Diagnostic Performance in Differentiating COVID-19 from Other Viral Pneumonias on CT Imaging: Multi-Reader Analysis Compared with an Artificial Intelligence-Based Model.

Growing evidence suggests that artificial intelligence tools could help radiologists in differentiating COVID-19 pneumonia from other types of viral (non-COVID-19) pneumonia. To test this hypothesis, an R-AI classifier capable of discriminating between COVID-19 and non-COVID-19 pneumonia was developed using CT chest scans of 1031 patients with positive swab for SARS-CoV-2 (n = 647) and other respiratory viruses (n = 384). The model was trained with 811 CT scans, while 220 CT scans (n = 151 COVID-19; n = 69 non-COVID-19) were used for independent validation. Four readers were enrolled to blindly evaluate the validation dataset using the CO-RADS score. A pandemic-like high suspicion scenario (CO-RADS 3 considered as COVID-19) and a low suspicion scenario (CO-RADS 3 considered as non-COVID-19) were simulated. Inter-reader agreement and performance metrics were calculated for human readers and R-AI classifier. The readers showed good agreement in assigning CO-RADS score (Gwet's AC2 = 0.71, p < 0.001). Considering human performance, accuracy = 78% and accuracy = 74% were obtained in the high and low suspicion scenarios, respectively, while the AI classifier achieved accuracy = 79% in distinguishing COVID-19 from non-COVID-19 pneumonia on the independent validation dataset. The R-AI classifier performance was equivalent or superior to human readers in all comparisons. Therefore, a R-AI classifier may support human readers in the difficult task of distinguishing COVID-19 from other types of viral pneumonia on CT imaging.

Correlation between lung ultrasound and chest CT patterns with estimation of pulmonary burden in COVID-19 patients.

PURPOSE: The capability of lung ultrasound (LUS) to distinguish the different pulmonary patterns of COVID-19 and quantify the disease burden compared to chest CT is still unclear. METHODS: PCR-confirmed COVID-19 patients who underwent both LUS and chest CT at the Emergency Department were retrospectively analysed. In both modalities, twelve peripheral lung zones were identified and given a Severity Score basing on main lesion pattern. On CT scans the well-aerated lung volume (%WALV) was visually estimated. Per-patient and per-zone assessments of LUS classification performance taking CT findings as reference were performed, further revisioning the images in case of discordant results. Correlations between number of disease-positive lung zones, Severity Score and %WALV on both LUS and CT were assessed. The area under receiver operating characteristic curve (AUC) was calculated to determine LUS performance in detecting %WALV ≤ 70 %. RESULTS: The study included 219 COVID-19 patients with abnormal chest CT. LUS correctly identified as positive 217 (99 %) patients, but per-zone analysis showed sensitivity = 75 % and specificity = 66 %. The revision of the 121 (55 %) cases with positive LUS and negative CT revealed COVID-compatible lesions in 42 (38 %) CT scans. Number of disease-positive zones, Severity Score and %WALV between LUS and CT showed moderate correlations. The AUCs for LUS Severity Score and number of LUS-positive zones did not differ in detecting %WALV ≤ 70 %. CONCLUSION: LUS in COVID-19 is valuable for case identification but shows only moderate correlation with CT findings as for lesion patterns and severity quantification. The number of disease-positive lung zones in LUS alone was sufficient to discriminate relevant disease burden.

Emergency CT for assessment and management of blunt traumatic splenic injuries at a Level 1 Trauma Center: 13-year study.

PURPOSE: To determine the relationship between multidetector computed tomography (MDCT) findings, management strategies, and ultimate clinical outcomes in patients with splenic injuries secondary to blunt trauma. MATERIALS AND METHODS: This Institutional Review Board-approved study collected 351 consecutive patients admitted at the Emergency Department (ED) of a Level I Trauma Center with blunt splenic trauma between October 2002 and November 2015. Their MDCT studies were retrospectively and independently reviewed by two radiologists to grade splenic injuries according to the American Association for the Surgery of Trauma (AAST) organ injury scale (OIS) and to detect intraparenchymal (type A) or extraparenchymal (type B) active bleeding and/or contained vascular injuries (CVI). Clinical data, information on management, and outcome were retrieved from the hospital database. Statistical analysis relied on Student's t, chi-squared, and Cohen's kappa tests. RESULTS: Emergency multiphase MDCT was obtained in 263 hemodynamically stable patients. Interobserver agreement for both AAST grading of injuries and vascular lesions was excellent (k = 0.77). Operative management (OM) was performed in 160 patients (45.58% of the whole cohort), and high-grade (IV and V) OIS injuries and type B bleeding were statistically significant (p < 0.05) predictors of OM. Nonoperative management (NOM) failed in 23 patients out of 191 (12.04%). In 75% of them, NOM failure occurred within 30 h from the trauma event, without significant increase of mortality. Both intraparenchymal and extraparenchymal active bleeding were predictive of NOM failure (p < 0.05). CONCLUSION: Providing detection and characterization of parenchymal and vascular traumatic lesions, MDCT plays a crucial role for safe and appropriate guidance of ED management of splenic traumas and contributes to the shift toward NOM in hemodynamically stable patients.

