A Lightweight Segmentation Network Based on Weak Supervision for COVID-19 Detection

The Coronavirus Disease 2019 (COVID-19) outbreak in late 2019 threatens global health security. Computed tomography (CT) can provide richer information for the diagnosis and treatment of COVID-19. Unfortunately, labeling of COVID-19 lesion chest CT images is an expensive affair. We solved the challenge of chest CT labeling by simply marking point annotations to the lesion areas, i.e., by marking individual pixels for each lesion area in the chest CT scan. It takes only a few seconds to complete the labeling using this labeling strategy. We also designed a lightweight segmentation model with approximately 10% of the number of model parameters of the conventional model. So, the proposed model segmented the lesions of a single image in only 0.05 s. In order to obtain the shape and size of lesions from point labels, the convex-hull based segmentation (CHS) loss function is proposed in this paper, which enables the model to obtain an approximate fully supervised performance on point labels. The experiments were compared with the current state-of-the-art (SOTA) point label segmentation methods on the COVID-19-CT-Seg dataset, and our model showed a large improvement: IoU improved by 28.85%, DSC improved by 28.91%, Sens improved by 13.75%, Spes improved by 1.18%, and MAE decreased by 1.10%. Experiments on the dataset show that the proposed model combines the advantages of lightweight and weak supervision, resulting in more accurate COVID-19 lesion segmentation results while having only a 10% performance difference with the fully supervised approach. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Human IFN-κ Inhibited Respiratory RNA Virus Replication Dependent on Cell-to-Cell Interaction in the Early Phase

Background:Interferon kappa (IFN-κ) is a type I interferon (IFN-I) that inhibits virus replication by evoking interferon-stimulated genes (ISGs). However, as an evolutionarily ancient interferon, IFN-κ may function differently from the later emerged interferon-α and β.Methods:Conventional molecular biology methods were used to determine the localization of IFN-κ and its structure and function. In addition, we employed RT-PCR, western blot, and RNA-Seq technologies to characterize the ISGs expression profile and antiviral activities exerted by IFN-κ or IFN-α2.Results:Human IFN-κ exists in two forms upon ectopic expression, one located on the cell membrane and the other secreted outside the cells. The membrane-anchored IFN-κ showed the ability to induce ISGs and curtail RNA virus replication, whereas the secreted IFN-κ failed to do so. Structural analyses indicated that 1-27aa at the N-terminus was the signal peptide, and 28-37aa was predicted as the transmembrane region. However, our data demonstrated that both of them were not associated with membrane localization of IFN-κ;the former influenced the expression and secretion of IFN-κ, and the latter had an impact on the induction of ISGs. In addition, prokaryotic purified soluble mature human IFN-κ was also capable of inducing ISGs and inhibiting RNA virus replication. Importantly, human IFN-κ induced a faster ISG response but with a lower intensity and a shorter half-life than the response of IFN-α2. In contrast, IFN-α2 started to function later but was stronger and more durable than IFN-κ.Conclusions:Human IFN-κ-induced ISG response and inhibited respiratory RNA virus replication dependent on cell-to-cell interactions. In addition, compared with IFN-α2, IFN-κ exerted effects more rapidly in the early phase, with less intensity and a shorter half-life. Therefore, IFN-κ may constitute the first line of IFN-I against respiratory virus infections. © 2022 Journal of Bone and Joint Surgery Inc.. All rights reserved.

Cough Detection Using Selected Informative Features from Audio Signals

Cough is a common symptom of respiratory and lung diseases. Cough detection is important to prevent, assess and control epidemic, such as COVID-19. This paper proposes a model to detect cough events from cough audio signals. The models are trained by the dataset combined ESC-50 dataset with self-recorded cough recordings. The test dataset contains inpatient cough recordings collected from inpatients of the respiratory disease department in Ruijin Hospital. We totally build 15 cough detection models based on different feature numbers selected by Random Frog, Uninformative Variable Elimination (UVE), and Variable influence on projection (VIP) algorithms respectively. The optimal model is based on 20 features selected from Mel Frequency Cepstral Coefficients (MFCC) features by UVE algorithm and classified with Support Vector Machine (SVM) linear two-class classifier. The best cough detection model realizes the accuracy, recall, precision and F1-score with 94.9%, 97.1%, 93.1% and 0.95 respectively. Its excellent performance with fewer dimensionality of the feature vector shows the potential of being applied to mobile devices, such as smartphones, thus making cough detection remote and non-contact. © 2021 IEEE.

Portable health screening device of respiratory infections

The COVID-19 epidemic was listed as a public health emergency of international concern by the WHO on January 30, 2020. To curb the secondary spread of the epidemic, many public places were equipped with thermal imagers to check the body temperature. However, the COVID-19 pneumonia has concealed symptoms: the first symptom may not be fever, and can be shortness of breath. During epidemic prevention, many people tend to wear masks. Therefore, in this demo paper, we proposed a portable non-contact health screening system for people wearing masks, which can simultaneously obtain body temperature and respiration state. This system consists of three modules viz. thermal image collection module, health indicator calculation module and health assessment module. In this system, the thermal video of human faces is first captured through a portable thermal imaging camera. Then, body temperature and respiration state are extracted from the video and imported into the following health assessment module. Finally, the screening result can be obtained. The results of preliminary experiments show that this system can offer an accurate screening result within 15 seconds. This system can be utilized in many application scenarios such as communities and campuses. The demo videos of the proposed system are available at: https://doi.org/10.6084/m9.figshare.12028032. © 2020 IEEE.