Fusing radiomics and deep learning features for automated classification of multi‐type pulmonary nodule
Medical Physics · 2025-07 · 52 (7)
DOI: 10.1002/mp.17901 ↗At a glance
Journal article in Medical Physics, published online on 2025-05-20. Written by Lingyan Du and 5 co-authors. Institution: School of Automation and Information Engineering, Sichuan University of Science and Engineering, Zigong, People's Republic of China. Major MEDLINE topics: Deep Learning, Tomography, X-Ray Computed, Image Processing, Computer-Assisted, Multiple Pulmonary Nodules. Cited 3 times so far (Crossref); 41 references. Funded by: National Natural Science Youth Foundation of China.
Abstract (original language)
Background
The accurate classification of lung nodules is critical to achieving personalized lung cancer treatment and prognosis prediction. The treatment options for lung cancer and the prognosis of patients are closely related to the type of lung nodules, but there are many types of lung nodules, and the distinctions between certain types are subtle, making accurate classification based on traditional medical imaging technology and doctor experience challenging.
Purpose
In this study, a novel method was used to analyze quantitative features in CT images using CT radiomics to reveal the characteristics of pulmonary nodules, and then feature fusion was used to integrate radiomics features and deep learning features to improve the accuracy of classification.
Methods
This paper proposes a fusion feature pulmonary nodule classification method that fuses radiomics features with deep learning neural network features, aiming to automatically classify different types of pulmonary nodules (such as Malignancy, Calcification, Spiculation, Lobulation, Margin, and Texture). By introducing the Discriminant Correlation Analysis feature fusion algorithm, the method maximizes the complementarity between the two types of features and the differences between different classes. This ensures interaction between the information, effectively utilizing the complementary characteristics of the features. The LIDC‐IDRI dataset is used for training, and the fusion feature model has been validated for its advantages and effectiveness in classifying multiple types of pulmonary nodules.
Results
The experimental results show that the fusion feature model outperforms the single‐feature model in all classification tasks. The AUCs for the tasks of classifying Calcification, Lobulation, Margin, Spiculation, Texture, and Malignancy reached 0.9663, 0.8113, 0.8815, 0.8140, 0.9010, and 0.9316, respectively. In tasks such as nodule calcification and texture classification, the fusion feature model significantly improved the recognition ability of minority classes.
Conclusions
The fusion of radiomics features and deep learning neural network features can effectively enhance the overall performance of pulmonary nodule classification models while also improving the recognition of minority classes when there is a significant class imbalance.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- School of Automation and Information Engineering, Sichuan University of Science and Engineering, Zigong, People's Republic of China.
- Intelligent Perception and Control Key Laboratory of Sichuan Province, Sichuan University of Science and Engineering, Yibin, People's Republic of China.
- Department of Integrated Traditional Chinese and Western Medicine, Zigong First People's Hospital, Zigong, People's Republic of China.
Funding
- National Natural Science Youth Foundation of China
Cite
APA
Du, L., Tang, G., Che, Y., Ling, S., Chen, X., & Pan, X. (2025). Fusing radiomics and deep learning features for automated classification of multi‐type pulmonary nodule. Medical Physics, 52(7). https://doi.org/10.1002/mp.17901
Vancouver
Du L, Tang G, Che Y, Ling S, Chen X, Pan X. Fusing radiomics and deep learning features for automated classification of multi‐type pulmonary nodule. Medical Physics. 2025;52(7). doi:10.1002/mp.17901
BibTeX
@article{Du2025,
author = {Du, Lingyan and Tang, Guozhi and Che, Yue and Ling, Shihai and Chen, Xin and Pan, Xingliang},
title = {Fusing radiomics and deep learning features for automated classification of multi‐type pulmonary nodule},
journal = {Medical Physics},
year = {2025},
volume = {52},
number = {7},
doi = {10.1002/mp.17901}
}
EUVIMED