Coronavirus covid-19 detection by means of explainable deep learning.

The coronavirus is caused by the infection of the SARS-CoV-2 virus: it represents a complex and new condition, considering that until the end of December 2019 this virus was totally unknown to the international scientific community. The clinical management of patients with the coronavirus disease has undergone an evolution over the months, thanks to the increasing knowledge of the virus, symptoms and efficacy of the various therapies. Currently, however, there is no specific therapy for SARS-CoV-2 virus, know also as Coronavirus disease 19, and treatment is based on the symptoms of the patient taking into account the overall clinical picture. Furthermore, the test to identify whether a patient is affected by the virus is generally performed on sputum and the result is generally available within a few hours or days. Researches previously found that the biomedical imaging analysis is able to show signs of pneumonia. For this reason in this paper, with the aim of providing a fully automatic and faster diagnosis, we design and implement a method adopting deep learning for the novel coronavirus disease detection, starting from computed tomography medical images. The proposed approach is aimed to detect whether a computed tomography medical images is related to an healthy patient, to a patient with a pulmonary disease or to a patient affected with Coronavirus disease 19. In case the patient is marked by the proposed method as affected by the Coronavirus disease 19, the areas symptomatic of the Coronavirus disease 19 infection are automatically highlighted in the computed tomography medical images. We perform an experimental analysis to empirically demonstrate the effectiveness of the proposed approach, by considering medical images belonging from different institutions, with an average time for Coronavirus disease 19 detection of approximately 8.9 s and an accuracy equal to 0.95.

Lactate dehydrogenase and PaO2/FiO2 ratio at admission helps to predict CT score in patients with COVID-19: An observational study.

INTRODUCTION: Since the beginning of the severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2) pandemic an important tool for patients with Coronavirus Disease 2019 (COVID-19) has been the computed tomography (CT) scan, but not always available in some settings The aim was to find a cut-off that can predict worsening in patients with COVID-19 assessed with a computed tomography (CT) scan and to find laboratory, clinical or demographic parameters that may correlate with a higher CT score. METHODS: We performed a multi-center, observational, retrospective study involving seventeen COVID-19 Units in southern Italy, including all 321 adult patients hospitalized with a diagnosis of COVID-19 who underwent at admission a CT evaluated using Pan score. RESULTS: Considering the clinical outcome and Pan score, the best cut-off point to discriminate a severe outcome was 12.5. High lactate dehydrogenase (LDH) serum value and low PaO2/FiO2 ratio (P/F) resulted independently associated with a high CT score. The Area Under Curve (AUC) analysis showed that the best cut-off point for LDH was 367.5 U/L and for P/F 164.5. Moreover, the patients with LDH> 367.5 U/L and P/F < 164.5 showed more frequently a severe CT score than those with LDH< 367.5 U/L and P/F> 164.5, 83.4%, vs 20%, respectively. CONCLUSIONS: A direct correlation was observed between CT score value and outcome of COVID-19, such as CT score and high LDH levels and low P/F ratio at admission. Clinical or laboratory tools that predict the outcome at admission to hospital are useful to avoiding the overload of hospital facilities.

Secondary Complications in COVID-19 Patients: A Case Series.

INTRODUCTION: Coronavirus SARS-CoV-2, the causative agent of COVID-19, primarily causes a respiratory tract infection that is not limited to respiratory distress syndrome, but it is also implicated in other body systems. Systemic complications were reported due to an exaggerated inflammatory response, which involves severe alveolar damage in the lungs and exacerbates the hypercoagulation that leads to venous thrombosis, ischemic attack, vascular dysfunction and infarction of visceral abdominal organs. Some complications are related to anticoagulant drugs that are administrated to stabilize hypercoagulability, but increase the risk of bleeding, hematoma and hemorrhage. The aim of this study is to report the diagnostic role of CT in the early diagnosis and management of patients with severe COVID-19 complications through the most interesting cases in our experience. MATERIAL AND METHODS: The retrospective analysis of patients studied for COVID-19 in our institution and hospitals, which are part of the university training network, was performed. CASES: Pneumomediastinum, cortical kidney necrosis, splenic infarction, cerebral ischemic stroke, thrombosis of the lower limb and hematomas are the most major complications that are reviewed in this study. CONCLUSIONS: Since the onset of the COVID-19 pandemic, the CT imaging modality with its high sensitivity and specificity remains the preferred imaging choice to diagnose early the different complications associated with COVID-19, such as thrombosis, ischemic stroke, infarction and pneumomediastinum, and their management, which significantly improved the outcomes.

