Facilitating standardized COVID-19 suspicion prediction based on computed tomography radiomics in a multi-demographic setting.

OBJECTIVE: To develop an automatic COVID-19 Reporting and Data System (CO-RADS)-based classification in a multi-demographic setting. METHODS: This multi-institutional review boards-approved retrospective study included 2720 chest CT scans (mean age, 58 years [range 18-100 years]) from Italian and Russian patients. Three board-certified radiologists from three countries assessed randomly selected subcohorts from each population and provided CO-RADS-based annotations. CT radiomic features were extracted from the selected subcohorts after preprocessing steps like lung lobe segmentation and automatic noise reduction. We compared three machine learning models, logistic regression (LR), multilayer perceptron (MLP), and random forest (RF) for the automated CO-RADS classification. Model evaluation was carried out in two scenarios, first, training on a mixed multi-demographic subcohort and testing on an independent hold-out dataset. In the second scenario, training was done on a single demography and externally validated on the other demography. RESULTS: The overall inter-observer agreement for the CO-RADS scoring between the radiologists was substantial (k = 0.80). Irrespective of the type of validation test scenario, suspected COVID-19 CT scans were identified with an accuracy of 84%. SHapley Additive exPlanations (SHAP) interpretation showed that the "wavelet_(LH)_GLCM_Imc1" feature had a positive impact on COVID prediction both with and without noise reduction. The application of noise reduction improved the overall performance between the classifiers for all types. CONCLUSION: Using an automated model based on the COVID-19 Reporting and Data System (CO-RADS), we achieved clinically acceptable performance in a multi-demographic setting. This approach can serve as a standardized tool for automated COVID-19 assessment. KEYPOINTS: • Automatic CO-RADS scoring of large-scale multi-demographic chest CTs with mean AUC of 0.93 ± 0.04. • Validation procedure resembles TRIPOD 2b and 3 categories, enhancing the quality of experimental design to test the cross-dataset domain shift between institutions aiding clinical integration. • Identification of COVID-19 pneumonia in the presence of community-acquired pneumonia and other comorbidities with an AUC of 0.92.

Contrast-enhanced mammography in the evaluation of breast calcifications: preliminary experience.

AIM: To evaluate the presence of contrast enhancement at the site of calcifications on contrast-enhanced mammography (CEM) and histopathologic results at vacuum-assisted biopsy (VAB), and to examine the association with lesion size and immunohistochemical characteristics, in order to assess disease aggressiveness in malignant lesions. METHODS: A total of 34 patients with 36 clusters of suspicious calcifications (BI-RADS 4) were investigated with CEM before the scheduled VAB. We evaluated the presence or absence of enhancement, histologic diagnosis, and, in case of malignant lesions, their size and the expression of Ki-67. RESULTS: In our case series, 15/36 (41.7%) lesions were malignant. In 7 cases, contrast enhancement was found at the site of calcifications. Data about size of lesions and immunohistochemical characterization were not available for all malignant cases. In 5 cases with CEM enhancement, all lesions were >5 mm and overexpressing Ki-67 (>20%); in 6 cases with no contrast enhancement, the lesions were <5 mm and with low Ki-67 values (<20%). CONCLUSION: Our preliminary study provides indications on the ability of CEM to recognize neoplasms larger than 5 mm, with high proliferative index (Ki-67 >20%), and frequently human epidermal growth factor receptor 2-positive. Our preliminary results suggest that CEM could detect aggressive malignancies. This could be the starting point for planning further studies with larger numbers of cases, in an attempt to reduce overdiagnosis and consequent overtreatment.

Our Assessment Using Palate Postoperative Problems Score (PPOPS): Tool for the Evaluation of Results in Palatal Surgery Techniques.

Obstructive sleep apnoea syndrome is a chronic condition characterized by frequent episodes of collapse of upper airways during sleep. Prevalence of the disease is settled at about 3-7%. Today, palatal surgery is a reference point in OSAHS treatment and there are many different surgical techniques. The purpose of our work is to compare post-operative results of palate surgery techniques used in our practice in OSAHS patients, studying the degree of patients' satisfaction with a recent score recommended by Rashwan et al. called PPOPS (Palate Post-Operative Problems Score). A retrospective study was performed on a sample of 40 patients subject to different palate surgery techniques for OSAS. Analysed surgical techniques were: Expansion Sphincter Pharyngoplasty (ESP), Uvulopalatopharyngoplasty (UPPP), Anterior Pharyngoplasty (AP), Barbed Reposition Pharyngoplasty (BRP). Patients answered the PPOPS and the results for each of the four techniques were compared. Group differences in the questionnaire total score were evaluated through Tukey's honest significance test for multiple (pairwise) comparisons. Overall average scores in the four groups were: AP 2.21, ESP 5.92, UPPP 2.8 and BRP 2.4. Comparing ESP with the other techniques (BRP, AP and UPPP) the scores were significantly higher (P < 0.05). Pairwise comparisons between the other three techniques (FA, UPPP and BRP) had a P value higher than 0.05, allowing to state that questionnaire results, in these cases, were similar to each other. Our work shows that different surgical techniques, even with the same purpose, could have different characteristics during follow-up. PPOPS is useful in post-operative for a better surgical practice.