Omnidirectional 2.5D representation for COVID-19 diagnosis using chest CTs.

The Coronavirus Disease 2019 (COVID-19) has drastically overwhelmed most countries in the last two years, and image-based approaches using computerized tomography (CT) have been used to identify pulmonary infections. Recent methods based on deep learning either require time-consuming per-slice annotations (2D) or are highly data- and hardware-demanding (3D). This work proposes a novel omnidirectional 2.5D representation of volumetric chest CTs that allows exploring efficient 2D deep learning architectures while requiring volume-level annotations only. Our learning approach uses a siamese feature extraction backbone applied to each lung. It combines these features into a classification head that explores a novel combination of Squeeze-and-Excite strategies with Class Activation Maps. We experimented with public and in-house datasets and compared our results with state-of-the-art techniques. Our analyses show that our method provides better or comparable prediction quality and accurately distinguishes COVID-19 infections from other kinds of pneumonia and healthy lungs.

A Hierarchical Superpixel-Based Approach for DIBR View Synthesis.

View synthesis allows observers to explore static scenes using aligned color images and depth maps captured in a preset camera path. Among the options, depth-image-based rendering (DIBR) approaches have been effective and efficient since only one pair of color and depth map is required, saving storage and bandwidth. The present work proposes a novel DIBR pipeline for view synthesis that properly tackles the different artifacts that arise from 3D warping, such as cracks, disocclusions, ghosts, and out-of-field areas. A key aspect of our contributions relies on the adaptation and usage of a hierarchical image superpixel algorithm that helps to maintain structural characteristics of the scene during image reconstruction. We compare our approach with state-of-the-art methods and show that it attains the best average results in two common assessment metrics under public still-image and video-sequence datasets. Visual results are also provided, illustrating the potential of our technique in real-world applications.

Single-channel EEG sleep stage classification based on a streamlined set of statistical features in wavelet domain.

The main objective of this study was to enhance the performance of sleep stage classification using single-channel electroencephalograms (EEGs), which are highly desirable for many emerging technologies, such as telemedicine and home care. The proposed method consists of decomposing EEGs by a discrete wavelet transform and computing the kurtosis, skewness and variance of its coefficients at selected levels. A random forest predictor is trained to classify each epoch into one of the Rechtschaffen and Kales' stages. By performing a comprehensive set of tests on 106,376 epochs available from the Physionet public database, it is demonstrated that the use of these three statistical moments has enhanced performance when compared to their application in the time domain. Furthermore, the chosen set of features has the advantage of exhibiting a stable classification performance for all scoring systems, i.e., from 2- to 6-state sleep stages. The stability of the feature set is confirmed with ReliefF tests which show a performance reduction when any individual feature is removed, suggesting that this group of feature cannot be further reduced. The accuracies and kappa coefficients yield higher than 90 % and 0.8, respectively, for all of the 2- to 6-state sleep stage classification cases.

HLA-DRB1* allele-associated genetic susceptibility and protection against multiple sclerosis in Brazilian patients.

Multiple sclerosis (MS) is a chronic autoimmune demyelinating disease of the central nervous system that causes neurological disorders in young adults. Previous studies in various populations highlighted an association between the HLA-DRB1*15 allele and MS. This study investigated the association between HLA-DRB1*15 and other HLA-DRB1 alleles and MS in a Brazilian Caucasian population sample from Londrina, Southern Brazil. HLA-DRB1 alleles were analyzed by polymerase chain reaction with specific sequence oligonucleotide primers in 119 MS patients and in 305 healthy blood donors as a control. Among the MS patients, 89 (75.0%) presented with relapsing remitting MS, 24 (20.0%) with secondary progressive MS and 6 (5.0%) with primary progressive MS. The frequency of the HLA-DRB1*15 allele observed in the MS Brazilian patients was similar to findings reported in previous studies carried out in populations worldwide. However, the results showed a higher frequency of the HLA-DRB1*15 allele in the MS patients compared to the controls, with a relative frequency of 0.1050 (10.50%) and 0.0443 (4.4%), respectively (OR=2.53; 95% CI 1.43-4.46; p=0.0009). A protector allele was also detected. The frequency of the HLA-DRB1*11 allele was reduced in the MS patients compared to the controls, with a relative frequency of 0.1345 (13.4%) and 0.1869 (18.7%), respectively (OR=0.67; 95% CI 0.44-1.03; p=0.0692). The results demonstrated that the HLA-DRB1*15 allele in heterozygosity is positively associated with MS (p=0.0079), and may be considered a genetic marker of susceptibility to the disease. A negative association between the HLA-DRB1*11 allele in homozygosity and MS was also verified (p=0.0418); this allele may be considered a genetic marker of resistance to MS in the Brazilian population.