Distinctive Role of the Systemic Inflammatory Profile in Non-Small-Cell Lung Cancer Younger and Elderly Patients Treated with a PD-1 Immune Checkpoint Blockade: A Real-World Retrospective Multi-Institutional Analysis.

An immune checkpoint blockade with mAbs to PD-1 and PD-L1 is an expanding therapeutic option for mNSCLC patients. This treatment strategy is based on the use of mAbs able to restore the anti-tumor activity of intratumoral T cells inhibited by PD-1 binding to PD-L1/2 on tumor and inflammatory cells. It has been speculated that a chronic status of systemic inflammation as well as the immunosenescence physiologically occurring in elderly patients may affect the efficacy of the treatment and the occurrence of irAEs. We performed a multi-institutional retrospective study aimed at evaluating the effects of these mAbs (nivolumab or atezolizumab) in 117 mNSCLC patients younger (90 cases) and older (27 cases) than 75 years in correlation with multiple inflammatory parameters (NLR, CRP, ESR, LDH and PCT). No differences were observed when the cohorts were compared in terms of the frequency of PFS, OS, inflammatory markers and immune-related adverse events (irAEs). Similarly, the occurrence of irAEs was strictly correlated with a prolonged OS survival in both groups. On the contrary, a negative correlation between the high baseline levels of inflammatory markers and OS could be demonstrated in the younger cohort only. Overall, PD-1/PD-L1-blocking mAbs were equally effective in young and elderly mNSCLC patients; however, the detrimental influence of a systemic inflammation at the baseline was only observed in young patients, suggesting different aging-related inflammation immunoregulative effects.

Renal involvement in COVID-19: focus on kidney transplant sector.

INTRODUCTION: Kidney transplant recipients and patients on the waiting list for kidney transplant who acquire SARS-CoV-2 infection are at serious risk of developing severe COVID-19, with an increased risk of mortality for the their immunosuppressive state; other risk factors for mortality have been identified in some comorbidities such as obesity, diabetes, asthma and chronic lung disease. MATERIALS AND METHODS: The COVID-19 pandemic has led to a sharp reduction in kidney transplants in most countries, mainly due to the concern of patients on the waiting list for their potential increased susceptibility to acquire SARS-CoV-2 infection in healthcare facilities and for the difficulties of transplant centers to ensure full activity as hospitals have had to focus most of their attention on COVID-19 patients. Indeed, while the infection curve continued its exponential rise, there was a vertical decline in kidney donation/transplant activity. CONCLUSION: This review article focuses on the damage induced by SARS-CoV-2 infection on kidney and on the adverse effect of this pandemic on the entire kidney transplant sector.

Evolution of CT Findings and Lung Residue in Patients with COVID-19 Pneumonia: Quantitative Analysis of the Disease with a Computer Automatic Tool.

