Xiaoran Li X, Xu C, Yu Y, et al. - As there is no non-invasive method to detect lymphovascular space invasion (LVSI), which is an independent prognostic factor in early-stage cervical cancer, researchers sought to establish a machine learning model that combines radiomics based on PET imaging with tenascin-C (TNC) and cyclooxygenase-2 (COX-2) for predicting LVSI. They retrospectively analyzed 112 patients with early-stage cervical squamous cell carcinoma who underwent PET/CT examination and extracted 401 radiomics features based on PET/CT images and integrated these into radiomics score (Rad-score). Patients with LVSI had significantly higher Rad-score when compared with those without. Findings revealed correlation of TNC to both the Rad-score and COX-2. Based on outcomes, they suggest the machine learning model of the combination of PET radiomics with COX-2 and TNC as a novel tool to detect LVSI in patients with early-stage cervical cancer.