Baseline whole-lung CT features deriving from deep learning and radiomics: prediction of benign and malignant pulmonary ground-glass nodules

Wenjun Huang; Heng Deng; Zhaobin Li; Zhanda Xiong; Taohu Zhou; Yanming Ge; Jing Zhang; Wenbin Jing; Yayuan Geng; Xiang Wang; Wenting Tu; Peng Dong; Shiyuan Liu; Li Fan

doi:10.3389/fonc.2023.1255007

Baseline whole-lung CT features deriving from deep learning and radiomics: prediction of benign and malignant pulmonary ground-glass nodules

Front Oncol. 2023 Aug 17:13:1255007. doi: 10.3389/fonc.2023.1255007. eCollection 2023.

Authors

Wenjun Huang^{1

2

3}, Heng Deng⁴, Zhaobin Li⁵, Zhanda Xiong⁶, Taohu Zhou^{1

2}, Yanming Ge^{2

7}, Jing Zhang³, Wenbin Jing³, Yayuan Geng⁸, Xiang Wang¹, Wenting Tu¹, Peng Dong², Shiyuan Liu¹, Li Fan¹

Affiliations

¹ Department of Radiology, Changzheng Hospital, Naval Medical University, Shanghai, China.
² School of Medical Imaging, Weifang Medical University, Weifang, Shandong, China.
³ Department of Radiology, The Second People's hospital of Deyang, Deyang, Sichuan, China.
⁴ School of Medicine, Shanghai University, Shanghai, China.
⁵ Department of Radiation Oncology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai, China.
⁶ Department of Artificial Intelligence Medical Imaging, Tron Technology, Shanghai, China.
⁷ Medical Imaging Center, Affiliated Hospital of Weifang Medical University, Weifang, Shandong, China.
⁸ Clinical Research Institute, Shukun (Beijing) Technology Co., Ltd., Beijing, China.

Abstract

Objective: To develop and validate the model for predicting benign and malignant ground-glass nodules (GGNs) based on the whole-lung baseline CT features deriving from deep learning and radiomics.

Methods: This retrospective study included 385 GGNs from 3 hospitals, confirmed by pathology. We used 239 GGNs from Hospital 1 as the training and internal validation set; 115 and 31 GGNs from Hospital 2 and Hospital 3 as the external test sets 1 and 2, respectively. An additional 32 stable GGNs from Hospital 3 with more than five years of follow-up were used as the external test set 3. We evaluated clinical and morphological features of GGNs at baseline chest CT and extracted the whole-lung radiomics features simultaneously. Besides, baseline whole-lung CT image features are further assisted and extracted using the convolutional neural network. We used the back-propagation neural network to construct five prediction models based on different collocations of the features used for training. The area under the receiver operator characteristic curve (AUC) was used to compare the prediction performance among the five models. The Delong test was used to compare the differences in AUC between models pairwise.

Results: The model integrated clinical-morphological features, whole-lung radiomic features, and whole-lung image features (CMRI) performed best among the five models, and achieved the highest AUC in the internal validation set, external test set 1, and external test set 2, which were 0.886 (95% CI: 0.841-0.921), 0.830 (95%CI: 0.749-0.893) and 0.879 (95%CI: 0.712-0.968), respectively. In the above three sets, the differences in AUC between the CMRI model and other models were significant (all P < 0.05). Moreover, the accuracy of the CMRI model in the external test set 3 was 96.88%.

Conclusion: The baseline whole-lung CT features were feasible to predict the benign and malignant of GGNs, which is helpful for more refined management of GGNs.

Keywords: X-ray computed; deep learning; ground-glass nodules; lung cancer; radiomics; tomography.

Grants and funding

This work was supported by the National Natural Science Foundation of China [grant numbers 82171926, 81930049, 82202140]; National Key R&D Program of China [grant numbers 2022YFC2010002, 2022YFC2010000]; the program of Science and Technology Commission of Shanghai Municipality [grant numbers 21DZ2202600, 19411951300]; Medical imaging database construction program of National Health Commission [grant number YXFSC2022JJSJ002]; the clinical Innovative Project of Shanghai Changzheng Hospital [grant number 2020YLCYJ-Y24]; Shanghai Sailing Program [grant number 20YF1449000].