PURPOSE: the purpose of this study was to assess the evolution of computed tomography (CT) findings and lung residue in patients with COVID-19 pneumonia, via quantified evaluation of the disease, using a computer aided tool. MATERIALS AND METHODS: we retrospectively evaluated 341 CT examinations of 140 patients (68 years of median age) infected with COVID-19 (confirmed by real-time reverse transcriptase polymerase chain reaction (RT-PCR)), who were hospitalized, and who received clinical and CT examinations. All CTs were evaluated by two expert radiologists, in consensus, at the same reading session, using a computer-aided tool for quantification of the pulmonary disease. The parameters obtained using the computer tool included the healthy residual parenchyma, ground glass opacity, consolidation, and total lung volume. RESULTS: statistically significant differences (p value ≤ 0.05) were found among quantified volumes of healthy residual parenchyma, ground glass opacity (GGO), consolidation, and total lung volume, considering different clinical conditions (stable, improved, and worsened). Statistically significant differences were found among quantified volumes for healthy residual parenchyma, GGO, and consolidation (p value ≤ 0.05) between dead patients and discharged patients. CT was not performed on cadavers; the death was an outcome, which was retrospectively included to differentiate findings of patients who survived vs. patients who died during hospitalization. Among discharged patients, complete disease resolutions on CT scans were observed in 62/129 patients with lung disease involvement ≤5%; lung disease involvement from 5% to 15% was found in 40/129 patients, while 27/129 patients had lung disease involvement between 16 and 30%. Moreover, 8-21 days (after hospital admission) was an "advanced period" with the most severe lung disease involvement. After the extent of involvement started to decrease-particularly after 21 days-the absorption was more obvious. CONCLUSIONS: a complete disease resolution on chest CT scans was observed in 48.1% of discharged patients using a computer-aided tool to quantify the GGO and consolidation volumes; after 16 days of hospital admission, the abnormalities identified by chest CT began to improve; in particular, the absorption was more obvious after 21 days.

Mood Disorder in Cancer Patients Undergoing Radiotherapy During the COVID-19 Outbreak.

Introduction: Novel coronavirus (COVID-19) is having a devastating psychological impact on patients, especially patients with cancer. This work aims to evaluate mood disorders of cancer patients undergoing radiation therapy during COVID-19 in comparison with cancer patients who underwent radiation therapy in 2019. Materials and Methods: We included all the patients undergoing radiation therapy at our department in two-time points (once a week for a month in May 2019) and during the COVID-19 outbreak (in April 2020). All the patients were asked to fulfill a validated questionnaire (STAI-Y1, State trait anxiety inventory scale), the Symptom Distress thermometer (SDT) (from 0 to 10 score), and the Beck Depression Inventory v.2 (BDI-2). We took into account the COVID-19 outbreak and also sex, age, week of radiation treatment, and disease. Results: We included 458 patients (220 males and 238 females), with a median age of 64 years. STAI-Y1 median score was 40 (mean 41,3, range 19-79), whereas the median score of SDT was five and BDI-2 median score was 11. STAI-Y1, SDT, and BDI-2 were significantly correlated with the COVID-19 outbreak (p < 0,001 for all the tests), sex (p: 0,016 for STAI-Y1, p < 0.001 for SDT, p:0.013 for BDI-2), week of treatment (p: 0.012 for STAI-Y1 and p: 0.031 for SDT), and disease (p:0.015 for STAI-Y1, p < 0.001 for SDT and p:0.020 for BDI-2). Conclusions: The prevalence of mood disorders in patients undergoing radiation therapy is higher than expected and even higher during the COVID-19 outbreak. These measurements could be useful as a baseline to start medical humanities programs to decrease these scores.

Covid-19 infection in cancer patients: the management in a diagnostic unit.

BACKGROUND: COVID-19 infection is particularly aggressive in frail patients, as cancer patients. Therefore, the more suitable management of the oncological patient requires a multidisciplinary assessment, to identify which patients should be treated, as inpatients or outpatients, and which treatments can be procrastinated. CONCLUSIONS: The role of radiologist is crucial, and, all cancer patients who need an imaging evaluation will need to be studied, using the most appropriate imaging tools related to the clinical question and paying a special attention to preserve public health. Guidelines are necessary in the correct organization of a radiology unit to manage patients with suspected or confirmed COVID-19 infection, and whenever possible, a satellite radiography center with dedicated equipment should be used to decrease the transmission risk.

Coronavirus Disease 2019 (COVID-19) in Italy: Double Reading of Chest CT Examination.

