Detection of COVID19 disease and triage of patients with artificial intelligence learning from chest x-rays

The automated analysis of RX images using Artificial Intelligence (AI) and Deep Learning (DL) models has great potential for a rapid diagnosis of COVID19. A robust and accurate DL model can serve as a detection and support system for medical decision making. A set of recent studies claim to have achieved impressive sensitivities (> 90%), higher than those of expert radiologists (69%). These high sensitivities are due to bias in the most widely used dataset, COVID19 Image Data Collection. This set includes a small number of positive cases of COVID19, coming from very heterogeneous sources (at least 15 countries) and the majority of the cases are seriously ill, which drastically reduces their clinical value. To contrast non-COVID classes, they use RX images from various public repositories of lung diseases. The resulting models have no clinical value as they will not be able to detect patients of low and moderate severity, which are the goal of a clinical screening system. Faced with this situation, there is an enormous need for higher quality data sets constructed under the same clinical protocol and in close collaboration with expert radiologists.

Federated machine learning is an approach that enables DL models to be trained on-premises, in a distributed way, sent to a central server where their weights are added, and a consolidated model is forwarded to all devices / nodes for continue learning. It uses distributed computing concepts to keep track of each model in the nodes and add and update models in each of the nodes.


The overall objective of the project is to develop a robust system for the detection of COVID19 and bacterial and viral pneumonias for the triage of patients. It is divided into five specific objectives:

  1. Expand the COVIDGR database with COVID19 radiographs from different national and international hospitals and make it public.
  2. Develop an intelligent system that increases detection in the 3 severity stages of COVID19, with the use of data quality techniques (smart data), DL and multi-class ranking, and the possible inclusion of clinical data.
  3. Develop a robust model on different X-ray regimens (different hospitals) using federated learning, detecting COVID19 for any X-ray machine.
  4. Develop DL models to distinguish between COVID19 and different lung diseases, such as pleural effusion, atelectasis, cardiomegaly, infiltrate, pulmonary nodule, pneumonia, ...
  5. Design methods to interpret / explain the decisions of DL models using new XAI methodologies.