Deep Learning on Chest X-ray Images to Detect and Evaluate Pneumonia Cases at the Era of COVID-19.

Coronavirus disease 2019 (COVID-19) is an infectious disease with first symptoms similar to the flu. COVID-19 appeared first in China and very quickly spreads to the rest of the world, causing then the 2019-20 coronavirus pandemic. In many cases, this disease causes pneumonia. Since pulmonary infections can be observed through radiography images, this paper investigates deep learning methods for automatically analyzing query chest X-ray images with the hope to bring precision tools to health professionals towards screening the COVID-19 and diagnosing confirmed patients. In this context, training datasets, deep learning architectures and analysis strategies have been experimented from publicly open sets of chest X-ray images. Tailored deep learning models are proposed to detect pneumonia infection cases, notably viral cases. It is assumed that viral pneumonia cases detected during an epidemic COVID-19 context have a high probability to presume COVID-19 infections. Moreover, easy-to-apply health indicators are proposed for estimating infection status and predicting patient status from the detected pneumonia cases. Experimental results show possibilities of training deep learning models over publicly open sets of chest X-ray images towards screening viral pneumonia. Chest X-ray test images of COVID-19 infected patients are successfully diagnosed through detection models retained for their performances. The efficiency of proposed health indicators is highlighted through simulated scenarios of patients presenting infections and health problems by combining real and synthetic health data.

Acoustic study of pharyngeal swallowing as a function of the volume and consistency of the bolus.

Cervical auscultation is a noninvasive technique for the exploration of swallowing and has been used since the 1960s. The aim of our study was to describe how the volume and consistency of the bolus affect swallowing acoustic sound characteristics in healthy subjects. Twenty-three subjects aged from 20 to 59 years were included (13 women and 10 men). A microphone mounted on a stethoscope chest piece, positioned on the skin on the right side in front of the posteroinferior border of the cricoid cartilage, was used; it was connected to a computer for acoustic recordings. Each subject swallowed 2-, 5-, and 10-ml aliquots of water, yogurt, and mashed potato. Each bolus was administered once, with a period of at least 30 s between each swallow. For each recorded sound, the total duration of the sound and the duration of each sound component (SC) (SC1, SC2, and SC3) and interval (IT1 and IT2) between the SCs were measured. For all records, the average duration of acoustic measures was calculated. Differences according to the volume and the consistency of the swallowed bolus were assessed using Student's t test for paired data. We calculated the percentage of recordings that included each SC. We also compared results between men and women using Student's t test. We successfully interpreted 540 of the 621 (87 %) records. The results indicated that the average total duration of the sound, and especially the average duration of SC2, increased with increasing volume and was greater for mashed potato than for the boluses of other consistencies. SC2 was present in all of the records.

Lung pneumonia severity scoring in chest X-ray images using transformers.

To create robust and adaptable methods for lung pneumonia diagnosis and the assessment of its severity using chest X-rays (CXR), access to well-curated, extensive datasets is crucial. Many current severity quantification approaches require resource-intensive training for optimal results. Healthcare practitioners require efficient computational tools to swiftly identify COVID-19 cases and predict the severity of the condition. In this research, we introduce a novel image augmentation scheme as well as a neural network model founded on Vision Transformers (ViT) with a small number of trainable parameters for quantifying COVID-19 severity and other lung diseases. Our method, named Vision Transformer Regressor Infection Prediction (ViTReg-IP), leverages a ViT architecture and a regression head. To assess the model's adaptability, we evaluate its performance on diverse chest radiograph datasets from various open sources. We conduct a comparative analysis against several competing deep learning methods. Our results achieved a minimum Mean Absolute Error (MAE) of 0.569 and 0.512 and a maximum Pearson Correlation Coefficient (PC) of 0.923 and 0.855 for the geographic extent score and the lung opacity score, respectively, when the CXRs from the RALO dataset were used in training. The experimental results reveal that our model delivers exceptional performance in severity quantification while maintaining robust generalizability, all with relatively modest computational requirements. The source codes used in our work are publicly available at https://github.com/bouthainas/ViTReg-IP .

SuperpixelGridMasks Data Augmentation: Application to Precision Health and Other Real-world Data.

A novel approach of data augmentation based on irregular superpixel decomposition is proposed. This approach called SuperpixelGridMasks permits to extend original image datasets that are required by training stages of machine learning-related analysis architectures towards increasing their performances. Three variants named SuperpixelGridCut, SuperpixelGridMean, and SuperpixelGridMix are presented. These grid-based methods produce a new style of image transformations using the dropping and fusing of information. Extensive experiments using various image classification models as well as precision health and surrounding real-world datasets show that baseline performances can be significantly outperformed using our methods. The comparative study also shows that our methods can overpass the performances of other data augmentations. SuperpixelGridCut, SuperpixelGridMean, and SuperpixelGridMix codes are publicly available at https://github.com/hammoudiproject/SuperpixelGridMasks.

Surface-based protein domains retrieval methods from a SHREC2021 challenge.

