Interstitial lung abnormalities: new insights between theory and clinical practice

Interstitial lung abnormalities (ILAs) represent radiologic abnormalities incidentally detected on chest computed tomography (CT) examination, potentially related to interstitial lung diseases (ILD). Numerous studies have demonstrated that ILAs are associated with increased risk of progression toward pulmonary fibrosis and mortality. Some radiological patterns have been proven to be at a higher risk of progression. In this setting, the role of radiologists in reporting these interstitial abnormalities is critical. This review aims to discuss the most recent advancements in understanding this radiological entity and the open issues that still prevent the translation from theory to practice, emphasizing the importance of ILA recognition and adequately reporting in clinical practice.

COVID-19 and Post-Acute COVID-19 Syndrome: From Pathophysiology to Novel Translational Applications

The new severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) was responsible for a global emergency, with the declaration of a pandemic in March 2020. SARS-CoV-2 can determine coronavirus disease 2019 (COVID-19), ranging from a mild illness to a serious condition requiring hospitalization in an intensive care unit. Furthermore, reports of persistent lung abnormalities and residual disability after a negative swab test suggest the presence of a post-acute COVID-19 syndrome, with the need for multidisciplinary rehabilitation strategies in the majority of survivors. However, the pathophysiological mechanisms of the acute and post-acute manifestations of COVID-19 have not been fully elucidated. In this Special Issue, a number of review and original articles provided a stimulating insight into the pathophysiology and diagnostics of COVID-19 and post-acute COVID-19 syndrome. Moreover, some novel prognostic and therapeutic applications were analyzed, with potential repercussions in clinical practice and future research. The need for further laboratory and translational research seems to emerge from this collection of articles, with the aim of elucidating the molecular mechanisms of COVID-19 at different stages of the disease. This could enable personalized prevention, interventional and rehabilitation strategies aimed at reducing disease progression and long-term disability.

B-Line Detection and Localization in Lung Ultrasound Videos Using Spatiotemporal Attention

The presence of B-line artefacts, the main artefact reflecting lung abnormalities in dengue patients, is often assessed using lung ultrasound (LUS) imaging. Inspired by human visual attention that enables us to process videos efficiently by paying attention to where and when it is required, we propose a spatiotemporal attention mechanism for B-line detection in LUS videos. The spatial attention allows the model to focus on the most task relevant parts of the image by learning a saliency map. The temporal attention generates an attention score for each attended frame to identify the most relevant frames from an input video. Our model not only identifies videos where B-lines show, but also localizes, within those videos, B-line related features both spatially and temporally, despite being trained in a weakly-supervised manner. We evaluate our approach on a LUS video dataset collected from severe dengue patients in a resource-limited hospital, assessing the B-line detection rate and the model’s ability to localize discriminative B-line regions spatially and B-line frames temporally. Experimental results demonstrate the efficacy of our approach for classifying B-line videos with an F1 score of up to 83.2% and localizing the most salient B-line regions both spatially and temporally with a correlation coefficient of 0.67 and an IoU of 69.7%, respectively.

Serum HMGB1, DKK1, and ACE2 as a Function of Lung Injuries in COVID-19 Patients

There is a need for a biomarker for lung injury in COVID-19 patients. In the present study, an attempt was carried out to examine the role of Dickkopf-related protein 1 (DKK1), High-mobility group box 1 protein (HMGB1), angiotensin-converting enzyme 2 (ACE2) as a function for the lung abnormalities in CT-scan (LACTS). To perform the goals, DKK1, HMGB1, and ACE2 were measured in patients and controls using the ELISA technique. In contrast, other parameters were measured spectrophotometrically. The results showed decreased SpO2 and albumin and an increase in the serum biochemical parameters (glucose, urea, creatinine, D-dimer, ACE2, DKK1, and HMGB1) in COVID-19 patients compared with the control group. In COVID-19 patients, the percentages of the lung abnormalities in CT-scan% are 40.67±11.84. The results showed that those patients with LACTS patients are slightly older and have lower SpO2 than the patients without the LACTS group. ACE2 shows a significant correlation with SpO2 (ρ = 0.336, p<0.01) and a negative correlation with albumin (ρ = -0.197, p<0.05). Other parameters showed no significant correlation with the measured biomarkers. In conclusion, COVID-19 patients have higher ACE, DKK1, and HMGB1 indicating the involvement of the pathways of these biomarkers in the disease progression including lung injury.

Based on improved deep convolutional neural network model pneumonia image classification

Pneumonia remains the leading infectious cause of death in children under the age of five, killing about 700,000 children each year and affecting 7% of the world’s population. X-ray images of lung become the key to the diagnosis of this disease, skilled doctors in the diagnosis of a certain degree of subjectivity, if the use of computer-aided medical diagnosis to automatically detect lung abnormalities, will improve the accuracy of diagnosis. This research aims to introduce a deep learning technology based on the combination of Xception neural network and long-term short-term memory (LSTM), which can realize automatic diagnosis of patients with pneumonia in X-ray images. First, the model uses the Xception network to extract the deep features of the data, passes the extracted features to the LSTM, and then the LSTM detects the extracted features, and finally selects the most needed features. Secondly, in the training set samples, the traditional cross-entropy loss cannot more balance the mismatch between categories. Therefore, this research combines Pearson’s feature selection ideas, fusion of the correlation between the two loss functions, and optimizes the problem. The experimental results show that the accuracy rate of this paper is 96%, the receiver operator characteristic curve accuracy rate is 99%, the precision rate is 98%, the recall rate is 91%, and the F1 score accuracy rate is 94%. Compared with the existing technical methods, the research has achieved expected results on the currently available datasets. And assist doctors to provide higher reliability in the classification task of childhood pneumonia.

Developmental Pathways Underlying Lung Development and Congenital Lung Disorders

Lung organogenesis is a highly coordinated process governed by a network of conserved signaling pathways that ultimately control patterning, growth, and differentiation. This rigorously regulated developmental process culminates with the formation of a fully functional organ. Conversely, failure to correctly regulate this intricate series of events results in severe abnormalities that may compromise postnatal survival or affect/disrupt lung function through early life and adulthood. Conditions like congenital pulmonary airway malformation, bronchopulmonary sequestration, bronchogenic cysts, and congenital diaphragmatic hernia display unique forms of lung abnormalities. The etiology of these disorders is not yet completely understood; however, specific developmental pathways have already been reported as deregulated. In this sense, this review focuses on the molecular mechanisms that contribute to normal/abnormal lung growth and development and their impact on postnatal survival.