Prediction of carcinogenic human papillomavirus types in cervical cancer from multiparametric magnetic resonance images with machine learning-based radiomics models.

PURPOSE: This study aimed to evaluate the potential of machine learning-based models for predicting carcinogenic human papillomavirus (HPV) oncogene types using radiomics features from magnetic resonance imaging (MRI). METHODS: Pre-treatment MRI images of patients with cervical cancer were collected retrospectively. An HPV DNA oncogene analysis was performed based on cervical biopsy specimens. Radiomics features were extracted from contrast-enhanced T1-weighted images (CE-T1) and T2-weighted images (T2WI). A third feature subset was created as a combined group by concatenating the CE-T1 and T2WI subsets. Feature selection was performed using Pearson's correlation coefficient and wrapper- based sequential-feature selection. Two models were built with each feature subset, using support vector machine (SVM) and logistic regression (LR) classifiers. The models were validated using a five-fold cross-validation technique and compared using Wilcoxon's signed rank and Friedman's tests. RESULTS: Forty-one patients were enrolled in the study (26 were positive for carcinogenic HPV oncogenes, and 15 were negative). A total of 851 features were extracted from each imaging sequence. After feature selection, 5, 17, and 20 features remained in the CE-T1, T2WI, and combined groups, respectively. The SVM models showed 83%, 95%, and 95% accuracy scores, and the LR models revealed 83%, 81%, and 92.5% accuracy scores in the CE-T1, T2WI, and combined groups, respectively. The SVM algorithm performed better than the LR algorithm in the T2WI feature subset (P = 0.005), and the feature sets in the T2WI and the combined group performed better than CE-T1 in the SVM model (P = 0.033 and 0.006, respectively). The combined group feature subset performed better than T2WI in the LR model (P = 0.023). CONCLUSION: Machine learning-based radiomics models based on pre-treatment MRI can detect carcinogenic HPV status with discriminative accuracy.

Can invasive diagnostic methods be reduced by magnetic resonance imaging in the diagnosis of diaphragmatic injuries in left thoracoabdominal penetrating injuries?

Aim: In this study, we aimed to investigate the effect of magnetic resonance imaging (MRI) in detecting diaphragmatic injury by comparing preoperative computed tomography (CT) and MRI imaging results with diagnostic laparoscopy/thoracoscopy results in patients with left thoracoabdominal penetrating injury. We investigated whether MRI reduces the rate of unnecessary surgery by examining its sensitivity and specificity. Materials and Methods: Patients with left thoracoabdominal penetrating injuries who applied to the Emergency Surgery Unit of Istanbul University Istanbul Faculty of Medicine between November 2017 and December 2020 were evaluated. Patients who underwent emergency surgery, who could not undergo MRI or CT for any reason or who could not be operated on were excluded from the study. Preoperative MRI and CT images of patients who underwent diagnostic laparoscopy/thoracoscopy due to left thoracoabdominal injury in our clinic were evaluated retrospectively by a radiologist who did not know the surgical results. MRI results of the cases were compared with surgical findings and CT images. Results: A total of 43 (41 males, mean age: 31, range: 15-57) patients were included in the study. The most common physical examination finding was lateral injury. The diaphragmatic injury was detected in 13 (30%) cases during surgical interventions. Laparoscopic repair was performed in 11 (84%) cases and thoracoscopic repair was performed in 2 (15%) cases with diaphragmatic injuries. MRI images of 14 (32%) cases were found to be compatible with diaphragmatic injury, in 1 of them no injury was observed during surgical intervention. According to these data, the sensitivity of MRI was calculated as 100%, specificity 94%, positive predictive value 86%, and negative predictive value 100%. The mean hospital stay was 6 days (1-30) in all cases. Conclusion: In our study, MRI was found to have high specificity and sensitivity in detecting diaphragmatic injuries. The number of negative laparoscopy/thoracoscopy can be reduced by performing surgical intervention only in cases with positive or suspected diaphragmatic injury on MRI. Results should be supported by conducting new studies with larger case series with normal MRI findings and long follow-ups.

Antineutrophil Cytoplasmic Antibody-Associated Vasculitis and COVID-19: The Clinical Course and Prognosis of 15 Patients From a Tertiary Care Center.

OBJECTIVE: The aim of this study was to evaluate incidence rates, prognoses, and disease-related factors associated with poor outcomes in patients with antineutrophil cytoplasmic antibody-associated vasculitis (AAV) who had coronavirus disease (COVID-19). METHODS: Patients with AAV were questioned for a history of COVID-19 in the outpatient setting. Cumulative clinical findings and treatment history were obtained from the patients' medical records. The clinical, laboratory, and imaging findings of inpatients with COVID-19 were recorded. The data of patients who developed symptomatic COVID-19 and/or died of the disease were used for comparison. RESULTS: Eighty-nine patients (47.2% female; mean age, 56 ± 12.5 years) were included. The diagnosis was granulomatosis with polyangiitis in 56 patients (62.9%) and microscopic polyangiitis in 33 (37.1%). Sixty-one (68.2%) and 21 patients (23.6%) had renal and peripheral nerve involvement, respectively. Ten patients had a history of diffuse alveolar hemorrhage. Fifteen patients (16.9%) had COVID-19, including 9 (60%) with severe pneumonia. Twelve patients (85.7%) were hospitalized, 6 (42.9%) were admitted to the intensive care unit, and 5 (35.7%) died. All deceased patients had hypogammaglobulinemia (IgG levels <700 mg/dL) during hospital admission. Symptomatic COVID-19 was associated with higher disease activity, glucocorticoid and rituximab treatments, and glomerular filtration rate <30 mL/min. A history of peripheral nerve involvement, higher organ damage scores, and hypogammaglobulinemia was associated with mortality. CONCLUSIONS: The prognosis was poor in our patients with AAV who had COVID-19, especially those with severe multisystem involvement. Hypogammaglobulinemia was associated with mortality. Serum IgG level monitoring in patients with AAV would be beneficial during the COVID-19 pandemic.