Identifying the individual metabolic abnormities from a systemic perspective using whole-body PET imaging.

INTRODUCTION: Distinct physiological states arise from complex interactions among the various organs present in the human body. PET is a non-invasive modality with numerous successful applications in oncology, neurology, and cardiology. However, while PET imaging has been applied extensively in detecting focal lesions or diseases, its potential in detecting systemic abnormalities is seldom explored, mostly because total-body imaging was not possible until recently. METHODS: In this context, the present study proposes a framework capable of constructing an individual metabolic abnormality network using a subject's whole-body 18F-FDG SUV image and a normal control database. The developed framework was evaluated in the patients with lung cancer, the one discharged after suffering from Covid-19 disease, and the one that had gastrointestinal bleeding with the underlying cause unknown. RESULTS: The framework could successfully capture the deviation of these patients from healthy subjects at the level of both system and organ. The strength of the altered network edges revealed the abnormal metabolic connection between organs. The overall deviation of the network nodes was observed to be highly correlated to the organ SUV measures. Therefore, the molecular connectivity of glucose metabolism was characterized at a single subject level. CONCLUSION: The proposed framework represents a significant step toward the use of PET imaging for identifying metabolic dysfunction from a systemic perspective. A better understanding of the underlying biological mechanisms and the physiological interpretation of the interregional connections identified in the present study warrant further research.

The study of antiviral drugs targeting SARS-CoV-2 nucleocapsid and spike proteins through large-scale compound repurposing.

Contributing to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) clinical treatment, a drug library encompassing approximately 3,142 clinical-stage or FDA-approved small molecules is profiled to identify the candidate therapeutic inhibitors targeting nucleocapsid protein (N) and spike protein (S) of SARS-CoV-2. 16 screened candidates with higher binding affinity are evaluated via virtual screening. Comparing to those under trial/temporarily used antivirus drugs (i.e., umifenovir, lopinavir), ceftriaxone, cefotaxime, and cefuroxime show higher binding affinities to the N-terminal domain of N protein (N-NTD), C-terminal domain of N protein (N-CTD), and receptor-binding domain of S protein (S-RBD). Cefotaxime and cefuroxime have high binding affinities towards S-RBD with angiotensin-converting enzyme 2 (ACE2) complex via influence the critical interface sites at the interface of S-RBD (Arg403, Tyr453, Trp495, Gly496, Phe497, Asn501and Tyr505) and ACE2 (Asn33, His34, Glu37, Asp38, Lys353, Ala386, Ala387, Gln388, Pro389, Phe390 and Arg393) complex.

FaNet: fast assessment network for the novel coronavirus (COVID-19) pneumonia based on 3D CT imaging and clinical symptoms.

The novel coronavirus (COVID-19) pneumonia has become a serious health challenge in countries worldwide. Many radiological findings have shown that X-ray and CT imaging scans are an effective solution to assess disease severity during the early stage of COVID-19. Many artificial intelligence (AI)-assisted diagnosis works have rapidly been proposed to focus on solving this classification problem and determine whether a patient is infected with COVID-19. Most of these works have designed networks and applied a single CT image to perform classification; however, this approach ignores prior information such as the patient's clinical symptoms. Second, making a more specific diagnosis of clinical severity, such as slight or severe, is worthy of attention and is conducive to determining better follow-up treatments. In this paper, we propose a deep learning (DL) based dual-tasks network, named FaNet, that can perform rapid both diagnosis and severity assessments for COVID-19 based on the combination of 3D CT imaging and clinical symptoms. Generally, 3D CT image sequences provide more spatial information than do single CT images. In addition, the clinical symptoms can be considered as prior information to improve the assessment accuracy; these symptoms are typically quickly and easily accessible to radiologists. Therefore, we designed a network that considers both CT image information and existing clinical symptom information and conducted experiments on 416 patient data, including 207 normal chest CT cases and 209 COVID-19 confirmed ones. The experimental results demonstrate the effectiveness of the additional symptom prior information as well as the network architecture designing. The proposed FaNet achieved an accuracy of 98.28% on diagnosis assessment and 94.83% on severity assessment for test datasets. In the future, we will collect more covid-CT patient data and seek further improvement.