CNNs trained with adult data are useful in pediatrics. A pneumonia classification example
PLOS ONE · 2024
DOI: 10.1371/journal.pone.0306703 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, 2024. Verfasst von Maria Rollan-Martinez-Herrera und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Applied Chest Imaging Laboratory, Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts, United States…. Hauptthemen laut MEDLINE: Pneumonia. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHLBI NIH HHS, NLM NIH HHS, NHLBI Division of Intramural Research.
Abstract (Originalsprache)
Background and objectives The scarcity of data for training deep learning models in pediatrics has prompted questions about the feasibility of employing CNNs trained with adult images for pediatric populations. In this work, a pneumonia classification CNN was used as an exploratory example to showcase the adaptability and efficacy of such models in pediatric healthcare settings despite the inherent data constraints.
Methods
To develop a curated training dataset with reduced biases, 46,947 chest X-ray images from various adult datasets were meticulously selected. Two preprocessing approaches were tried to assess the impact of thoracic segmentation on model attention outside the thoracic area. Evaluation of our approach was carried out on a dataset containing 5,856 chest X-rays of children from 1 to 5 years old.
Results
An analysis of attention maps indicated that networks trained with thorax segmentation placed less attention on regions outside the thorax, thus eliminating potential bias. The ensuing network exhibited impressive performance when evaluated on an adult dataset, achieving a pneumonia discrimination AUC of 0.95. When tested on a pediatric dataset, the pneumonia discrimination AUC reached 0.82.
Conclusions
The results of this study show that adult-trained CNNs can be effectively applied to pediatric populations. This could potentially shift focus towards validating adult models over pediatric population instead of training new CNNs with limited pediatric data. To ensure the generalizability of deep learning models, it is important to implement techniques aimed at minimizing biases, such as image segmentation or low-quality image exclusion.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Radiology, Applied Chest Imaging Laboratory, Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts, United States of America.
- Division of Pulmonary and Critical Care Medicine, Chest Imaging Laboratory, Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts, United States of America.
ORCID-Profile: Rubén San José Estépar, Pietro Nardelli
Förderung
- NHLBI NIH HHS
- NLM NIH HHS
- NHLBI Division of Intramural Research
- Fundación Alfonso Martín Escudero
Zitieren
APA
Rollan-Martinez-Herrera, M., Díaz, A. A., Estépar, R. S. J., Sanchez-Ferrero, G. V., Ross, J. C., Estépar, R. S. J., & Nardelli, P. (2024). CNNs trained with adult data are useful in pediatrics. A pneumonia classification example. PLOS ONE. https://doi.org/10.1371/journal.pone.0306703
Vancouver
Rollan-Martinez-Herrera M, Díaz AA, Estépar RSJ, Sanchez-Ferrero GV, Ross JC, Estépar RSJ, et al. CNNs trained with adult data are useful in pediatrics. A pneumonia classification example. PLOS ONE. 2024. doi:10.1371/journal.pone.0306703
BibTeX
@article{RollanMartinezHerrera2024,
author = {Rollan-Martinez-Herrera, Maria and Díaz, Alejandro A and Estépar, Rubén San José and Sanchez-Ferrero, Gonzalo Vegas and Ross, James C and Estépar, Raúl San José and Nardelli, Pietro},
title = {CNNs trained with adult data are useful in pediatrics. A pneumonia classification example},
journal = {PLOS ONE},
year = {2024},
doi = {10.1371/journal.pone.0306703}
}
EUVIMED