Radiomics-based Prediction Model of Tumor Spread Through Air Space in Lung Adenocarcinoma

Spread through air space (STAS) has been reported as a negative prognostic factor in patients with lung cancer undergone sublobar resection. Its preoperative assessment could thus be useful to customize surgical treatment. Radiomics has been recently proposed to predict STAS in patients with lung adenocarcinoma. However, all the studies have strictly selected both imaging and patients, leading to results hardly applicable to daily clinical practice. The aim of this study is to test a radiomics-based prediction model of STAS in practice-based dataset and verify its validity and translational potentials. Radiological and clinical data from 100 consecutive patients with resected lung adenocarcinoma were retrospectively collected for the training section. As in common clinical practice, preoperative CT images were acquired independently by different physicians and from different hospitals. Therefore, our dataset presents high variance in model and manufacture of scanner, acquisition and reconstruction protocol, endovenous contrast phase and pixel size. To test the effect of normalization in highly varying data, preoperative CT images and tumor region of interest were preprocessed with four different pipelines. Features were extracted using pyradiomics and selected considering both separation power and robustness within pipelines. After that, a radiomics-based prediction model of STAS were created using the most significant associated features. This model were than validated in a group of 50 patients prospectively enrolled as external validation group to test its efficacy in STAS prediction.

Sex

All

Minimum age

18 Years

Inclusion Criteria:

* Patients with suspected or cito-histologically proven lung adenocarcinoma undergoing lung cancer surgery;
* Available preoperative CT images
* Age older than 18 years

Exclusion Criteria:

* Chest wall infiltration
* Induction radio or chemotherapy
* Incomplete surgical resection

• BACKGROUNDJiang C, Luo Y, Yuan J, You S, Chen Z, Wu M, Wang G, Gong J. CT-based radiomics and machine learning to predict spread through air space in lung adenocarcinoma. Eur Radiol. 2020 Jul;30(7):4050-4057. doi: 10.1007/s00330-020-06694-z. Epub 2020 Feb 28. PMID 32112116
• BACKGROUNDChen D, She Y, Wang T, Xie H, Li J, Jiang G, Chen Y, Zhang L, Xie D, Chen C. Radiomics-based prediction for tumour spread through air spaces in stage I lung adenocarcinoma using machine learning. Eur J Cardiothorac Surg. 2020 Jul 1;58(1):51-58. doi: 10.1093/ejcts/ezaa011. PMID 32011674
• BACKGROUNDZhuo Y, Feng M, Yang S, Zhou L, Ge D, Lu S, Liu L, Shan F, Zhang Z. Radiomics nomograms of tumors and peritumoral regions for the preoperative prediction of spread through air spaces in lung adenocarcinoma. Transl Oncol. 2020 Oct;13(10):100820. doi: 10.1016/j.tranon.2020.100820. Epub 2020 Jul 1. PMID 32622312
• DERIVEDBassi M, Russomando A, Vannucci J, Ciardiello A, Dolciami M, Ricci P, Pernazza A, D'Amati G, Mancini Terracciano C, Faccini R, Mantovani S, Venuta F, Voena C, Anile M. Role of radiomics in predicting lung cancer spread through air spaces in a heterogeneous dataset. Transl Lung Cancer Res. 2022 Apr;11(4):560-571. doi: 10.21037/tlcr-21-895. PMID 35529792