Radiomics Combined With Frozen Section Prediction Model for Spread Through Air Space in Lung Adenocarcinoma

Preoperative CT-based Radiomics Combined With Intraoperative Frozen Section is Predictive of Spread Through Air Space in Early Lung Adenocarcinoma

a multifactorial model combining radiomics with frozen section analysis is a potential biomarker for assessing Spread Through Air Space during surgery, which can provide decision-making support to therapeutic planning for early-stage lung adenocarcinomas.

Spread through air space (STAS) is a novel invasive pattern of lung adenocarcinoma and is also a risk factor for recurrence and worse prognosis of lung adenocarcinoma. Its preoperative assessment could thus be useful to customize surgical treatment. Radiomics and frozen section haave been recently proposed to predict STAS in patients with lung adenocarcinoma. Radiomics-based Prediction Model is highly sensitive but not specific for STAS detection. While, frozen section is highly specific but not sensitive for STAS detection in early lung adenocarcinomas.

Therefore, the proposed project aims to develop and validate a multifactorial model combining radiomics with frozen section analysis to assesse Spread Through Air Space during surgery, which can provide decision-making support to therapeutic planning for early-stage lung adenocarcinomas.

Inclusion Criteria:

1. intraoperative frozen section diagnosis and final pathology diagnosis are available
2. preoperative standard non-enhanced CT is available
3. Pathologically confirmed

Exclusion Criteria:

1. with a previous history of radiation therapy, chemotherapy or biopsy
2. the time interval between the CT examination and surgery was more than two weeks