Proteins are essential to nearly all cellular mechanism and the effectors of the cells activities. As such, they often interact through their surface with other proteins or other cellular ligands such as ions or organic molecules. The evolution generates plenty of different proteins, with unique abilities, but also proteins with related functions hence similar 3D surface properties (shape, physico-chemical properties, …). The protein surfaces are therefore of primary importance for their activity. In the present work, we assess the ability of different methods to detect such similarities based on the geometry of the protein surfaces (described as 3D meshes), using either their shape only, or their shape and the electrostatic potential (a biologically relevant property of proteins surface). Five different groups participated in this contest using the shape-only dataset, and one group extended its pre-existing method to handle the electrostatic potential. Our comparative study reveals both the ability of the methods to detect related proteins and their difficulties to distinguish between highly related proteins. Our study allows also to analyze the putative influence of electrostatic information in addition to the one of protein shapes alone. Finally, the discussion permits to expose the results with respect to ones obtained in the previous contests for the extended method. The source codes of each presented method have been made available online.

A featureless approach to 3D polyhedral building modeling from aerial images.

This paper presents a model-based approach for reconstructing 3D polyhedral building models from aerial images. The proposed approach exploits some geometric and photometric properties resulting from the perspective projection of planar structures. Data are provided by calibrated aerial images. The novelty of the approach lies in its featurelessness and in its use of direct optimization based on image rawbrightness. The proposed framework avoids feature extraction and matching. The 3D polyhedral model is directly estimated by optimizing an objective function that combines an image-based dissimilarity measure and a gradient score over several aerial images. The optimization process is carried out by the Differential Evolution algorithm. The proposed approach is intended to provide more accurate 3D reconstruction than feature-based approaches. Fast 3D model rectification and updating can take advantage of the proposed method. Several results and evaluations of performance from real and synthetic images show the feasibility and robustness of the proposed approach.

MaskedFace-Net - A dataset of correctly/incorrectly masked face images in the context of COVID-19.

Wearing face masks appears as a solution for limiting the spread of COVID-19. In this context, efficient recognition systems are expected for checking that people faces are masked in regulated areas. Hence, a large dataset of masked faces is necessary for training deep learning models towards detecting people wearing masks and those not wearing masks. Currently, there are no available large dataset of masked face images that permits to check if faces are correctly masked or not. Indeed, many people are not correctly wearing their masks due to bad practices, bad behaviors or vulnerability of individuals (e.g., children, old people). For these reasons, several mask wearing campaigns intend to sensitize people about this problem and good practices. In this sense, this work proposes an image editing approach and three types of masked face detection dataset; namely, the Correctly Masked Face Dataset (CMFD), the Incorrectly Masked Face Dataset (IMFD) and their combination for the global masked face detection (MaskedFace-Net). Realistic masked face datasets are proposed with a twofold objective: i) detecting people having their faces masked or not masked, ii) detecting faces having their masks correctly worn or incorrectly worn (e.g.; at airport portals or in crowds). To the best of our knowledge, no large dataset of masked faces provides such a granularity of classification towards mask wearing analysis. Moreover, this work globally presents the applied mask-to-face deformable model for permitting the generation of other masked face images, notably with specific masks. Our datasets of masked faces (137,016 images) are available at https://github.com/cabani/MaskedFace-Net. The dataset of face images Flickr-Faces-HQ3 (FFHQ), publicly made available online by NVIDIA Corporation, has been used for generating MaskedFace-Net.

Transoral robotic surgery versus conventional surgery in treatment for squamous cell carcinoma of the upper aerodigestive tract.

BACKGROUND: The purpose of our work was to compare a group of patients undergoing transoral robotic surgery (TORS group) for squamous cell carcinoma of the upper aerodigestive tract and a matched group of patients undergoing conventional surgery (conventional surgery group) for the same indication. METHODS: In this retrospective single-center study, 26 patients were included in each group. RESULTS: There were significantly fewer tracheotomies in the TORS group (p < .001). The mean durations of feeding by nasogastric tube and hospitalization were shorter for the TORS group (p = .001). There was no significant difference in disease-free survival at 3 years (p = .76). Mean treatment cost was $7124 lower for the TORS group (p = .03). CONCLUSION: This comparative study shows that robotic technology can be used to treat selected squamous cell carcinomas of the upper aerodigestive tract, reducing morbidity and treatment costs while providing equivalent cancer control at 3 years.

[Hearing loss and Alzheimer's disease]. / Déficit auditif et maladie d'Alzheimer.

Recent studies suggest that subjects with hearing loss are more likely to develop Alzheimer's disease. Hearing loss can be consecutive to presbycusis and/or to central auditory dysfunction. Standard audiometric measures (pure tone and speech intelligibility) allow the diagnosis of presbycusis. However, to demonstrate central auditory dysfunction, specific audiometric tests are needed such as noisy and/or dichotic tests. Actually, no consensus exists to investigate hearing loss in people with Alzheimer's disease though hearing loss may be an early manifestation of Alzheimer's disease. Until now, investigations and clinical procedure related to the diagnosis of Alzheimer's disease ignored the hearing ability of the patient. However, the major part of care management and investigations implies the patient's communication ability with the caregivers. Hearing loss may be one of the most unrecognized deficit in subjects with Alzheimer's disease. Auditory rehabilitation could benefit to the patient in order to lessen cognitive decline, but this must be investigated during longitudinal studies in order to clearly demonstrate their efficiency.