The MRI radiomics signature can predict the pathologic response to neoadjuvant chemotherapy in locally advanced esophageal squamous cell carcinoma

Objectives To investigate the MRI radiomics signatures in predicting pathologic response among patients with locally advanced esophageal squamous cell carcinoma (ESCC), who received neoadjuvant chemotherapy (NACT). Methods Patients who underwent NACT from March 2015 to October 2019 were prospectively included. Each patient underwent esophageal MR scanning within one week before NACT and within 2–3 weeks after completion of NACT, prior to surgery. Radiomics features extracted from T2-TSE-BLADE were randomly split into the training and validation sets at a ratio of 7:3. According to the progressive tumor regression grade (TRG), patients were stratified into two groups: good responders (GR, TRG 0 + 1) and poor responders (non-GR, TRG 2 + 3). We constructed the Pre/Post-NACT model (Pre/Post-model) and the Delta-NACT model (Delta-model). Kruskal–Wallis was used to select features, logistic regression was used to develop the final model. Results A total of 108 ESCC patients were included, and 3/2/4 out of 107 radiomics features were selected for constructing the Pre/Post/Delta-model, respectively. The selected radiomics features were statistically different between GR and non-GR groups. The highest area under the curve (AUC) was for the Delta-model, which reached 0.851 in the training set and 0.831 in the validation set. Among the three models, Pre-model showed the poorest performance in the training and validation sets (AUC, 0.466 and 0.596), and the Post-model showed better performance than the Pre-model in the training and validation sets (AUC, 0.753 and 0.781). Conclusions MRI-based radiomics models can predict the pathological response after NACT in ESCC patients, with the Delta-model exhibiting optimal predictive efficacy. Clinical relevance statement MRI radiomics features could be used as a useful tool for predicting the efficacy of neoadjuvant chemotherapy in esophageal carcinoma patients, especially in selecting responders among those patients who may be candidates to benefit from neoadjuvant chemotherapy. Key Points • The MRI radiomics features based on T2WI-TSE-BLADE could potentially predict the pathologic response to NACT among ESCC patients. • The Delta-model exhibited the best predictive ability for pathologic response, followed by the Post-model, which similarly had better predictive ability, while the Pre-model performed less well in predicting TRG.