Abstract

Simple SummaryPrognosis for patients with locally advanced esophageal squamous cell carcinoma (ESCC) remains poor mainly due to late diagnosis and limited curative treatment options. Neoadjuvant chemoradiotherapy (nCRT) plus surgery is considered the standard of care for patients with locally advanced ESCC. Currently, predicting prognosis remains a challenging task. Quantitative imaging radiomics analysis has shown promising results, but these methods are traditionally data-intensive, requiring a large sample size, and are not necessarily based on the underlying biology. Feature selection based on genomics is proposed in this work, leveraging differentially expressed genes to reduce the number of radiomic features allowing for the creation of a CT-based radiomic model using the genomics-based feature selection method. The established radiomic signature was prognostic for patients’ long-term survival. The radiomic nomogram could provide a valuable prediction for individualized long-term survival.Purpose: To evaluate the prognostic value of baseline and restaging CT-based radiomics with features associated with gene expression in esophageal squamous cell carcinoma (ESCC) patients receiving neoadjuvant chemoradiation (nCRT) plus surgery. Methods: We enrolled 106 ESCC patients receiving nCRT from two institutions. Gene expression profiles of 28 patients in the training set were used to detect differentially expressed (DE) genes between patients with and without relapse. Radiomic features that were correlated to DE genes were selected, followed by additional machine learning selection. A radiomic nomogram for disease-free survival (DFS) prediction incorporating the radiomic signature and prognostic clinical characteristics was established for DFS estimation and validated. Results: The radiomic signature with DE genes feature selection achieved better performance for DFS prediction than without. The nomogram incorporating the radiomic signature and lymph nodal status significantly stratified patients into high and low-risk groups for DFS (p < 0.001). The areas under the curve (AUCs) for predicting 5-year DFS were 0.912 in the training set, 0.852 in the internal test set, 0.769 in the external test set. Conclusions: Genomics association was useful for radiomic feature selection. The established radiomic signature was prognostic for DFS. The radiomic nomogram could provide a valuable prediction for individualized long-term survival.

Highlights

  • Esophageal cancer (EC) accounted for 572,034 new cases and 508,585 deaths of cancer overall worldwide in 2018, ranking seventh in incidence and sixth terms of mortality [1]

  • In the multivariate analysis with Akaike information criterion (AIC) stepwise selection for the construction of nomogram 1, Rad-score 1 (HR: 2.55; 95% CI: 1.85,3.52; p < 0.001), and clinical N staging (HR: 3.23; 95% CI: 1.66, 6.29; p < 0.001) were identified as independent prognoFsigtuicref3a. cPtroogrnsositnic nthomeoCgroamxs.pPrroobpaboilrittyioofn3a-yleahraaznda5r-dyesarmdiosedaseel-fraene sdurwvivearl eofitnhecnoormpoogrraamtseddevienlotpoedthbye nomFigougrRreaad3m-s.cPo1rreoa(gnFndiognsoudtiraclesnt3aog)mi.ngoRignarfdoarm-msacst.oioPrner. o(a2b) aN(boHmiliRotgy:rao3mf.2135(-w;yie9tha5rg%eannoCmdiIc5:s-f1ye.ae9tau8rre,ds5eisl.e3ec3atios;nep)-.f(r

  • For patients with esophageal squamous cell carcinoma (ESCC) treated by neoadjuvant chemoradiation (nCRT), Laruea et al [43] developed a CT-based radiomic model with an area under the curve (AUC) of 0.61 and borderline significant Kaplan–Meier curve result in the validation dataset (p = 0.053)

Read more

Summary

Introduction

Esophageal cancer (EC) accounted for 572,034 new cases and 508,585 deaths of cancer overall worldwide in 2018, ranking seventh in incidence and sixth terms of mortality [1]. Because of late-stage cancer diagnosis and limited clinical curative modality, the five-year overall survival (OS) rates for ESCC patients range from 15% to 25% [3]. Surgery has a central role in disease management, but a large proportion of patients showed local or distant metastasis after surgery within 3 years [4,5]. The addition of adjuvant chemotherapy or radiation therapy has proven to improve survival in patients with involved lymph node disease [6,7]. A recent network meta-analysis showed that adjuvant chemotherapy or radiation therapy could not significantly reduce death risk compared with surgery alone [8]. The CROSS study demonstrated that patients receiving nCRT followed by surgery have a significantly increased median overall survival than those receiving surgery alone (49.4 vs 29.0 months, p = 0.003) [9]. The ability to identify patients with poor prognoses is required for more effective personalized disease management

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call