AUTHOR=Xu Yao , Li Yu , Yin Hongkun , Tang Wen , Fan Guohua 

TITLE=Consecutive Serial Non-Contrast CT Scan-Based Deep Learning Model Facilitates the Prediction of Tumor Invasiveness of Ground-Glass Nodules

JOURNAL=Frontiers in Oncology

VOLUME=Volume 11 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.725599

DOI=10.3389/fonc.2021.725599

ISSN=2234-943X

ABSTRACT=Introduction
Tumors are continuously evolving biological systems which can be monitored by medical imaging. Previous studies only focus on single timepoint images, whether the performance could be further improved by using serial non-contrast CT imaging obtained during nodules follow-up management remains unclear. In this study, we evaluated DL model for predicting tumor invasiveness of GGNs through analyzing time series CT images
Methods
A total of 168 pathologically confirmed GGN cases (48 non-invasive lesions and 120 invasive lesions) were retrospectively collected and randomly assigned to the development dataset (n=123) and independent testing dataset (n=45). All patients underwent consecutive non-contrast CT examinations and the baseline CT and 3-month follow-up CT images were collected. The gross region of interest (ROI) patches containing only tumor region and the full ROI patches including both tumor and peri-tumor regions were cropped from CT images. A baseline model was built on the image features and demographic features. Four DL models were proposed: two single-DL model using gross ROI (model 1) or full ROI patches (model 3) from baseline CT images, and two serial-DL models using gross ROI (model 2) or full ROI patches (model 4) from consecutive CT images (baseline scan and 3-month follow-up scan). In addition, a combined model integrating serial full ROI patches and clinical information was also constructed
Results
The area under the curve (AUC) of the baseline model, models 1, model 2, model 3 and model 4 were 0.562 (95% CI, 0.406-0.710), 0.693 (95% CI, 0.538–0.822), 0.787 (95% CI, 0.639–0.895), 0.727 (95% CI, 0.573–0.849), and 0.811 (95% CI, 0.667–0.912) in the independent  dataset, respectively. The results indicated  the peri-tumor region had potential to contribute to tumor invasiveness prediction, and the model performance was further improved by integrating imaging scans at multiple timepoints. Furthermore, the combined model showed best discrimination ability, with AUC, sensitivity, specificity and accuracy achieving 0.831 (95% CI, 0.690–0.926), 86.7%, 73.3% and 82.2%, respectively.
Conclusion
The DL model integrating full ROIs from serial CT images shows improved predictive performance in differentiating non-invasive from invasive GGNs than the model using only baseline CT images, which could benefit the clinical management of GGNs.