Comparison and fusion prediction model for lung adenocarcinoma with micropapillary and solid pattern using clinicoradiographic, radiomics and deep learning features

Expression and role of FKBPL in lung adenocarcinoma

Dysregulated expression of FK506-binding protein like (FKBPL) has been demonstrated to play crucial roles in tumour development. However, the role of FKBPL in lung adenocarcinoma (ADC) remains unclear. Using immunohistochemical staining, we showed that FKBPL expression was significantly lower in lung ADC than the normal tissues (P < 0.0001). Patients with well or moderately differentiated tumours have higher FKBPL expression compared with patients with poor differentiated tumours (P = 0.037). However, no significant associations were found between FKBPL expression and other clinicopathological variables (P > 0.05 for all). Cox univariate analysis showed that high FKBPL expression was correlated with prolonged overall survival (OS) (P = 0.010). Kaplan-Meier analysis further confirmed that the FKBPL-low group showed a significantly shorter OS than the FKBPL-high group (P = 0.0081). FKBPL expression was not shown as an independent prognostic factor for OS in the multivariate analysis (P = 0.063). Moreover, our study demonstrated that FKBPL could suppress the proliferation of lung ADC cells by delaying cell cycle G1/S phase transition. In addition, FKBPL resulted in increased apoptosis in lung ADC cells. Using the Human Apoptosis Array Kit, we observed that overexpression of FKBPL in lung ADC A549 cells significantly decreased the anti-apoptotic proteins, including heat shock protein 32 (HSP32), heat shock protein 27 (HSP27), and paraoxonase-2 (PON2). FKBPL depletion significantly attenuated the pro-apoptotic protein, phospho-p53 (S46), in lung ADC H1975 cells. These new findings provide an experimental basis for further theoretical investigation of lung ADC.

Predicting micropapillary or solid pattern of lung adenocarcinoma with CT-based radiomics, conventional radiographic and clinical features

BACKGROUND

To build prediction models with radiomics features, clinical/conventional radiographic signs and combined scores for the discrimination of micropapillary or solid subtypes (high-risk subtypes) of lung adenocarcinoma.

METHODS

This retrospective study enrolled 351 patients with and without high-risk subtypes. Least Absolute Shrinkage and Selection Operator (LASSO) regression with cross-validation was performed to determine the optimal features of radiomics model. Missing clinical data were imputed by Multiple Imputation with Chain Equations (MICE). Clinical model with radiographic signs was built and scores of both models were integrated to establish combined model. Receiver operating characteristics (ROC) curves, area under ROC curves and decision curve analysis (DCA) were plotted to evaluate the model performance and clinical application.

RESULTS

Stratified splitting allocated 246 patients into training set. MICE for missing values obtained complete and unbiased data for the following analysis. Ninety radiomic features and four clinical/conventional radiographic signs were used to predict the high-risk subtypes. The radiomic model, clinical model and combined model achieved AUCs of 0.863 (95%CI: 0.817-0.909), 0.771 (95%CI: 0.713-0.713) and 0.872 (95%CI: 0.829-0.916) in the training set, and 0.849 (95%CI: 0.774-0.924), 0.778 (95%CI: 0.687-0.868) and 0.853 (95%CI: 0.782-0.925) in the test set. Decision curve showed that the radiomic and combined models were more clinically useful when the threshold reached 37.5%.

CONCLUSIONS

Radiomics features could facilitate the prediction of subtypes of lung adenocarcinoma. A simple combination of radiomics and clinical scores generated a robust model with high performance for the discrimination of micropapillary or solid subtype of lung adenocarcinoma.