OBJECTIVE: The aim of the study was to characterize the perfusion patterns on perfusion computed tomography (PCT) in patients with seizures masquerading as acute stroke.
METHODS: We conducted a study on patients with acute seizures as stroke mimics. The inclusion criteria for this study were patients (1) initially presenting with stroke-like symptoms but finally diagnosed to have seizures and (2) with PCT performed within 72 h of seizures. The PCT of seizure patients (n = 27) was compared with that of revascularized stroke patients (n = 20) as the control group.
RESULTS: Among the 27 patients with seizures as stroke mimics, 70.4% (n = 19) showed characteristic PCT findings compared with the revascularized stroke patients, which were as follows: (1) multi-territorial cortical hyperperfusion {(73.7% [14/19] vs. 0% [0/20], p = 0.002), sensitivity of 73.7%, negative predictive value (NPV) of 80%}, (2) involvement of the ipsilateral thalamus {(57.9% [11/19] vs. 0% [0/20], p = 0.007), sensitivity of 57.9%, NPV of 71.4%}, and (3) reduced perfusion time {(84.2% [16/19] vs. 0% [0/20], p = 0.001), sensitivity of 84.2%, NPV of 87%}. These 3 findings had 100% specificity and positive predictive value in predicting patients with acute seizures in comparison with reperfused stroke patients. Older age was strongly associated with abnormal perfusion changes (p = 0.038), with a mean age of 66.8 ± 14.5 years versus 49.2 ± 27.4 years (in seizure patients with normal perfusion scan).
CONCLUSIONS: PCT is a reliable tool to differentiate acute seizures from acute stroke in the emergency setting.
CASE REPORT: We present a 8-year-old boy complaining from difficulty in breathing and breastfeeding in the neonatal period due to an adenoid-like nasopharyngeal mass. Histological examination revealed solid and cystic squamous nests and numerous duct-like structures within collagenised stroma. Both epithelial and myoepithelial differentiation were noted in the tubular component.
DISCUSSION: A review of the clinical and histopathological features of published cases revealed that ancient lesions showed more prominent and complex epithelial component and more collagen rich stroma. We would like to suggest the possibility of salivary gland anlage tumour to be considered in the differential diagnosis of neonatal respiratory distress cases.
METHODS: Overall, 612 patients (306 COVID-19 and 306 non-COVID-19 pneumonia) were recruited. Twenty radiological features were extracted from CT images to evaluate the pattern, location, and distribution of lesions of patients in both groups. All significant CT features were fed in five classifiers namely decision tree, K-nearest neighbor, naïve Bayes, support vector machine, and ensemble to evaluate the best performing CAD system in classifying COVID-19 and non-COVID-19 cases.
RESULTS: Location and distribution pattern of involvement, number of the lesion, ground-glass opacity (GGO) and crazy-paving, consolidation, reticular, bronchial wall thickening, nodule, air bronchogram, cavity, pleural effusion, pleural thickening, and lymphadenopathy are the significant features to classify COVID-19 from non-COVID-19 groups. Our proposed CAD system obtained the sensitivity, specificity, and accuracy of 0.965, 93.54%, 90.32%, and 91.94%, respectively, using ensemble (COVIDiag) classifier.
CONCLUSIONS: This study proposed a COVIDiag model obtained promising results using CT radiological routine features. It can be considered an adjunct tool by the radiologists during the current COVID-19 pandemic to make an accurate diagnosis.
KEY POINTS: • Location and distribution of involvement, number of lesions, GGO and crazy-paving, consolidation, reticular, bronchial wall thickening, nodule, air bronchogram, cavity, pleural effusion, pleural thickening, and lymphadenopathy are the significant features between COVID-19 from non-COVID-19 groups. • The proposed CAD system, COVIDiag, could diagnose COVID-19 pneumonia cases with an AUC of 0.965 (sensitivity = 93.54%; specificity = 90.32%; and accuracy = 91.94%). • The AUC, sensitivity, specificity, and accuracy obtained by radiologist diagnosis are 0.879, 87.10%, 88.71%, and 87.90%, respectively.