Dealing with distribution mismatch in semi-supervised deep learning for COVID-19 detection using chest X-ray images: A novel approach using feature densities

  title={Dealing with distribution mismatch in semi-supervised deep learning for COVID-19 detection using chest X-ray images: A novel approach using feature densities},
  author={Saul Calderon-Ramirez and Shengxiang Yang and David A. Elizondo and Armaghan Moemeni},
  journal={Applied Soft Computing},
  pages={108983 - 108983}

Figures and Tables from this paper

Improving Semi-supervised Deep Learning by using Automatic Thresholding to Deal with Out of Distribution Data for COVID-19 Detection using Chest X-ray Images

An automatic thresholding method is proposed toter out-of-distribution data in the unlabeled dataset using the Mahalanobis distance using the feature space built by a pre-trained Image-net Feature Extractor to score each unlabeling observation.



Dealing with Scarce Labelled Data: Semi-supervised Deep Learning with Mix Match for Covid-19 Detection Using Chest X-ray Images

A semi-supervised deep learning framework based on the Mix Match architecture to classify chest X-rays into Covid-19, pneumonia and healthy cases is developed and test and shows an accuracy increase of around 15% under low labelled / unlabelled data ratio.

Deep Learning for Screening COVID-19 using Chest X-Ray Images

A new concept called domain extension transfer learning (DETL) is proposed, with pre-trained deep convolutional neural network, on a related large chest X-Ray dataset that is tuned for classifying between four classes viz. normal, pneumonia, other_disease, and Covid – 19.

Deep learning approaches for COVID-19 detection based on chest X-ray images

A real use case of semi-supervised learning for mammogram classification in a local clinic of Costa Rica

It is shown that the use of a semi-supervised deep learning combined with transfer learning and data augmentation can provide a meaningful advantage when using scarce labelled observations, as mammogram datasets are often very imbalanced.

The Effectiveness of Image Augmentation in Deep Learning Networks for Detecting COVID-19: A Geometric Transformation Perspective

This paper empirically examined the influence of augmentation with respect to detection accuracy, dataset diversity, augmentation methodology, and network size, and provided clinical perspectives on geometric augmentation to consider regarding the development of a robust COVID-19 X-ray-based detector.

Semi-Supervised Learning under Class Distribution Mismatch

This work addresses under-studied and realistic SSL problem by a novel algorithm named Uncertainty-Aware Self-Distillation (UASD), which produces soft targets that avoid catastrophic error propagation, and empower learning effectively from unconstrained unlabelled data with out-of-distribution (OOD) samples.

Diagnosing COVID-19 pneumonia from x-ray and CT images using deep learning and transfer learning algorithms

A simple convolution neural network and modified pre-trained AlexNet model are applied on the prepared X-rays and CT scan images and the result shows that the utilized models can provide accuracy up to 98% via pre- trained network and 94.1% accuracy by using the modified CNN.

Deep learning based detection and analysis of COVID-19 on chest X-ray images

The PA view of chest x-ray scans for covid-19 affected patients as well as healthy patients are taken and deep learning-based CNN models are used, which give the highest accuracy for detecting Chest X-rays images as compared to other models.

Improving Uncertainty Estimation With Semi-Supervised Deep Learning for COVID-19 Detection Using Chest X-Ray Images

This work implements a COVID-19 infection detection system based on chest X-ray images with uncertainty estimation, and proposes the usage of the Jensen-Shannon distance between the uncertainty distributions of correct and incorrect estimations.