Related Experiment Video
Updated: Jun 5, 2025

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
Distribution-based detection of radiographic changes in pneumonia patterns: A COVID-19 case study
Sofia C Pereira1,2, Joana Rocha1,2, Aurélio Campilho1,2
1Institute for Systems and Computer Engineering, Technology and Science (INESC-TEC), Portugal.
This study introduces a novel population-based approach for detecting COVID-19 pneumonia on chest radiographs by analyzing distributional anomalies. This method outperforms traditional single-image analysis, offering a potential early warning system for emerging respiratory diseases.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Public Health
Background:
- Chest radiograph classification is crucial for diagnosing respiratory diseases.
- The COVID-19 pandemic heightened the need for accurate radiographic analysis.
- Conventional methods struggle with overlapping radiological features between COVID-19 and other pneumonias.
Purpose of the Study:
- To develop a novel approach for identifying COVID-19 pneumonia using distributional anomaly detection.
- To compare the efficacy of population-based (distributional) versus instance-based methods for COVID-19 detection.
- To establish a potential early warning system for emerging infectious respiratory diseases.
Main Methods:
- Utilized a population-based approach focusing on sets of chest radiographs.
- Employed distributional anomaly detection to identify deviations from normal pneumonia patterns.
- Used an autoencoder for feature extraction and compared instance-based and distribution-based assessments.
Main Results:
- The proposed distribution-based methodology demonstrated superior performance compared to conventional instance-based techniques.
- The approach effectively identified radiographic changes associated with COVID-19 positive cases.
- Significant separability was observed between COVID-positive and COVID-negative pneumonia radiographs using the distributional method.
Conclusions:
- Distributional anomaly detection offers a more robust method for identifying COVID-19 pneumonia than instance-based approaches.
- This approach can serve as an early warning system for detecting shifts in radiographic data, signaling potential outbreaks.
- Continuous monitoring of distributional shifts in medical imaging data can enable prompt public health responses to emerging health threats.
Related Concept Videos
Pneumonia III: Complications and Assessment
Pneumonia II: Pathophysiology
Radiological Investigation I: X-ray and CT
Radiological Investigation II: MRI and Ventilation Perfusion Scan
Magnetic Resonance Imaging (MRI) and Ventilation Perfusion Scans are two radiological investigations that offer detailed diagnostic images of the body, particularly lung structures.
MRI
MRI uses magnetic fields and radiofrequency signals to distinguish between normal and abnormal tissues. This technology provides a more detailed diagnostic image than CT scans, enabling it to characterize pulmonary nodules, stage bronchogenic carcinoma, and evaluate inflammatory activity in...
Pulmonary Tuberculosis IV
Several diagnostic approaches are used to detect TB. The conventional method is the Tuberculin Skin Test (TST), also known as the Mantoux test. However, this method has...
Pneumonia IV: Management
Bacterial Pneumonia Treatment
For bacterial pneumonia, antibiotics serve as the cornerstone of therapy. Initial treatment often begins with empirical antibiotics, tailored to the anticipated causative organism and adjusted based on culture results. Key antibiotic choices include:

