Predicting pathological complete response of neoadjuvant radiotherapy and targeted therapy for soft tissue sarcoma by...

To construct effective prediction models for neoadjuvant radiotherapy (RT) and targeted therapy based on whole-tumor texture analysis of multisequence MRI for soft tissue sarcoma (STS) patients.

Thirty patients with STS of the extremities or trunk from a prospective phase II trial were enrolled for this analysis. All patients underwent pre- and post-neoadjuvant RT MRI examinations from which whole-tumor texture features were extracted, including T₁-weighted with fat saturation and contrast enhancement (T₁FSGd), T₂-weighted with fat saturation (T₂FS), and diffusion-weighted imaging (DWI) sequences and their corresponding apparent diffusion coefficient (ADC) maps. According to the postoperative pathological results, the patients were divided into pathological complete response (pCR) and non-pCR (N-pCR) groups. pCR was defined as less than 5% of residual tumor cells by postoperative pathology. Delta features were defined as the percentage change in a texture feature from pre- to post-neoadjuvant RT MRI. After data reduction and feature selection, logistic regression was used to build prediction models. ROC analysis was performed to assess the diagnostic performance.

Five of 30 patients (16.7%) achieved pCR. The Delta_Model (AUC 0.92) had a better predictive ability than the Pre_Model (AUC 0.78) and Post_Model (AUC 0.76) and was better than AJCC staging (AUC 0.52) and RECIST 1.1 criteria (AUC 0.52). The Combined_Model (pre, post, and delta features) had the best predictive performance (AUC 0.95).

Whole-tumor texture analysis of multisequence MRI can well predict pCR status after neoadjuvant RT and targeted therapy in STS patients, with better performance than RECIST 1.1 and AJCC staging.

• MRI multisequence texture analysis could predict the efficacy of neoadjuvant RT and targeted therapy for STS patients. • Texture features showed incremental value beyond routine clinical factors. • The Combined_Model with features at multiple time points showed the best performance.