Lung Segmentation and Characterization in COVID-19 Patients for Assessing Pulmonary Thromboembolism: An Approach Based on Deep Learning and Radiomics

Abstract

The COVID-19 pandemic is inevitably changing the world in a dramatic way, and the role of computed tomography (CT) scans can be pivotal for the prognosis of COVID-19 patients. Since the start of the pandemic, great care has been given to the relationship between interstitial pneumonia caused by the infection and the onset of thromboembolic phenomena. In this preliminary study, we collected n = 20 CT scans from the Polyclinic of Bari, all from patients positive with COVID-19, nine of which developed pulmonary thromboembolism (PTE). For eight CT scans, we obtained masks of the lesions caused by the infection, annotated by expert radiologists; whereas for the other four CT scans, we obtained masks of the lungs (including both healthy parenchyma and lesions). We developed a deep learning-based segmentation model that utilizes convolutional neural networks (CNNs) in order to accurately segment the lung and lesions. By considering the images from publicly available datasets, we also realized a training set composed of 32 CT scans and a validation set of 10 CT scans. The results obtained from the segmentation task are promising, allowing to reach a Dice coefficient higher than 97%, posing the basis for analysis concerning the assessment of PTE onset. We characterized the segmented region in order to individuate radiomic features that can be useful for the prognosis of PTE. Out of 919 extracted radiomic features, we found that 109 present different distributions according to the Mann–Whitney U test with corrected p-values less than 0.01. Lastly, nine uncorrelated features were retained that can be exploited to realize a prognostic signature.

COVID-19 Infection in Children and Infants: Current Status on Therapies and Vaccines

“…Children under the age of 12 generally had mild symptoms that resolved within a week, while symptoms in adolescents were similar to those in adults [ 51 , 52 , 53 , 54 , 55 , 56 , 57 ]. Regarding the disease manifestation, SARS-CoV-2 infection can lead to asymptomatic cases [ 58 ], and COVID-19 ranges from mild flu-like illness (ILI) with mild to moderate development, with a good clinical course [ 56 ], to life-threatening complications [ 59 , 60 , 61 , 62 ], although pediatric deaths have also rarely been reported [ 63 ]. SARS-CoV-2 affects the respiratory tract, resulting in pneumonia, gastrointestinal (GI), cardiovascular or neurological systems [ 64 , 65 ].…”

“…The most frequent mild and moderate clinical pictures involve the respiratory and gastrointestinal systems. In the pediatric population, the most frequently observed symptoms are: fatigue, body aches, headache, low-grade fever, nasal congestion, runny nose, wheezing, dry cough, odynophagia, ageusia and anosmia accompanied by gastrointestinal symptoms, such as stomach pain and diarrhea [ 19 , 62 , 67 , 68 ].…”

A Fusion Biopsy Framework for Prostate Cancer Based on Deformable Superellipses and nnU-Net

“…The encoder–decoder structures have been implemented in different convolutional network architectures, including SegNet [ 30 ], U-Net [ 31 ], U-Net 3D [ 32 ], and V-Net [ 33 ]. Besides prostate segmentation, applications in medical imaging tasks of those architectures encompass liver vessels delineation [ 34 ], segments classification [ 35 ], lung COVID-19 lesions segmentation [ 36 ], and vertebrae segmentation [ 37 ].…”

Effectiveness of SARS-CoV-2 Vaccines for Short- and Long-Term Immunity: A General Overview for the Pandemic Contrast

“…The most common major complications are thromboembolic and massive pulmonary embolism [ 166 , 167 ], diffuse microvascular thrombosis [ 168 ], neurological complications resulting in strokes, encephalopathy, mono-polyneuritis, and pseudo-depressive forms that can arise from scratch or emerge from a pre-existing framework. The respiratory and hemodynamic stabilizations of the patient must be carried out with absolute timeliness regardless of the swab examination.…”