This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Three-Stage Frameworkfor Accurate Pediatric Chest X-ray Diagnosis Using Self-Supervision and Transfer Learning on Small Datasets
by
Yufeng Zhang
Yufeng Zhang 1,*
,
Joseph Kohne
Joseph Kohne 2
,
Emily Wittrup
Emily Wittrup 1
and
Kayvan Najarian
Kayvan Najarian 1,3,4,5
1
Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USA
2
Department of Pediatrics, University of Michigan, Ann Arbor, MI 48103, USA
3
Michigan Institute for Data Science (MIDAS), University of Michigan, Ann Arbor, MI 48109, USA
4
Department of Emergency Medicine, University of Michigan, Ann Arbor, MI 48109, USA
5
Max Harry Weil Institute for Critical Care Research and Innovation, University of Michigan, Ann Arbor, MI 48109, USA
*
Author to whom correspondence should be addressed.
Diagnostics 2024, 14(15), 1634; https://doi.org/10.3390/diagnostics14151634 (registering DOI)
Submission received: 22 June 2024
/
Revised: 19 July 2024
/
Accepted: 25 July 2024
/
Published: 29 July 2024
Abstract
Pediatric respiratory disease diagnosis and subsequent treatment require accurate and interpretable analysis. A chest X-ray is the most cost-effective and rapid method for identifying and monitoring various thoracic diseases in children. Recent developments in self-supervised and transfer learning have shown their potential in medical imaging, including chest X-ray areas. In this article, we propose a three-stage framework with knowledge transfer from adult chest X-rays to aid the diagnosis and interpretation of pediatric thorax diseases. We conducted comprehensive experiments with different pre-training and fine-tuning strategies to develop transformer or convolutional neural network models and then evaluate them qualitatively and quantitatively. The ViT-Base/16 model, fine-tuned with the CheXpert dataset, a large chest X-ray dataset, emerged as the most effective, achieving a mean AUC of 0.761 (95% CI: 0.759–0.763) across six disease categories and demonstrating a high sensitivity (average 0.639) and specificity (average 0.683), which are indicative of its strong discriminative ability. The baseline models, ViT-Small/16 and ViT-Base/16, when directly trained on the Pediatric CXR dataset, only achieved mean AUC scores of 0.646 (95% CI: 0.641–0.651) and 0.654 (95% CI: 0.648–0.660), respectively. Qualitatively, our model excels in localizing diseased regions, outperforming models pre-trained on ImageNet and other fine-tuning approaches, thus providing superior explanations. The source code is available online and the data can be obtained from PhysioNet.
Share and Cite
MDPI and ACS Style
Zhang, Y.; Kohne, J.; Wittrup, E.; Najarian, K.
Three-Stage Frameworkfor Accurate Pediatric Chest X-ray Diagnosis Using Self-Supervision and Transfer Learning on Small Datasets. Diagnostics 2024, 14, 1634.
https://doi.org/10.3390/diagnostics14151634
AMA Style
Zhang Y, Kohne J, Wittrup E, Najarian K.
Three-Stage Frameworkfor Accurate Pediatric Chest X-ray Diagnosis Using Self-Supervision and Transfer Learning on Small Datasets. Diagnostics. 2024; 14(15):1634.
https://doi.org/10.3390/diagnostics14151634
Chicago/Turabian Style
Zhang, Yufeng, Joseph Kohne, Emily Wittrup, and Kayvan Najarian.
2024. "Three-Stage Frameworkfor Accurate Pediatric Chest X-ray Diagnosis Using Self-Supervision and Transfer Learning on Small Datasets" Diagnostics 14, no. 15: 1634.
https://doi.org/10.3390/diagnostics14151634
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article metric data becomes available approximately 24 hours after publication online.