Related Experiment Video
Updated: Jul 2, 2025
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
14.2K
Exploration of Interpretability Techniques for Deep COVID-19 Classification Using Chest X-ray Images
Soumick Chatterjee1,2,3, Fatima Saad4,5, Chompunuch Sarasaen4,5,6
1Data and Knowledge Engineering Group, Otto von Guericke University, 39106 Magdeburg, Germany.
Journal of Imaging
|February 23, 2024
Summary
Deep learning models accurately diagnosed COVID-19 from chest X-rays, with an ensemble model achieving an F1 score of 0.89. Interpretability analysis revealed ResNet models offered the clearest insights into diagnostic decisions.
Area of Science:
- Medical Imaging and Artificial Intelligence
- Deep Learning in Healthcare
- Radiology and Diagnostic Imaging
Background:
- The COVID-19 pandemic highlighted the need for rapid and accurate diagnostic tools.
- Medical imaging, particularly chest X-rays, is crucial for identifying respiratory illnesses.
- Artificial intelligence (AI) offers potential to enhance diagnostic accuracy and efficiency.
Purpose of the Study:
- To evaluate the performance of five deep learning models and their ensemble for classifying COVID-19, pneumonia, and healthy subjects using chest X-ray images.
- To assess the interpretability of these deep learning models using various local and global techniques.
- To determine the most effective model for COVID-19 diagnosis based on performance and interpretability.
Main Methods:
- Utilized five deep learning models (ResNet18, ResNet34, InceptionV3, InceptionResNetV2, DenseNet161) for multi-label classification of chest X-ray images.
- Employed an ensemble approach with majority voting to combine predictions from individual models.
- Applied local interpretability methods (occlusion, saliency, etc.) and global techniques (neuron activation profiles) to analyze model behavior.
Main Results:
- The ensemble model achieved a mean micro F1 score of 0.89 for COVID-19 classification.
- Individual model performance for COVID-19 classification ranged from a mean micro F1 score of 0.66 to 0.875.
- Qualitative analysis indicated that ResNet models provided superior interpretability compared to other evaluated networks.
Conclusions:
- Deep learning models, especially ensembles, demonstrate high efficacy in diagnosing COVID-19 from chest X-rays.
- Model interpretability is essential for understanding and trusting AI-driven diagnostic tools in clinical settings.
- The study underscores the value of integrating interpretability methods into the model selection process for medical AI applications.
Related Concept Videos
01:20Imaging Studies for Cardiovascular System III: X-Ray
188
The most common cardiovascular diagnostic test is an X-ray. It produces images of the heart, blood vessels, and adjacent structures.
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
188
01:30Radiological Investigation I: X-ray and CT
238
Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...
238
01:24X-ray Imaging
5.5K
German physicist Wilhelm Röntgen (1845–1923) was experimenting with electrical current when he discovered that a mysterious and invisible "ray" would pass through his flesh but leave an outline of his bones on a screen coated with a metal compound. In 1895, Röntgen made the first durable record of the internal parts of a living human: an "X-ray" image (as it came to be called) of his wife’s hand. Scientists worldwide quickly began their own experiments with...
5.5K