Detection of biliary and vascular anatomy in living liver donors: value of gadobenate dimeglumine enhanced MR and MDCT angiography.

OBJECTIVE: To evaluate the performance of magnetic resonance (MR) and multidetector computed tomography (MDCT) in the assessment of living donor's vascular and biliary anatomy, having surgical findings as reference standard. METHODS: Thirty-two living liver donors underwent MR cholangiography (1.5-T; standard cholangiography pulse sequences and delayed acquisitions after administration of biliary contrast agent) for biliary anatomy evaluation. MDCT (16-row multidetector scanner, multiphase protocol, 3mm slice thickness) was also performed in all cases for the assessment of vascular anatomy before transplantation. Hepatic veins (<4mm in diameter) were not considered. MR and MDCT images interpretation was performed by two reviewers by consensus, based on source axial images, multiplanar reformats, and three-dimensional (3D) postprocessing images. Surgical intraoperative findings were used as standard of reference. RESULTS: At surgery, 17 biliary anomalies, 3 portal anomalies, 32 venous and 8 arterial variants were found in the 32 patients. MR correctly identified 15/17 biliary anomalies, with a sensitivity of 88% and a specificity of 93%. MDCT correctly identified 8/8 arterial, 3/3 portal and 29/32 venous variants, with a sensitivity of 100% and 91%, respectively, and a specificity of 100%. CONCLUSIONS: MR and MDCT proved to be efficient in evaluating living liver donor's biliary and vascular anatomy.

Role of MDCT in the diagnosis of hepatocellular carcinoma in patients with cirrhosis undergoing orthotopic liver transplantation.

OBJECTIVE: The purpose of this study was to assess the diagnostic performance of MDCT in the detection of hepatocellular carcinoma in patients with cirrhosis undergoing orthotopic liver transplantation. MATERIALS AND METHODS: Eighty-eight consecutively registered patients who underwent MDCT 6 months before liver transplantation were evaluated. The original reports were analyzed, and the CT images were retrospectively reevaluated independently by two radiologists who made the final interpretation in consensus. The imaging findings were correlated with histopathologic findings in the explanted livers on a patient-by-patient and a lesion-by-lesion basis. RESULTS: Histopathologic examination revealed 139 hepatocellular carcinomas in 48 of the 88 patients. MDCT correctly depicted 89 of 139 hepatocellular carcinomas (sensitivity, 64%) at the original examination and 102 at reevaluation (sensitivity, 73.3%). Patient-by-patient analysis showed a specificity of 75% in the original reports and of 77.5% at reevaluation. A large number of false-positive nodules were found, most (59.2%) of them being smaller than 1 cm in diameter. CONCLUSION: MDCT has reasonable sensitivity in the detection of hepatocellular carcinoma in patients with cirrhosis who undergo liver transplantation. Attention should be paid, however, to avoiding overestimation of the extent of disease.

A fully automated method for lung nodule detection from postero-anterior chest radiographs.

In the past decades, a great deal of research work has been devoted to the development of systems that could improve radiologists' accuracy in detecting lung nodules. Despite the great efforts, the problem is still open. In this paper, we present a fully automated system processing digital postero-anterior (PA) chest radiographs, that starts by producing an accurate segmentation of the lung field area. The segmented lung area includes even those parts of the lungs hidden behind the heart, the spine, and the diaphragm, which are usually excluded from the methods presented in the literature. This decision is motivated by the fact that lung nodules may be found also in these areas. The segmented area is processed with a simple multiscale method that enhances the visibility of the nodules, and an extraction scheme is then applied to select potential nodules. To reduce the high number of false positives extracted, cost-sensitive support vector machines (SVMs) are trained to recognize the true nodules. Different learning experiments were performed on two different data sets, created by means of feature selection, and employing Gaussian and polynomial SVMs trained with different parameters; the results are reported and compared. With the best SVM models, we obtain about 1.5 false positives per image (fp/image) when sensitivity is approximately equal to 0.71; this number increases to about 2.5 and 4 fp/image when sensitivity is = 0.78 and = 0.85, respectively. For the highest sensitivity (= 0.92 and 1.0), we get 7 or 8 fp/image.