E-resources
Peer reviewed
-
Bahani, Mourad; El Ouaazizi, Aziza; Avram, Robert; Maalmi, Khalil
Displays, July 2024, 2024-07-00, Volume: 83Journal Article
In the field of Artificial Intelligence (AI) and Medicine, chest X-ray images are crucial for diagnosing various diseases. However, training AI models presents challenges, particularly with limited data or cases involving significant pathology or minor anomalies. To address the constraint of limited data, data augmentation has emerged as a popular technique in medical imaging. One promising approach to augmenting chest X-ray images involves leveraging text-to-image generation, which transforms textual disease descriptions into synthetic images. This technique effectively rectifies class imbalances and enhances the accuracy and reliability of AI models used in medical imaging applications. This study introduces a text-to-image generation architecture based on DF-GAN to augment chest X-ray images. The study aims to assess the impact of augmented data on the performance of two AI models, namely VGG16 and ResNet50, in a classification task. The experimentation is conducted on two challenging datasets, namely Chest X-rays from Indiana University and NIH Chest X-rays. The findings reveal that integrating text-to-image generated data enhances sensitivity by 2.1%, specificity by 1.9%, and AUC by 1.4%, while also mitigating overfitting during training across both datasets. These results underscore the potential of text-to-image generation in bolstering the accuracy and robustness of AI models employed in medical imaging tasks. •Proposed text-to-image generation using DF-GAN to augment chest X-ray images.•Demonstrated impact of augmented data on VGG16 and ResNet50 in classifying X-rays.•Evaluated technique on challenging datasets: Chest X-rays (IU) and NIH X-rays.•Augmented data improved sensitivity by 2.1% and specificity by 1.9% across datasets.•Text-to-image generation mitigated overfitting and enhanced accuracy in medical imaging.
![loading ... loading ...](themes/default/img/ajax-loading.gif)
Shelf entry
Permalink
- URL:
Impact factor
Access to the JCR database is permitted only to users from Slovenia. Your current IP address is not on the list of IP addresses with access permission, and authentication with the relevant AAI accout is required.
Year | Impact factor | Edition | Category | Classification | ||||
---|---|---|---|---|---|---|---|---|
JCR | SNIP | JCR | SNIP | JCR | SNIP | JCR | SNIP |
Select the library membership card:
If the library membership card is not in the list,
add a new one.
DRS, in which the journal is indexed
Database name | Field | Year |
---|
Links to authors' personal bibliographies | Links to information on researchers in the SICRIS system |
---|
Source: Personal bibliographies
and: SICRIS
The material is available in full text. If you wish to order the material anyway, click the Continue button.