A Bayesian deep learning model with consolidation-to-tumor ratio (CTR) prior revolutionizes the prediction of spread through air spaces (STAS) in stage IA lung adenocarcinoma: a large-scale diagnostic study.

BACKGROUND

The preoperative prediction of spread through air spaces (STAS) in patients with early-stage lung adenocarcinoma (LUAD) is crucial for selecting the appropriate surgical approach and improving patient outcomes. Previous research has confirmed that there is a significant correlation between consolidation-to-tumor ratio (CTR) and STAS. This study aimed to develop a Bayesian deep learning (DL) model based on the CTR prior to predict STAS in patients with stage IA LUAD.

METHODS

This large-scale diagnostic study included patients with solitary primary invasive LUAD who underwent complete resection between November 2017 and October 2023. Enrolled patients were randomly assigned to training, validation, and test cohorts in a 7:2:1 ratio. Using a variational Bayesian inference framework, we developed a DL model based on the CTR prior (STAS-DL). The performance of STAS-DL was compared with another DL model without the CTR prior (STAS-DL) using the receiver operating characteristic (ROC) curve, calibration curve, decision curve analysis (DCA), and clinical impact curve (CIC).

RESULTS

A total of 1,374 patients were included, with 961 in the training cohort, 275 in the validation cohort, and 138 in the test cohort. The results showed that CTR in the STAS-positive group was significantly higher than that in the STAS-negative group [0.63 (interquartile range, 0.36, 0.98) . 0.35 (interquartile range, 0.19, 0.60), P<0.001]. Compared to STAS-DL, the area under the ROC curve (AUC) tends to be higher for STAS-DL (0.831 . 0.731, P=0.06) in the validation cohort, and STAS-DL demonstrated a significantly higher AUC (0.858 . 0.637, P=0.008) in the test cohort. Additionally, the calibration curve suggested better calibration for STAS-DL. DCA and CIC also indicated that STAS-DL conferred higher clinical net benefit.

CONCLUSIONS

The proposed model based on the CTR prior offers significant advantages in predicting STAS in patients with stage IA LUAD, and incorporating doctors' knowledge as priors can effectively guide the development of DL models.