Initial chest X-ray findings in pediatric patients diagnosed with H1N1 virus infection

Learning to learn by yourself: Unsupervised meta-learning with self-knowledge distillation for COVID-19 diagnosis from pneumonia cases

The goal of diagnosing the coronavirus disease 2019 (COVID-19) from suspected pneumonia cases, that is, recognizing COVID-19 from chest X-ray or computed tomography (CT) images, is to improve diagnostic accuracy, leading to faster intervention. The most important and challenging problem here is to design an effective and robust diagnosis model. To this end, there are three challenges to overcome: (1) The lack of training samples limits the success of existing deep-learning-based methods. (2) Many public COVID-19 data sets contain only a few images without fine-grained labels. (3) Due to the explosive growth of suspected cases, it is urgent and important to diagnose not only COVID-19 cases but also the cases of other types of pneumonia that are similar to the symptoms of COVID-19. To address these issues, we propose a novel framework called Unsupervised Meta-Learning with Self-Knowledge Distillation to address the problem of differentiating COVID-19 from pneumonia cases. During training, our model cannot use any true labels and aims to gain the ability of learning to learn by itself. In particular, we first present a deep diagnosis model based on a relation network to capture and memorize the relation among different images. Second, to enhance the performance of our model, we design a self-knowledge distillation mechanism that distills knowledge within our model itself. Our network is divided into several parts, and the knowledge in the deeper parts is squeezed into the shallow ones. The final results are derived from our model by learning to compare the features of images. Experimental results demonstrate that our approach achieves significantly higher performance than other state-of-the-art methods. Moreover, we construct a new COVID-19 pneumonia data set based on text mining, consisting of 2696 COVID-19 images (347 X-ray + 2349 CT), 10,155 images (9661 X-ray + 494 CT) about other types of pneumonia, and the fine-grained labels of all. Our data set considers not only a bacterial infection or viral infection which causes pneumonia but also a viral infection derived from the influenza virus or coronavirus.

Pediatric SARS, H1N1, MERS, EVALI, and Now Coronavirus Disease (COVID-19) Pneumonia: What Radiologists Need to Know

OBJECTIVE. The purpose of this article is to review new pediatric lung disorders-including disorders that have occurred in recent years years such as severe acute respiratory syndrome (SARS), swine-origin influenza A (H1N1), Middle East respiratory syndrome (MERS), e-cigarette or vaping product use-associated lung injury (EVALI), and coronavirus disease (COVID-19) pneumonia-to enhance understanding of the characteristic imaging findings. CONCLUSION. Although the clinical symptoms of SARS, H1N1, MERS, EVALI, and COVID-19 pneumonia in pediatric patients may be nonspecific, some characteristic imaging findings have emerged or are currently emerging. It is essential for radiologists to have a clear understanding of the characteristic imaging appearances of these lung disorders in pediatric patients to ensure optimal patient care.

H1N1 with fatal viral septicemia in a normal child: A case report

Regardless of the agent, the inflammatory response is interconnected with infection. Mostly the initial response to infection is severe sepsis and characterized by a pro-inflammatory state, which then progresses to an anti-inflammatory state that develops and favors secondary infections (Florescu and Kalil, 2011) [1]. T-helper 1 (Th1) cells activated by microorganisms increase transcription of pro-inflammatory cytokines such as tumor necrosis factor (TNF-α), interferon-γ (INF-γ), and interleukin-2 (IL-2) (Hotchkiss and Karl, 2003; Brown and Jones, 2004; Russell, 2006) [[2], [3], [4]]. Different cytokines, TNF-α, interleukins, lymphokines, monokines, IFN-γ, colony-stimulating factor (CSF) and transforming growth factors, released from endothelial cells and subsequently from macrophages can induce lymphocyte activation and infiltration at the sites of infection and will exert direct antiviral effects. Subsequently, with the shift toward an anti-inflammatory state, activated T-helper 2 (Th2) cells secrete interleukin-4 (IL-4) and interleukin-10 (IL-10) (Hotchkiss and Karl, 2003; Russell, 2006) [2,4]. Sometimes, T cells can become anergic and fail to proliferate as wells producing cytokines (Hotchkiss and Karl, 2003) [2]. Type I IFN has a potent anti-influenza virus activity, it induces transcription of several interferon-stimulated genes, which in turn restrict viral replication (Garcia-Sastre, 2011) [5]. However, the influenza virus developed several mechanisms to evade IFN response as NS1 protein, IFN-antagonist produced by the virus, PB1–F2 proteins that inhibit IFN induction, the viral polymerase inhibits IFN function, and M2 protein prevents toll-like receptor (TLR) induction (Garcia-Sastre, 2011) [5].

Influenza virus can also trigger the deregulation of the innate immune system with excessive cytokines release leading to potentially harmful consequences (Teijaro et al., 2011) [6]. Abnormal immune response to influenza can lead to endothelial damage through the remodeling of the cellular cytoskeleton, loss of intercellular junctional integrity, cellular apoptosis, deregulation of coagulation, the consequent alteration of microvascular permeability, tissue edema, and shock (Steinberg et al., 2012) [7]. This increase in permeability of the endothelium is mainly due to the intercellular pathways and to a lesser extent through the transcellular leak (Steinberg et al., 2012) [7]. Such vascular hyperpermeability and multi-organ failure with severe edema, shock, acute lung injury, and even acute encephalopathy have been described in severe influenza infections (Wang et al., 2010; Armstrong et al., 2013) [8,9]. Novel drugs and vaccines such as peramivir, baloxavir marboxil, and 4 egg-based quadrivalent inactivated influenza vaccines have been added recently [10]. These changes require better and more efficient diagnostic and therapeutic approaches to avoid a fatal progression. I would like to report a child patient with H1N1 influenza, who developed rapid fatal viral septicemia.