DCE-MRI radiomics nomogram can predict response to neoadjuvant chemotherapy in esophageal cancer

Jinrong Qu,Ling Ma,Xu Yan,Hailiang Li,Jianjun Qin,Hongkai Zhang,Yanan Lu,Jia Guo,Hui Liu,Zhaoqi Wang,Ihab R Kamel

doi:10.1007/s12672-022-00464-7

Abstract

ObjectivesTo assess volumetric DCE-MRI radiomics nomogram in predicting response to neoadjuvant chemotherapy (nCT) in EC patients.MethodsThis retrospective analysis of a prospective study enrolled EC patients with stage cT1N + M0 or cT2-4aN0-3M0 who received DCE-MRI within 7 days before chemotherapy, followed by surgery. Response assessment was graded from 1 to 5 according to the tumor regression grade (TRG). Patients were stratified into responders (TRG1 + 2) and non-responders (TRG3 + 4 + 5). 72 radiomics features and vascular permeability parameters were extracted from DCE-MRI. The discriminating performance was assessed with ROC. Decision curve analysis (DCA) was used for comparing three different models.ResultsThis cohort included 82 patients, and 72 tumor radiomics features and vascular permeability parameters acquired from DCE-MRI. mRMR and LASSO were performed to choose the optimized subset of radiomics features, and 3 features were selected to create the radiomics signature that were significantly associated with response (P < 0.001). AUC of combining radiomics signature and DCE-MRI performance in the training (n = 41) and validation (n = 41) cohort was 0.84 (95% CI 0.57–1) and 0.86 (95% CI 0.74–0.97), respectively. This combined model showed the best discrimination between responders and non-responders, and showed the highest positive and positive predictive value in both training set and test set.ConclusionsThe radiomics features are useful for nCT response prediction in EC patients.

Highlights

Esophageal cancer (EC) is the sixth leading cause of cancer mortality globally [1]
It has been reported that neoadjuvant chemoradiotherapy (nCRT) could achieve more pathologic complete response than neoadjuvant chemotherapy (nCT), an updated meta-analysis showed no clear advantage of nCRT over nCT [6]
The results showed that the combined radiomics and Dynamic contrast enhanced (DCE)-MRI nomogram showed the best discrimination ability (AUC 0.84; 95% CI 0.57–1.00 in the training set, area under curve (AUC) 0.86; 95% CI 0.74–0.97 in the test set) that the value of cutoff is 0.5

Summary

Introduction

Esophageal cancer (EC) is the sixth leading cause of cancer mortality globally [1]. Neoadjuvant therapy combined with surgery has become the standard treatment for local advanced EC [2, 3], and which includes neoadjuvant chemoradiotherapy (nCRT) and neoadjuvant chemotherapy (nCT) [4, 5]. It has been reported that nCRT could achieve more pathologic complete response (pCR) than nCT, an updated meta-analysis showed no clear advantage of nCRT over nCT [6]. ECs are mainly adenocarcinoma, and nCRT is the treatment of choice [7]. In China and Japan, almost all the ECs are squamous cell carcinoma, and nCT is the treatment of choice for stages II and III [5]. NCT could improve overall survival, surgery is still important especially for non-responsive patients [8]. Pretreatment prediction of response to nCT in EC remains challenging

Objectives

Methods

Results

Conclusion