To assess the performance of the second reading of chest compute tomography (CT) examinations by expert radiologists in patients with discordance between the reverse transcription real-time fluorescence polymerase chain reaction (RT-PCR) test for COVID-19 viral pneumonia and the CT report. Three hundred and seventy-eight patients were included in this retrospective study (121 women and 257 men; 71 years median age, with a range of 29-93 years) and subjected to RT-PCR tests for suspicious COVID-19 infection. All patients were subjected to CT examination in order to evaluate the pulmonary disease involvement by COVID-19. CT images were reviewed first by two radiologists who identified COVID-19 typical CT patterns and then reanalyzed by another two radiologists using a CT structured report for COVID-19 diagnosis. Weighted к values were used to evaluate the inter-reader agreement. The median temporal window between RT-PCRs execution and CT scan was zero days with a range of (-9,11) days. The RT-PCR test was positive in 328/378 (86.8%). Discordance between RT-PCR and CT findings for viral pneumonia was revealed in 60 cases. The second reading changed the CT diagnosis in 16/60 (26.7%) cases contributing to an increase the concordance with the RT-PCR. Among these 60 cases, eight were false negative with positive RT-PCR, and 36 were false positive with negative RT-PCR. Sensitivity, specificity, positive predictive value and negative predictive value of CT were respectively of 97.3%, 53.8%, 89.0%, and 88.4%. Double reading of CT scans and expert second readers could increase the diagnostic confidence of radiological interpretation in COVID-19 patients.

COVID-19 pneumonia: computer-aided quantification of healthy lung parenchyma, emphysema, ground glass and consolidation on chest computed tomography (CT).

OBJECTIVE: To calculate by means of a computer-aided tool the volumes of healthy residual lung parenchyma, of emphysema, of ground glass opacity (GGO) and of consolidation on chest computed tomography (CT) in patients with suspected viral pneumonia by COVID-19. MATERIALS AND METHODS: This study included 116 patients that for suspected COVID-19 infection were subjected to the reverse transcription real-time fluorescence polymerase chain reaction (RT-PCR) test. A computer-aided tool was used to calculate on chest CT images healthy residual lung parenchyma, emphysema, GGO and consolidation volumes for both right and left lung. Expert radiologists, in consensus, assessed the CT images using a structured report and attributed a radiological severity score at the disease pulmonary involvement using a scale of five levels. Nonparametric test was performed to assess differences statistically significant among groups. RESULTS: GGO was the most represented feature in suspected CT by COVID-19 infection; it is present in 102/109 (93.6%) patients with a volume percentage value of 19.50% and a median value of 0.64 L, while the emphysema and consolidation volumes were low (0.01 L and 0.03 L, respectively). Among quantified volume, only GGO volume had a difference statistically significant between the group of patients with suspected versus non-suspected CT for COVID-19 (p < < 0.01). There were differences statistically significant among the groups based on radiological severity score in terms of healthy residual parenchyma volume, of GGO volume and of consolidations volume (p < < 0.001). CONCLUSION: We demonstrated that, using a computer-aided tool, the COVID-19 pneumonia was mirrored with a percentage median value of GGO of 19.50% and that only GGO volume had a difference significant between the patients with suspected or non-suspected CT for COVID-19 infection.

Coronavirus disease 2019 (COVID-19) in Italy: features on chest computed tomography using a structured report system.

