Construction and Validation of a General Medical Image Dataset for Pretraining
Journal of Imaging Informatics in Medicine · 15.08.2024 · 38 (2) · 1051-1061
DOI: 10.1007/s10278-024-01226-3 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Journal of Imaging Informatics in Medicine, online erschienen am 15.08.2024. Verfasst von Rongguo Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Academy for Multidisciplinary Studies, Capital Normal University, 105 West Third Ring Road North, Haidian District, Beijing, China. zrongguo@cnu.edu.…. Hauptthemen laut MEDLINE: Deep Learning, Image Processing, Computer-Assisted, Diagnostic Imaging. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China.
Abstract (Originalsprache)
In the field of deep learning for medical image analysis, training models from scratch are often used and sometimes, transfer learning from pretrained parameters on ImageNet models is also adopted. However, there is no universally accepted medical image dataset specifically designed for pretraining models currently. The purpose of this study is to construct such a general dataset and validate its effectiveness on downstream medical imaging tasks, including classification and segmentation. In this work, we first build a medical image dataset by collecting several public medical image datasets (CPMID). And then, some pretrained models used for transfer learning are obtained based on CPMID. Various-complexity Resnet and the Vision Transformer network are used as the backbone architectures. In the tasks of classification and segmentation on three other datasets, we compared the experimental results of training from scratch, from the pretrained parameters on ImageNet, and from the pretrained parameters on CPMID. Accuracy, the area under the receiver operating characteristic curve, and class activation map are used as metrics for classification performance. Intersection over Union as the metric is for segmentation evaluation. Utilizing the pretrained parameters on the constructed dataset CPMID, we achieved the best classification accuracy, weighted accuracy, and ROC-AUC values on three validation datasets. Notably, the average classification accuracy outperformed ImageNet-based results by 4.30%, 8.86%, and 3.85% respectively. Furthermore, we achieved the optimal balanced outcome of performance and efficiency in both classification and segmentation tasks. The pretrained parameters on the proposed dataset CPMID are very effective for common tasks in medical image analysis such as classification and segmentation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Academy for Multidisciplinary Studies, Capital Normal University, 105 West Third Ring Road North, Haidian District, Beijing, China. zrongguo@cnu.edu.cn.
- Institute of Advanced Research, Infervision, Beijing, China.
- Academy for Multidisciplinary Studies, Capital Normal University, 105 West Third Ring Road North, Haidian District, Beijing, China.
Förderung
- National Key R&D Program of China
Zitieren
APA
Zhang, R., Pei, C., Shi, J., & Wang, S. (2024). Construction and Validation of a General Medical Image Dataset for Pretraining. Journal of Imaging Informatics in Medicine, 38(2), 1051-1061. https://doi.org/10.1007/s10278-024-01226-3
Vancouver
Zhang R, Pei C, Shi J, Wang S. Construction and Validation of a General Medical Image Dataset for Pretraining. Journal of Imaging Informatics in Medicine. 2024;38(2):1051-1061. doi:10.1007/s10278-024-01226-3
BibTeX
@article{Zhang2024,
author = {Zhang, Rongguo and Pei, Chenhao and Shi, Ji and Wang, Shaokang},
title = {Construction and Validation of a General Medical Image Dataset for Pretraining},
journal = {Journal of Imaging Informatics in Medicine},
year = {2024},
volume = {38},
number = {2},
pages = {1051--1061},
doi = {10.1007/s10278-024-01226-3}
}
EUVIMED