COVID-19 after 2 Years from Hospital Discharge: A Pulmonary Function and Chest Computed Tomography Follow-Up Study.

INTRODUCTION: Serial follow-up with pulmonary function testing (PFT) and chest computed tomography (CT) after severe COVID-19 are recommended. As a result, many longitudinal studies have been published on COVID-19 of different grade of severity up to 1-year follow-up. Therefore, we aimed at a long-term observational study throughout 2 years after severe COVID-19. METHODS: Severe COVID-19 patients were consecutively recruited after hospital discharge between March and June 2020 and prospectively followed up for 24 months, with mMRC dyspnea scale and PFT at 6, 12, and 24 months. Chest CT was performed when clinically indicated. RESULTS: One hundred one patients enrolled completed the observational study. At 24 months, those with reduced total lung capacity (TLC) were 16%, associated with fibrotic ground glass opacity (GGO) and mMRC score >1, respectively, in 75% and 69% of them. At 24 months, those with a reduced diffusing capacity of the lung for CO were 41%, associated with fibrotic GGO and mMRC score >1, respectively, in 53% and 22% of them. CONCLUSION: Two years after hospitalization for severe COVID-19, a non-negligible number of patients still suffer from "long COVID" due to respiratory damage.

Radiomic Detection of EGFR Mutations in NSCLC.

Radiomics is defined as the use of automated or semi-automated post-processing and analysis of multiple features derived from imaging exams. Extracted features might generate models able to predict the molecular profile of solid tumors. The aim of this study was to develop a predictive algorithm to define the mutational status of EGFR in treatment-naïve patients with advanced non-small cell lung cancer (NSCLC). CT scans from 109 treatment-naïve patients with NSCLC (21 EGFR-mutant and 88 EGFR-wild type) underwent radiomics analysis to develop a machine learning model able to recognize EGFR-mutant from EGFR-WT patients via CT scans. A "test-retest" approach was used to identify stable radiomics features. The accuracy of the model was tested on an external validation set from another institution and on a dataset from the Cancer Imaging Archive (TCIA). The machine learning model that considered both radiomic and clinical features (gender and smoking status) reached a diagnostic accuracy of 88.1% in our dataset with an AUC at the ROC curve of 0.85, whereas the accuracy values in the datasets from TCIA and the external institution were 76.6% and 83.3%, respectively. Furthermore, 17 distinct radiomics features detected at baseline CT scan were associated with subsequent development of T790M during treatment with an EGFR inhibitor. In conclusion, our machine learning model was able to identify EGFR-mutant patients in multiple validation sets with globally good accuracy, especially after data optimization. More comprehensive training sets might result in further improvement of radiomics-based algorithms. SIGNIFICANCE: These findings demonstrate that data normalization and "test-retest" methods might improve the performance of machine learning models on radiomics images and increase their reliability when used on external validation datasets.

Inferior vena cava resection without reconstruction for retroperitoneal malignancies.

Inferior vena cava (IVC) involvement in retroperitoneal malignancies is a rare occurrence and radical surgery with major vascular resection represents the only potential curative treatment. IVC replacement after resection is still controversial and only small series and few prospective data are available. We report a series of three patients affected by retroperitoneal masses involving IVC treated with vena cava resection without replacement. All patients were treated by a radical R0 surgical procedure associated with infrarenal IVC resection and no reconstruction. Based on preoperative radiologic imaging and intraoperative findings, one patient also underwent right nephrectomy, while another patient underwent left renal vein ligation without nephrectomy. Neither early nor late severe post-operative complications related to the absence of IVC outflow were observed. Resection without replacement of the infrarenal IVC results in acceptable morbidity, thus specific risks related to the use of prosthetic grafts can be avoided.