CLSSL-ResNet: Predicting malignancy of solitary pulmonary nodules from CT images by chimeric label with self-supervised learning
Journal of X-Ray Science and Technology · 2023
DOI: 10.3233/xst-230063 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of X-Ray Science and Technology, 2023. Verfasst von Tianhu Zhao und 8 weiteren Autor:innen. Beteiligte Einrichtung: College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China. Hauptthemen laut MEDLINE: Solitary Pulmonary Nodule, Lung Neoplasms, Adenocarcinoma of Lung, Multiple Pulmonary Nodules. Die Arbeit nennt 17 Literaturangaben.
Abstract (Originalsprache)
BACKGROUND: Pulmonary granulomatous nodules (GN) with spiculation or lobulation have a similar morphological appearance to solid lung adenocarcinoma (SADC) under computed tomography (CT). However, these two kinds of solid pulmonary nodules (SPN) have different malignancies and are sometimes misdiagnosed. OBJECTIVE: This study aims to predict malignancies of SPNs by a deep learning model automatically. METHODS: A chimeric label with self-supervised learning (CLSSL) is proposed to pre-train a ResNet-based network (CLSSL-ResNet) for distinguishing isolated atypical GN from SADC in CT images. The malignancy, rotation, and morphology labels are integrated into a chimeric label and utilized to pre-train a ResNet50. The pre-trained ResNet50 is then transferred and fine-tuned to predict the malignancy of SPN. Two image datasets of 428 subjects (Dataset1, 307; Dataset2, 121) from different hospitals are collected. Dataset1 is divided into training, validation, and test data by a ratio of 7:1:2 to develop the model. Dataset2 is utilized as an external validation dataset. RESULTS: CLSSL-ResNet achieves an area under the ROC curve (AUC) of 0.944 and an accuracy (ACC) of 91.3%, which was much higher than that of the consensus of two experienced chest radiologists (77.3%). CLSSL-ResNet also outperforms other self-supervised learning models and many counterparts of other backbone networks. In Dataset2, AUC and ACC of CLSSL-ResNet are 0.923 and 89.3%, respectively. Additionally, the ablation experiment result indicates higher efficiency of the chimeric label. CONCLUSION: CLSSL with morphology labels can increase the ability of feature representation by deep networks. As a non-invasive method, CLSSL-ResNet can distinguish GN from SADC via CT images and may support clinical diagnoses after further validation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China.
- Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University, Shenyang, China.
- Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, China.
- Department of Radiology, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China.
- Department of Radiology, The Fifth Affiliated Hospital of Guangzhou Medical University, Guangzhou, China.
- Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ, USA.
Zitieren
APA
Zhao, T., Qi, S., Yue, Y., Zhang, B., Li, J., Wen, Y., Yao, Y., Qian, W., & Guan, Y. (2023). CLSSL-ResNet: Predicting malignancy of solitary pulmonary nodules from CT images by chimeric label with self-supervised learning. Journal of X-Ray Science and Technology. https://doi.org/10.3233/xst-230063
Vancouver
Zhao T, Qi S, Yue Y, Zhang B, Li J, Wen Y, et al. CLSSL-ResNet: Predicting malignancy of solitary pulmonary nodules from CT images by chimeric label with self-supervised learning. Journal of X-Ray Science and Technology. 2023. doi:10.3233/xst-230063
BibTeX
@article{Zhao2023,
author = {Zhao, Tianhu and Qi, Shouliang and Yue, Yong and Zhang, Baihua and Li, Jingxu and Wen, Yanhua and Yao, Yudong and Qian, Wei and Guan, Yubao},
title = {CLSSL-ResNet: Predicting malignancy of solitary pulmonary nodules from CT images by chimeric label with self-supervised learning},
journal = {Journal of X-Ray Science and Technology},
year = {2023},
doi = {10.3233/xst-230063}
}
EUVIMED