Explore the vast range of titles available.

The recognition of COVID-19 infection from X-ray images is an emerging field in the learning and computer vision community. Despite the great efforts that have been made in this field since the appearance of COVID-19 (2019), the field still suffers from two drawbacks. First, the number of available X-ray scans labeled as COVID-19-infected is relatively small. Second, all the works that have been carried out in the field are separate; there are no unified data, classes, and evaluation protocols. In this work, based on public and newly collected data, we propose two X-ray COVID-19 databases, which are three-class COVID-19 and five-class COVID-19 datasets. For both databases, we evaluate different deep learning architectures. Moreover, we propose an Ensemble-CNNs approach which outperforms the deep learning architectures and shows promising results in both databases. In other words, our proposed Ensemble-CNNs achieved a high performance in the recognition of COVID-19 infection, resulting in accuracies of 100% and 98.1% in the three-class and five-class scenarios, respectively. In addition, our approach achieved promising results in the overall recognition accuracy of 75.23% and 81.0% for the three-class and five-class scenarios, respectively. We make our databases of COVID-19 X-ray scans publicly available to encourage other researchers to use it as a benchmark for their studies and comparisons.

In recent years, automatic tissue phenotyping has attracted increasing interest in the Digital Pathology (DP) field. For Colorectal Cancer (CRC), tissue phenotyping can diagnose the cancer and differentiate between different cancer grades. The development of Whole Slide Images (WSIs) has provided the required data for creating automatic tissue phenotyping systems. In this paper, we study different hand-crafted feature-based and deep learning methods using two popular multi-classes CRC-tissue-type databases: Kather-CRC-2016 and CRC-TP. For the hand-crafted features, we use two texture descriptors (LPQ and BSIF) and their combination. In addition, two classifiers are used (SVM and NN) to classify the texture features into distinct CRC tissue types. For the deep learning methods, we evaluate four Convolutional Neural Network (CNN) architectures (ResNet-101, ResNeXt-50, Inception-v3, and DenseNet-161). Moreover, we propose two Ensemble CNN approaches: Mean-Ensemble-CNN and NN-Ensemble-CNN. The experimental results show that the proposed approaches outperformed the hand-crafted feature-based methods, CNN architectures and the state-of-the-art methods in both databases.

Some patients with idiopathic pulmonary fibrosis (IPF) develop severe acute respiratory failure (ARF) requiring admission to an intensive care unit (ICU) and ventilatory support. A limited number of observational studies have reported that noninvasive ventilation (NIV) can be an effective treatment to support breathing and to prevent use of invasive mechanical ventilation in these patients. This study aimed to retrospectively investigate the clinical status and outcomes in IPF patients receiving NIV for ARF and to identify those clinical and laboratory characteristics, which could be considered risk factors for its failure. This is a retrospective analysis of short-term outcomes in 18 IPF patients being administered NIV for ARF. This study was conducted in a 4-bed respiratory ICU (RICU) in a university hospital. Eighteen IPF patients who were administered NIV between January 1, 2005, and April 30, 2013, were included. The outcome measures are the need for endotracheal intubation despite NIV treatment and mortality rate during their RICU stay. The length of the patients' stay in the RICU and their survival rate following RICU admission were also evaluated. Noninvasive ventilation was successful in 8 patients and unsuccessful in 10 who required endotracheal intubation. All the patients in the NIV failure group died within 20.2 ± 15.3 days of intubation. The patients in the NIV success group spent fewer days in the RICU (11.6 ± 4.5 vs 24.6 ± 13.7; P = .0146). The median survival time was significantly shorter for the patients in the NIV failure with respect to the success group (18.0 [95% confidence interval {CI}, 9.0-25.0] vs 90.0 [95% CI, 65.0-305.0] days; P < .0001); the survival rate at 90 days was, likewise, lower in the NIV failure group (0% vs 34% ± 19.5%). At admission, the patients in the failure group had significantly higher respiratory rate values (36.9 ± 7.8 vs 30.5 ± 3.3 breaths/min; P = .036), plasma N-terminal fragment of the prohormone of B-type natriuretic peptide (NT-proBNP) levels (4528.8 ± 4012.8 vs 634.6 ± 808.0 pg/mL; P = .023) and serum C-reactive protein values (72.0 ± 50.0 vs 20.7 ± 24.0 μg/mL; P = .0289) with respect to those in the success group. Noninvasive ventilation failure was correlated to the plasma NT-proBNP levels at RICU admission (P = .0326) with an odds ratio of 12.2 (95% CI, 1.2 to infinity) in the patients with abnormally high values (>900 pg/mL). The outcome of IPF patients who were administered NIV was quite poor. The use of NIV was, nevertheless, found to be associated with clinical benefits in selected IPF patients, preventing the need for intubation and reducing the rate of complications/death. Elevated plasma NT-proBNP levels at the time of ICU admission is a simple clinical marker for poor NIV outcome.