Peritumoral radiomics features on preoperative thin-slice CT images can predict the spread through air spaces of lung adenocarcinoma

Abstract

The spread through air spaces (STAS) is recognized as a negative prognostic factor in patients with early-stage lung adenocarcinoma. The present study aimed to develop a machine learning model for the prediction of STAS using peritumoral radiomics features extracted from preoperative CT imaging. A total of 339 patients who underwent lobectomy or limited resection for lung adenocarcinoma were included. The patients were randomly divided (3:2) into training and test cohorts. Two prediction models were created using the training cohort: a conventional model based on the tumor consolidation/tumor (C/T) ratio and a machine learning model based on peritumoral radiomics features. The areas under the curve for the two models in the testing cohort were 0.70 and 0.76, respectively (P = 0.045). The cumulative incidence of recurrence (CIR) was significantly higher in the STAS high-risk group when using the radiomics model than that in the low-risk group (44% vs. 4% at 5 years; P = 0.002) in patients who underwent limited resection in the testing cohort. In contrast, the 5-year CIR was not significantly different among patients who underwent lobectomy (17% vs. 11%; P = 0.469). In conclusion, the machine learning model for STAS prediction based on peritumoral radiomics features performed better than the C/T ratio model.

Computed Tomography Radiomics for Preoperative Prediction of Spread Through Air Spaces in the Early Stage of Surgically Resected Lung Adenocarcinomas

“…Previous studies have investigated the value of radiomics features for STAS prediction, mostly in patients with early stage surgically resected lung adenocarcinoma. 23 24 25 26 27 28 29 44 45 46 47 48 Most previous studies constructed radiomics models using radiomics features, with the number of selected features ranging from 2 to 12, and reported the performance of the model using the AUC, which ranged from 0.63 to 0.99. Although all previous studies concluded that radiomics features were useful for the preoperative prediction of STAS, the actual added value of radiomics to the conventional prediction model and the association with survival were rarely investigated.…”

Combined model of radiomics and clinical features for differentiating pneumonic-type mucinous adenocarcinoma from lobar pneumonia: An exploratory study

“…This non-invasive method has shown its potential usefulness for the identification of internal tumor heterogeneity ( 7 , 8 ). In recent decades, radiomics has been well proven in the identification, staging, and evaluation of lung cancer ( 9 ). Wang et al.…”

“…This non-invasive method has shown its potential usefulness for the identification of internal tumor heterogeneity (7,8). In recent decades, radiomics has been well proven in the identification, staging, and evaluation of lung cancer (9). Wang et al found that CT imaging features characteristic of PIMA might provide prognostic information and individual risk assessment in addition to clinical factors (10).…”

Investigation of the combination of intratumoral and peritumoral radiomic signatures for predicting epidermal growth factor receptor mutation in lung adenocarcinoma

“…7,9 Some studies have reported the usefulness of radiomic features derived from intratumoral and peritumoral regions for predicting tumor spread in air space (STAS). [12][13][14] STAS is also associated with EGFR mutations. 14 Moreover, the predictive model by Wang et al established that both the intratumoral and peritumoral regions are important for predicting EGFR mutation.…”

“…Some studies have reported the usefulness of radiomic features derived from intratumoral and peritumoral regions for predicting tumor spread in air space (STAS). 12 , 13 , 14 STAS is also associated with EGFR mutations. 14 Moreover, the predictive model by Wang et al.…”