An explainable AI system for automated COVID-19 assessment and lesion categorization from CT-scans.

COVID-19 infection caused by SARS-CoV-2 pathogen has been a catastrophic pandemic outbreak all over the world, with exponential increasing of confirmed cases and, unfortunately, deaths. In this work we propose an AI-powered pipeline, based on the deep-learning paradigm, for automated COVID-19 detection and lesion categorization from CT scans. We first propose a new segmentation module aimed at automatically identifying lung parenchyma and lobes. Next, we combine the segmentation network with classification networks for COVID-19 identification and lesion categorization. We compare the model's classification results with those obtained by three expert radiologists on a dataset of 166 CT scans. Results showed a sensitivity of 90.3% and a specificity of 93.5% for COVID-19 detection, at least on par with those yielded by the expert radiologists, and an average lesion categorization accuracy of about 84%. Moreover, a significant role is played by prior lung and lobe segmentation, that allowed us to enhance classification performance by over 6 percent points. The interpretation of the trained AI models reveals that the most significant areas for supporting the decision on COVID-19 identification are consistent with the lesions clinically associated to the virus, i.e., crazy paving, consolidation and ground glass. This means that the artificial models are able to discriminate a positive patient from a negative one (both controls and patients with interstitial pneumonia tested negative to COVID) by evaluating the presence of those lesions into CT scans. Finally, the AI models are integrated into a user-friendly GUI to support AI explainability for radiologists, which is publicly available at http://perceivelab.com/covid-ai. The whole AI system is unique since, to the best of our knowledge, it is the first AI-based software, publicly available, that attempts to explain to radiologists what information is used by AI methods for making decisions and that proactively involves them in the decision loop to further improve the COVID-19 understanding.

Role of testosterone in SARS-CoV-2 infection: A key pathogenic factor and a biomarker for severe pneumonia.

OBJECTIVES: To investigate the association between sex hormones and the severity of coronavirus disease 2019 (COVID-19). Furthermore, associations between sex hormones and systemic inflammation markers, viral shedding and length of hospital stay were studied. DESIGN AND METHODS: This case-control study included a total of 48 male patients with COVID-19 admitted to an Italian reference hospital. The 24 cases were patients with PaO2/FiO2 <250 mmHg and who needed ventilatory support during hospitalization (severe COVID-19). The 24 controls were selected in a 1:1 ratio, matched by age, from patients who maintained PaO2/FiO2 >300 mmHg at all times and who may have required low-flow oxygen supplementation during hospitalization (mild COVID-19). For each group, sex hormones were evaluated on hospital admission. RESULTS: Patients with severe COVID-19 (cases) had a significantly lower testosterone level compared with patients with mild COVID-19 (controls). Median total testosterone (TT) was 1.4 ng/mL in cases and 3.5 ng/mL in controls (P = 0.005); median bioavailable testosterone (BioT) was 0.49 and 1.21 in cases and controls, respectively (P = 0.008); and median calculated free testosterone (cFT) was 0.029 ng/mL and 0.058 ng/mL in cases and controls, respectively (P = 0.015). Low TT, low cFT and low BioT were correlated with hyperinflammatory syndrome (P = 0.018, P = 0.048 and P = 0.020, respectively) and associated with longer length of hospital stay (P = 0.052, P = 0.041 and P = 0.023, respectively). No association was found between sex hormone level and duration of viral shedding, or between sex hormone level and mortality rate. CONCLUSIONS: A low level of testosterone was found to be a marker of clinical severity of COVID-19.

Spontaneous ilio-psoas haematomas (IPHs): a warning for COVID-19 inpatients.

