COVID-19 diagnosis using AI

Obscuration to Clarity: Bone Suppression for Enhanced Localization in Pneumothorax Segmentation of Chest Radiographs

This study shows that bone suppression in chest radiographs improves pneumothorax segmentation accuracy across different models and datasets.

Bayesian automatic screening of pneumoniaand lung lesions localization from CT scans. Acombined method toward a more user-centredand explainable approach

This paper develops a Bayesian method for pneumonia and lung lesion localization in CT scans, combining uncertainty measures with object detection to improve explainability and reduce automation bias.

Comparative assessment of machine learning algorithms to predict severity of disease in COVID-19 patients based on eight cofactors

The paper compares machine learning algorithms to predict COVID-19 severity using eight cofactors and finds that most algorithms outperform SVM based on AUC scores.

Novel Automatic Classification of Human Adult Lung Alveolar Type II Cells Infected with SARS-CoV-2 through Deep Transfer Learning Approach

This paper develops a deep transfer learning approach to classify healthy and SARS-CoV-2 infected human alveolar type II cells using electron microscopy images, achieving high accuracy and speed.

Pneumonia Detection with Semantic Similarity Scores

This paper develops an abnormality detection method for pneumonia using self-supervised contrastive learning and Mahalanobis distance scores, outperforming previous unsupervised methods.

Single shot detector application for image disease localization

The paper applies a Single Shot Detector (SSD) with a VGG-16 backbone to predict anomaly locations in chest X-ray images.

Exponentiating pixel values for data augmentation to improve deep learning image classification in chest X-rays

This study evaluates using exponentiated pixel values for data augmentation in CNNs to classify chest X-rays, finding improved test accuracy at specific exponents.