To assess the use of a structured report in the Chest Computed Tomography (CT) reporting of patients with suspicious viral pneumonia by COVID-19 and the evaluation of the main CT patterns. This study included 134 patients (43 women and 91 men; 68.8 years of mean age, range 29-93 years) with suspicious COVID-19 viral infection evaluated by reverse transcription real-time fluorescence polymerase chain reaction (RT-PCR) test. All patients underwent CT examinations at the time of admission. CT images were reviewed by two radiologists who identified COVID-19 CT patterns using a structured reports. Temporal difference mean value between RT-PCRs and CT scan was 0.18 days ± 2.0 days. CT findings were positive for viral pneumonia in 94.0% patients while COVID-19 was diagnosed at RT-PCR in 77.6% patients. Time mean value to complete the structured report by radiologist was 8.5 min ± 2.4 min. The disease on chest CT predominantly affected multiple lobes and the main CT feature was ground glass opacity (GGO) with or without consolidation (96.8%). GGO was predominantly bilateral (89.3%), peripheral (80.3%), multifocal/patching (70.5%). Consolidation disease was predominantly bilateral (83.9%) with prevalent peripheral (87.1%) and segmental (47.3%) distribution. Additional CT signs were the crazy-paving pattern in 75.4% of patients, the septal thickening in 37.3% of patients, the air bronchogram sign in 39.7% and the "reversed halo" sign in 23.8%. Less frequent characteristics at CT regard discrete pulmonary nodules, increased trunk diameter of the pulmonary artery, pleural effusion and pericardium effusion (7.9%, 6.3%, 14.3% and 16.7%, respectively). Barotrauma sign was absent in all the patients. High percentage (54.8%) of the patients had mediastinal lymphadenopathy. Using a Chest CT structured report, with a standardized language, we identified that the cardinal hallmarks of COVID-19 infection were bilateral, peripheral and multifocal/patching GGO and bilateral consolidation with peripheral and segmental distribution.

Explainable Deep Learning for Pulmonary Disease and Coronavirus COVID-19 Detection from X-rays.

BACKGROUND AND OBJECTIVE: Coronavirus disease (COVID-19) is an infectious disease caused by a new virus never identified before in humans. This virus causes respiratory disease (for instance, flu) with symptoms such as cough, fever and, in severe cases, pneumonia. The test to detect the presence of this virus in humans is performed on sputum or blood samples and the outcome is generally available within a few hours or, at most, days. Analysing biomedical imaging the patient shows signs of pneumonia. In this paper, with the aim of providing a fully automatic and faster diagnosis, we propose the adoption of deep learning for COVID-19 detection from X-rays. METHOD: In particular, we propose an approach composed by three phases: the first one to detect if in a chest X-ray there is the presence of a pneumonia. The second one to discern between COVID-19 and pneumonia. The last step is aimed to localise the areas in the X-ray symptomatic of the COVID-19 presence. RESULTS AND CONCLUSION: Experimental analysis on 6,523 chest X-rays belonging to different institutions demonstrated the effectiveness of the proposed approach, with an average time for COVID-19 detection of approximately 2.5 seconds and an average accuracy equal to 0.97.

Coronavirus Disease 2019 (COVID-19) in Italy: Double reading of chest CT examination (preprint)

OBJECTIVETo assess the performance of the second reading of chest Compute Tomography (CT) examinations by expert radiologists in patients with discordance between the reverse transcription real-time fluorescence polymerase chain reaction (RT-PCR) test for COVID-19 viral pneumonia and the first CT report.MATERIALS AND METHODS.Three hundred seventy-heigth patients were included in this retrospective study (121 women and 257 men; 71 years of median age - range, 29–93 years) subjected to RT-PCR test for suspicious COVID-19 infection. All patients were subjected to CT examination in order to evaluate the pulmonary disease involvement by COVID-19. CT images were reviewed first by two radiologists who identified COVID-19 typical CT patterns and then reanalyzed by anoter two radiologists using a CT structured report for COVID-19 diagnosis.RESULTS.The median temporal window between RT-PCRs execution and CT scan was 0 days with a range of [-9, 11] days. RT-PCR test was resulted positive in 328/378 (86.8%). Discordance between RT-PCR and CT findings for viral pneumonia was revealed in 60 cases. The second reading changed the CT diagnosis in 16/60 (26.7%) cases contributing to increase the concordance with the RT-PCR. Among these 60 cases, 8 were false negative with positive RT-PCR, and 36 were false positive with negative RT-PCR. Sensitivity, specificity, positive predictive value and negative predictive value of CT were respectively of 97.3%, 53.8%, 89.0%, and 88.4%.CONCLUSION.Double reading of CT could increase the diagnostic confidence of radiological interpretation in COVID-19 patients. Using expert second readers could reduce the rate of discrepant cases between RT-PCR results and CT diagnosis for COVID-19 viral pneumonia.