INTRODUCTION: Critically ill patients with COVID-19 are at increased risk of developing a hypercoagulable state due to haemostatic changes directly related to the SARS-CoV-2 infection or to the consequence of the cytokine storm. Anticoagulation is now recommended to reduce the thrombotic risk. Ilio-psoas haematoma (IPH) is a potentially lethal condition that can arise during the hospitalization, especially in intensive care units (ICUs) and frequently reported as a complication of anticoagulation treatment. MATERIALS AND METHODS: We report a case series of seven subjects with SARS-CoV-2 pneumonia complicated by Ilio-psoas haematomas (IPHs) at our COVID-Hospital in Rome, Italy. RESULTS: Over the observation period, 925 subjects with confirmed SARS-CoV-2 infection were admitted to our COVID-hospital. Among them, we found seven spontaneous IPHs with an incidence of 7.6 cases per 1000 hospitalization. All the reported cases had a severe manifestation of COVID-19 pneumonia, with at least one comorbidity and 5/7 were on treatment with low weight molecular heparin for micro or macro pulmonary thrombosis. CONCLUSIONS: Given the indications to prescribe anticoagulant therapy in COVID-19 and the lack of solid evidences on the optimal dose and duration, it is important to be aware of the iliopsoas haematoma as a potentially serious complication in COVID-19 inpatients. KEY MESSAGE Critically ill patients with COVID-19 are at increased risk of hypercoagulability state and anticoagulation therapy is recommended. Ilio-psoas haematoma (IPH) is found to be a complication of anticoagulation regimen especially in severe COVID-19 cases. An incidence of 7.6 cases per 1000 admission of IPHs was reported. Hypoesthesia of the lower limbs, pain triggered by femoral rotation, hypovolaemia and anaemia are the most common symptoms and signs of IPHs that should alert physician.

Patient Access to an Online Portal for Outpatient Radiological Images and Reports: Two Years' Experience.

To assess the incidence of outpatient examinations delivered through a web portal in the Latium Region in 2 years and compare socio-demographic characteristics of these users compared to the total of examinations performed. All radiological exams (including MRI, X-ray and CT) performed from March 2017 to February 2019 were retrospectively analysed. For each exam, anonymized data of users who attended the exam were extracted and their characteristics were compared according to digital access to the reports. Overall, 9068 exams were performed in 6720 patients (55.8% males, median age 58 years, interquartile range (IQR) 46-70) of which 90.2% residents in Rome province, mainly attending a single radiological examination (77.3%). Among all exams, 446 (4.9%) were accessed, of which 190 (4.4%) in the first and 5.4% in the second year (p < 0.041). MRI was the type of exams mostly accessed (175, 7.0%). Being resident in the provinces of the Latium Region other than Rome was associated with a higher access rate (OR = 1.84, p = 0.001). Considering the overall costs sustained to implement a web portal which allows users a personal access to their own reports, if all users would have accessed/downloaded their exams, an overall users' and hospital savings up to €255,808.28 could have been determined. The use of a web portal could represent a consistent economical advantage for the user, the hospital and the environment. Even if increasing over time, the use of web portal is still limited and strategies to increase the use of such systems should be implemented.

2019-novel Coronavirus severe adult respiratory distress syndrome in two cases in Italy: An uncommon radiological presentation.

INTRODUCTION: Several recent case reports have described common early chest imaging findings of lung pathology caused by 2019 novel Coronavirus (SARS-COV2) which appear to be similar to those seen previously in SARS-CoV and MERS-CoV infected patients. OBJECTIVE: We present some remarkable imaging findings of the first two patients identified in Italy with COVID-19 infection travelling from Wuhan, China. The follow-up with chest X-Rays and CT scans was also included, showing a progressive adult respiratory distress syndrome (ARDS). RESULTS: Moderate to severe progression of the lung infiltrates, with increasing percentage of high-density infiltrates sustained by a bilateral and multi-segmental extension of lung opacities, were seen. During the follow-up, apart from pleural effusions, a tubular and enlarged appearance of pulmonary vessels with a sudden caliber reduction was seen, mainly found in the dichotomic tracts, where the center of a new insurgent pulmonary lesion was seen. It could be an early alert radiological sign to predict initial lung deterioration. Another uncommon element was the presence of mediastinal lymphadenopathy with short-axis oval nodes. CONCLUSIONS: Although only two patients have been studied, these findings are consistent with the radiological pattern described in literature. Finally, the pulmonary vessels enlargement in areas where new lung infiltrates develop in the follow-up CT scan, could describe an early predictor radiological sign of lung impairment.

