse outcomes.

McS-Net: Multi-class Siamese network for severity of COVID-19 infection classification from lung CT scan slices

Worldwide COVID-19 is a highly infectious and rapidly spreading disease in almost all age groups. The Computed Tomography (CT) scans of lungs are found to be accurate for the timely diagnosis of COVID-19 infection. In the proposed work, a deep learning-based P-shot N-ways Siamese network along with prototypical nearest neighbor classifiers is implemented for the classification of COVID-19 infection from lung CT scan slices. For this, a Siamese network with an identical sub-network (weight sharing) is used for image classification with a limited dataset for each class. The feature vectors are obtained from the pre-trained sub-networks having weight sharing. The performance of the proposed methodology is evaluated on the benchmark MosMed dataset having categories zero (healthy control) and numerous COVID-19 infections. The proposed methodology is evaluated on (a) chest CT scans provided by medical hospitals in Moscow, Russia for 1110 patients, and (b) case study of low-dose CT scans of 42 patients provided by Avtaran healthcare in India. The deep learning-based Siamese network (15-shot 5-ways) obtained an accuracy of 98.07%, the sensitivity of 95.66%, specificity of 98.83%, and F1-score of 95.10%. The proposed work outperforms the COVID-19 infection severity classification with limited scans availability for numerous infection categories.

Describing Pulmonary Nodules Using 3D Clustering

Introduction. Determining the tumor (nodule) characteristics in terms of the shape, location, and type is an essential step after nodule detection in medical images for selecting the appropriate clinical intervention by radiologists. Computer-aided detection (CAD) systems efficiently succeeded in the nodule detection by 2D processing of computed tomography (CT)-scan lung images; however, the nodule (tumor) description in more detail is still a big challenge that faces these systems.Materials and Methods. In this paper, the 3D clustering is carried out on volumetric CT-scan images containing the nodule and its structures to describe the nodule progress through the consecutive slices of the lung in CT images.Results. This paper combines algorithms to cluster and define nodule’s features in 3D visualization. Applying some 3D functions to the objects, clustered using the K-means technique of CT lung images, provides a 3D visual exploration of the nodule shape and location. This study mainly focuses on clustering in 3D to discover complex information for a case missed in the radiologist’s report. In addition, the 3D-Density-based spatial clustering of applications with noise (DBSCAN) method and another 3D application (plotly) have been applied to evaluate the proposed system in this work. The proposed method has discovered a complicated case in data and automatically provides information about the nodule types (spherical, juxta-pleural, and pleural-tail). The algorithm is validated on the standard data consisting of the lung computed tomography scans with nodules greater and less than 3mm in size.Discussion and Conclusions. Based on the proposed model, it is possible to cluster lung nodules in volumetric CT scan and determine a set of characteristics such as the shape, location and type.