Artificial intelligence to codify lung CT in Covid-19 patients.

The spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has already assumed pandemic proportions, affecting over 100 countries in few weeks. A global response is needed to prepare health systems worldwide. Covid-19 can be diagnosed both on chest X-ray and on computed tomography (CT). Asymptomatic patients may also have lung lesions on imaging. CT investigation in patients with suspicion Covid-19 pneumonia involves the use of the high-resolution technique (HRCT). Artificial intelligence (AI) software has been employed to facilitate CT diagnosis. AI software must be useful categorizing the disease into different severities, integrating the structured report, prepared according to subjective considerations, with quantitative, objective assessments of the extent of the lesions. In this communication, we present an example of a good tool for the radiologist (Thoracic VCAR software, GE Healthcare, Italy) in Covid-19 diagnosis (Pan et al. in Radiology, 2020. https://doi.org/10.1148/radiol.2020200370). Thoracic VCAR offers quantitative measurements of the lung involvement. Thoracic VCAR can generate a clear, fast and concise report that communicates vital medical information to referring physicians. In the post-processing phase, software, thanks to the help of a colorimetric map, recognizes the ground glass and differentiates it from consolidation and quantifies them as a percentage with respect to the healthy parenchyma. AI software therefore allows to accurately calculate the volume of each of these areas. Therefore, keeping in mind that CT has high diagnostic sensitivity in identifying lesions, but not specific for Covid-19 and similar to other infectious viral diseases, it is mandatory to have an AI software that expresses objective evaluations of the percentage of ventilated lung parenchyma compared to the affected one.

Coronavirus Disease 2019 (COVID-19) in Italy: features on Chest Computed Tomography using a structured report system (preprint)

OBJECTIVE. To assess the use of a structured report system in the Chest Computed Tomography (CT) reporting of patients with suspicious viral pneumonia by COVID-19 and the evaluation of the main CT patterns.MATERIALS AND METHODS. This study included 134 patients (43 women and 91 men; 68.8 years of mean age, range 29-93 years) with suspicious COVID-19 viral infection evaluated by reverse transcription real-time fluorescence polymerase chain reaction (RT-PCR) test. All patients underwent CT examinations at the time of admission. CT images were reviewed by two radiologists who identified COVID-19 CT patterns using a structured reports.RESULTS. Temporal difference mean value between RT-PCRs and CT scan was 0.18 days ±2.0 days. CT findings were positive for viral pneumonia in 94.0% patients while COVID-19 was diagnosed at RT-PCR in 77.6% patients. Mean value of time for radiologist to complete the structured report was 8.5 min±2.4 min. The disease on chest CT predominantly affected multiple lobes and the main CT feature was GGOs with or without consolidation (96.8%). GGOs was predominantly bilateral (89.3%), peripheral (80.3%), multifocal/patching (70.5%). Consolidation disease was predominantly bilateral (83.9%) with prevalent peripheral (87.1%) and segmental (47.3%) distribution. Additional CT signs were the crazy-paving pattern in 75.4% of patients, the septal thickening in 37.3% of patients, the air bronchogram sign in 39.7% and the “reversed halo” sign in 23.8%. Less frequent characteristics at CT regard discrete pulmonary nodules, increased trunk diameter of the pulmonary artery, pleural effusion and pericardium effusion (7.9%, 6.3%, 14.3% and 16.7%, respectively). Barotrauma sign was absent in all the patients. High percentage (54.8%) of the patients had mediastinal lymphadenopathy.CONCLUSION. Using a Chest CT structured report, with a standardized language, we identified that the cardinal hallmarks of COVID-19 infection were bilateral, peripheral and multifocal/patching ground-glass opacities and bilateral consolidations with peripheral and segmental distribution.