Image quality and radiation dose reduction in chest CT in pulmonary infection.

PURPOSE: To evaluate the effect of dose reduction with iterative reconstruction (IR) on image quality of chest CT scan comparing two protocols. MATERIALS AND METHODS: Fifty-nine patients were enrolled. The two CT protocols were applied using Iterative Reconstruction (ASIR™) 40% but different noise indexes, recording dose-length product (DLP) and volume computed tomography dose index (CTDIvol). The subjective IQ was rated based on the distinction of anatomic details using a 4-point Likert scale based on the European Guidelines on Quality Criteria for CT. For each patient, two single CTs, at enrollment (group 1) and at follow-up after lowering the dose (group 2), were evaluated by two radiologists evaluating, for each examination, five different lung regions (central zone-CZ; peripheral zone-PZ; sub-pleural region-SPR; centrilobular region-CLR; and apical zone-AZ). An inter-observer agreement was expressed by weighted Cohen's kappa statistics (k) and intra-individual differences of subjective image analysis through visual grading characteristic (VGC) analysis. RESULTS: An average 50.4% reduction in CTDIvol and 51.5% reduction in DLP delivered were observed using the dose-reduced protocol. An agreement between observers evaluating group 1 CTs was perfect (100%) and moderate to good in group 2 examinations (k-Cohen ranging from 0.56 for PZ and AZ to 0.70 for SPR). In the VGC analysis, image quality ratings were significantly better for group 1 than group 2 scans for all regions (AUCVGC ranging from 0.56 for CZ to 0.62). However, disagreement was limited to a score 4 (excellent)-to-score 3 (good) IQ transition; apart from a single case in PZ, both the observers scored the IQ at follow-up as 2 (sufficient) starting from a score 4 (excellent). CONCLUSION: Dose reduction achieved in the follow-up CT scans, although a lower IQ still allows a good diagnostic confidence.

Central Nervous System involvement in tuberculosis: An MRI study considering differences between patients with and without Human Immunodeficiency Virus 1 infection.

BACKGROUND: Magnetic resonance imaging (MRI) is largely used in the diagnosis of central nervous system involvement of tuberculosis (CNSTB), yet there is no MRI comparison study between HIV+ and HIV- patients with CNSTB. The aim of the present study was to identify MRI differences in CNSTB between HIV+ and HIV- patients and possibly find early characteristics that could raise the suspect of this disease. METHODS: We included all patients admitted in our institution between 2011 and 2018 with confirmed diagnosis of CNSTB, and MRI performed in the first week. Patients with preexisting brain pathology or immunodeficiency not HIV related were excluded. We compared CNSTB MRI features between the two groups. RESULTS: Sixty-nine patients were included (19 HIV+; 50 HIV-). Findings in HIV+ group: 6 lung TB, 5 hydrocephalus, 4 meningeal enhancement, 6 stroke, 2 hemorrhages, and 10 tuberculomas. HIV- group: 22 lung tuberculosis, 15 hydrocephalus, 21 meningeal enhancement, 5 stroke, 4 hemorrhages, 20 tuberculomas. The only statistically significant difference between the two groups was in the stroke occurrence, more frequent in the HIV+ group (P=.028), all involving the basal ganglia. CONCLUSIONS: Stroke involving the basal ganglia best differentiates CNSTB patients who are HIV+ from those HIV-. This finding was not correlated with meningeal enhancement suggesting that small arteries involvement might precede it. Therefore, we think that HIV+ patients with a new onset of stroke should be evaluated for CNSTB. Follow-up MRI should also be planned since meningeal enhancement might appear in later stages of the disease.