No abstract

No abstract

a combination of clinical variables and radiomic features), and the receiver operating characteristic as well as the corresponding area under the curve (AUC) was reckoned for each model to identify the model with the higher predictability. Results: Among 378 patients, 238 patients were classified as PD-L1 positive and 140 patients as PD-L1 negative. There was no significant difference in clinical characteristics including age, FIGO stage, and histologic diagnosis between the two PD-L1 expression groups (P > 0.05 for all). With the total of 25 selected MRI-based radiomics features which were significantly associated with PD-L1 expression levels, we established two prediction models for predicting PD-L1 positivity. Models that comprised clinical variables and clinical combined with MRI-based radiomic features resulted in an AUC of 0.56 and 0.96, respectively. Conclusion: Model composed of clinical variables and MRI radiomic features can predict PD-L1 expression in cervical cancer. This model may facilitate noninvasive assessment of PD-L1 expression, and may be helpful in guiding immunotherapy for cervical cancer patients in clinical practice.

No abstract

No abstract