346. Head to Toe Imaging of Complications and Sequelae of COVID- 19 and COVID-19 Vaccination

Background COVID 19 is associated with a hypercoagulable state with cytokine storm syndrome and thrombocytopenia leading to complications across various systems. COVID-19 infection, its treatment, resultant immunosuppression, and pre-existing comorbidities have made patients vulnerable to secondary infections Methods We systematically reviewed COVID-19 cases between Jan to May 2021 for pulmonary and extrapulmonary complications. Patients with recent COVID-19 vaccination and neurological symptoms were also included. Figure 1. “Black turbinate” sign of mucormycosis Contrast enhanced coronal T1 FS images of paranasal sinuses shows necrotic non-enhancing right superior and middle turbinates (*) with extension into the right orbital fat. FIGURE 2 - A composite image of Coronal CT of upper abdomen in arterial phase and lung bases in lung window showing wedge showing right renal infarcts (line arrow) due to inferior polar artery thrombosis and ground glass opacities (solid arrow) in lung bases. Results Neurological complications: Neurological complications include ischemic and haemorrhagic strokes. Other complications are encephalopathy, encephalitis, Guillain-Barré syndrome, acute hemorrhagic necrotizing encephalopathy. Demyelination and radiculopathies are seen as post vaccination complications. Mucormycosis: Unprecedented high rate of invasive fungal sinusitis in association with COVID -19 is reported from the Indian subcontinent. This has a propensity for intra orbital and intracranial extension. COVID -19 associated coagulopathy: COVID -19 is a pro-inflammatory hypercoagulable state. Pulmonary thromboembolism, deep venous thrombosis and catheter related thrombosis are well documented. Cardiac complications: Cardiac manifestations include Myocardial Injury with non-obstructed coronary arteries (MINOCA), myocarditis, myocardial ischemia, cardiomyopathy. Pulmonary complications and sequelae of COVID -19: Progression of lung injury to ARDS during the initial phase and fibrosis of parenchyma in the recovery phase. Spontaneous pneumomediastinum, pneumatoceles and pneumothorax and secondary infections are identified in our study. COVID- 19 associated gastrointestinal complications: Patients evaluated for renal colic, pancreatitis, cholecystitis showed, ground glass opacities or subpleural bands in typical Covid-19 distribution. COVID-19 may lead of acute kidney and bowel injury due to arterial thrombosis. COVID - 19 associated myonecrosis: Ischemia of the small caliber vessels may result in myonecrosis. FIGURE 3 - Coronal STIR image shows thickened and hyperintense trunks and divisions of the right brachial plexus suggestive of plexopathy in a COVID -19 patient with H/O recent COVID-19 vaccination. Figure 4. Axial CT chest section in lung window showing pneumothorax (white arrow) and pneumatocele ( grey arrow) with peripheral ground glass opacities and consolidations in both lungs. Conclusion Awareness of these unusual manifestations will facilitate an early diagnosis, improve management and help reduce morbidity and mortality Disclosures All Authors: No reported disclosures

An Explainable Framework for Diagnosis of COVID-19 Pneumonia via Transfer Learning and Discriminant Correlation Analysis

The new coronavirus COVID-19 has been spreading all over the world in the last six months, and the death toll is still rising. The accurate diagnosis of COVID-19 is an emergent task as to stop the spreading of the virus. In this paper, we proposed to leverage image feature fusion for the diagnosis of COVID-19 in lung window computed tomography (CT). Initially, ResNet-18 and ResNet-50 were selected as the backbone deep networks to generate corresponding image representations from the CT images. Second, the representative information extracted from the two networks was fused by discriminant correlation analysis to obtain refined image features. Third, three randomized neural networks (RNNs): extreme learning machine, Schmidt neural network and random vector functional-link net, were trained using the refined features, and the predictions of the three RNNs were ensembled to get a more robust classification performance. Experiment results based on five-fold cross validation suggested that our method outperformed state-of-the-art algorithms in the diagnosis of COVID-19.

It’s Not All about Echocardiography. Open the Lung Window for the Cardiac Emergencies

In the acute cardiac care setting, undifferentiated clinical presentations such as dyspnea, chest pain, shock, and cardiac arrest are common diagnostic challenges for the clinician. Lung ultrasonography is a well-established diagnostic tool which can be integrated in simplified decision making algorithms during the initial approach of the patient, in order to differentiate accurately cardiac from non-cardiac causes and improve the management of time-sensitive cardiovascular emergencies.

Interobserver Variation of Colonic Polyp Measurement at Computed Tomography Colonography

Background The concept of “advanced polyps” is well accepted and is defined as polyps ≥10 mm and/or those having a villous component and/or demonstrating areas of dysplasia. Of these parameters, computed tomography colonography (CTC) can only document size. The accepted management of CTC-detected “advanced polyps” is to recommend excision if feasible, whereas the management of “intermediate” (6–9 mm) polyps is more controversial, and interval surveillance may be acceptable. Therefore, distinction between 6-9 mm and ≥10 mm is important. Methods Datasets containing 26 polyps originally reported as between 8-12 mm in diameter were reviewed independently by 4 CTC-accredited radiologists. Observers tabulated the largest measurement for each polyp on axial, coronal, sagittal, and endoluminal views at lung-window settings. These measurements were also compared to those determined by the computer-aided detection (CAD) software. Results The interobserver reliability intra-class correlation coefficient (ICC) for sagittal projection was 0.80 (“excellent” category of Hosmer and Lemeshow [2004]), 0.71 for axial (“acceptable”), 0.69 for coronal, and 0.41 for endoluminal (“unacceptable”). The largest of sagittal/axial/coronal measurement gave the best reliability with the smallest variance (ICC = 0.80; 95% CI 0.67–0.89). For 8 of 26 polyps, at least one radiologist's measurement placed the polyp in a different category compared to a colleague. For the majority of the polyps, the CAD significantly overestimated the readings compared to the largest of the manual measurements with an average difference of 1.6 mm ( P < .0001 for sagittal/axial/coronal). This resulted in 33% of polyps falling into a different category—10% were lower and 23% were higher ( P < .034). Conclusion It is apparent that around the cutoff point of 10 mm between “advanced” and “intermediate” polyps, interobserver performance is variable.