A Multiclass Radiomics Method-Based WHO Severity Scale for Improving COVID-19 Patient Assessment and Disease Characterization From CT Scans.

OBJECTIVES: The aim of this study was to evaluate the severity of COVID-19 patients' disease by comparing a multiclass lung lesion model to a single-class lung lesion model and radiologists' assessments in chest computed tomography scans. MATERIALS AND METHODS: The proposed method, AssessNet-19, was developed in 2 stages in this retrospective study. Four COVID-19-induced tissue lesions were manually segmented to train a 2D-U-Net network for a multiclass segmentation task followed by extensive extraction of radiomic features from the lung lesions. LASSO regression was used to reduce the feature set, and the XGBoost algorithm was trained to classify disease severity based on the World Health Organization Clinical Progression Scale. The model was evaluated using 2 multicenter cohorts: a development cohort of 145 COVID-19-positive patients from 3 centers to train and test the severity prediction model using manually segmented lung lesions. In addition, an evaluation set of 90 COVID-19-positive patients was collected from 2 centers to evaluate AssessNet-19 in a fully automated fashion. RESULTS: AssessNet-19 achieved an F1-score of 0.76 ± 0.02 for severity classification in the evaluation set, which was superior to the 3 expert thoracic radiologists (F1 = 0.63 ± 0.02) and the single-class lesion segmentation model (F1 = 0.64 ± 0.02). In addition, AssessNet-19 automated multiclass lesion segmentation obtained a mean Dice score of 0.70 for ground-glass opacity, 0.68 for consolidation, 0.65 for pleural effusion, and 0.30 for band-like structures compared with ground truth. Moreover, it achieved a high agreement with radiologists for quantifying disease extent with Cohen κ of 0.94, 0.92, and 0.95. CONCLUSIONS: A novel artificial intelligence multiclass radiomics model including 4 lung lesions to assess disease severity based on the World Health Organization Clinical Progression Scale more accurately determines the severity of COVID-19 patients than a single-class model and radiologists' assessment.

Improved Diagnostic Yield and Specimen Quality With Endobronchial Ultrasound-Guided Forceps Biopsies: A Retrospective Analysis.

BACKGROUND: Endobronchial ultrasound (EBUS) transbronchial needle aspiration (TBNA) has a high diagnostic yield when evaluating mediastinal and hilar lymphadenopathy (LAD). Having previously demonstrated the safety of EBUS-guided cautery-assisted transbronchial nodal forceps biopsy (ca-TBFB), we report disease-specific improvements in diagnostic yield and tissue acquisition when supplementing the EBUS-TBNA-based standard of care (SOC) with ca-TBFB. METHODS: We retrospectively reviewed 213 patients who sequentially underwent SOC and ca-TBFB during the same procedure. We determined 3 clinical scenarios of interest based on preprocedural imaging: isolated mediastinal/hilar LAD, LAD associated with a nodule or mass suspicious for malignancy, and LAD associated with parenchymal findings suggestive of sarcoidosis. Using validated methods, we assessed diagnostic yield on a per-patient basis and specimen quality on a per-node basis on the 136 patients meeting diagnostic criteria. RESULTS: Administration of disease-specific SOC with ca-TBFB yielded gains that varied by diagnosis. Diagnostic yields of SOC and its supplementation with ca-TBFB were 91.8% and 93.4% (P = .50) of the 61 patients diagnosed with solid-organ malignancy, 62.7% and 94.9% (P < .001) of the 59 patients diagnosed with sarcoidosis, and 62.5% and 93.8% (P = .042) of the 16 patients diagnosed with lymphoma, the. For each disease process, specimens obtained with ca-TBFB exhibited statistically higher quality. CONCLUSIONS: We suggest that relative to SOC, ca-TBFB improves diagnostic yield for sarcoidosis and lymphoma while providing uniformly better tissue quality and cellularity. We propose a protocol for use of this innovative technique.

An illustrative case of endocardial fibroelastosis and recalcitrant intracardiac thrombosis: a case report.

BACKGROUND: Endocardial Fibroelastosis is diffuse, accentuated proliferation of ventricular endocardium causing a rare form of restrictive cardiomyopathy in both children and adults. It is an incompletely understood cause of heart failure predominantly in Sub-Saharan Africa associated with high morbidity and mortality. Atrial fibrillation and thrombus formation are common accompanying complications and portend a poor prognosis. Due to rarity of the condition in the developed countries and lack of evidence based options, the optimal strategy for anticoagulation is unclear. CASE PRESENTATION: Herein, we describe a relatively asymptomatic patient with endocardial fibroelastosis who has been found to have atrial fibrillation and a large thrombus in the right atrium. Currently, there is no evidence-based strategy in the management of endocardial fibroelastosis-associated intracardiac thrombus. This case report illustrates a scenario by which the use of apixaban potentially benefited or prevented the thrombus formation compared with warfarin as demonstrated by imaging findings. CONCLUSIONS: The patients with endocardial fibroelastosis are at risk of developing intracardiac thrombus due to sticky substrate lining cardiac chambers while being relatively asymptomatic. No directed therapy is known for the management of heart failure and any complications of subsequent arrhythmias. The general recommendations follow those of same conditions in other hosts. Novel oral anticoagulant agents can be considered in the treatment of atrial thrombus in the appropriate settings.