Development and validation a radiomics combined clinical model predicts treatment response for esophageal squamous cell carcinoma patients

PURPOSE

This study is aimed to develop and validate a machine learning model, which combined radiomics and clinical characteristics to predicting the definitive chemoradiotherapy (dCRT) treatment response in esophageal squamous cell carcinoma (ESCC) patients.

METHODS

204 advanced ESCC patients were included who underwent dCRT at our hospital. Patients were randomly divided into training cohort and validation cohort with a ratio of 7:3. The radiomics features were selected by LASSO algorithm. The clinical features were selected by multivariate logistics analysis (p < 0.05). Subsequently, a combined radiomics and clinical model was established and validated to predict the treatment response in ESCC patients by logistic regression model. The performance of the model was evaluated by receiver operating characteristic (ROC) curve, decision curve analysis (DCA), nomogram, and calibration curve.

RESULTS

Total of 944 radiomics features were extracted from the pre-treatment contrasted enhanced CT images (CECT). After feature selection, 3 radiomics features and 3 clinical features were identified as the most predictive variables. The combined model shows better prediction performance among radiomics model or clinical model. The radiomics model's AUC values in training and validation cohort are 0.71,0.69. As for clinical model the AUC values were 0.74,0.75 in training and validation cohort. However, the AUC values in combined model are 0.79, 0.78 in training cohort and validation cohort, respectively. DCA and calibration curve also demonstrated good performance for the combined model.

CONCLUSION

The radiomics combined clinical features model demonstrates superior treatment response prediction ability for ESCC patients received dCRT. This model has the potential to assist clinicians in identifying non-responsive patients before treatment and guide individualized therapy for advanced ESCC patients.

Treatment Outcomes and Risk Factors for Incomplete Treatment after Definitive Chemoradiotherapy for Non-Resectable or Metastatic Esophageal Cancer

Among patients with unresectable or metastatic esophageal cancer who receive definitive chemotherapy or chemoradiotherapy, the rates of treatment-related adverse events and incomplete treatment remain high. We conducted this study to investigate survival after definitive treatments and identify predicting factors for incomplete treatment. The data of patients who received definitive chemotherapy or chemoradiotherapy for esophageal cancer were retrospectively examined. The patients were assigned to Group 1: incomplete definitive treatment; Group 2: complete definitive treatment; or Group 3: complete definitive treatment with additional salvage surgery. The data of 273 patients (90, 166, and 17 in Groups 1, 2, and 3, respectively) were analyzed. In the survival analysis, the median overall survival of Groups 1, 2, and 3 were 2.6, 10.3, and 29.5 months, respectively. A significant difference in 3-year overall survival was observed among the groups (2.2%, 12.4%, and 48.5%, p < 0.001). In multivariable analysis, the independent risk factors for incomplete definitive treatment included poor performance score (hazard ratio (HR): 5.23, p = 0.001), bone metastasis (HR: 2.18, p = 0.024), airway invasion (HR: 2.90, p = 0.001), and liver cirrhosis (HR: 3.20, p = 0.026). Incomplete definitive treatment is associated with a far worse prognosis. Poor performance, bone metastasis, airway invasion, and liver cirrhosis are risk factors for incomplete treatment.

Induction Chemotherapy Followed by Chemoradiotherapy With or Without Consolidation Chemotherapy Versus Chemoradiotherapy Followed by Consolidation Chemotherapy for Esophageal Squamous Cell Carcinoma

Objective

This study aimed to compare the efficacy and safety of induction chemotherapy followed by concurrent chemoradiotherapy (I-CCRT), induction chemotherapy followed by concurrent chemoradiotherapy and consolidation chemotherapy (I-CCRT-C), and concurrent chemoradiotherapy followed by consolidation chemotherapy (CCRT-C) for locally advanced esophageal squamous cell carcinoma (ESSC).

Patients and Methods

Patients with locally advanced ESCC who underwent definitive chemoradiotherapy with cisplatin plus fluorouracil or docetaxel from February 2012 to December 2018 were retrospectively reviewed. Kaplan–Meier curve was used to estimate survival. Efficacy was assessed using RECIST, version 1.0. Prognosis factors were identified with Cox regression analysis.

Results

Patients were treated with CCRT-C (n = 59), I-CCRT (n = 20), and I-CCRT-C (n = 48). The median follow-up duration was 73.9 months for the entire cohort. The ORR of the CCRT-C, I-CCRT, and I-CCRT-C groups was 89.8%, 70.0%, and 77.1%, respectively (p = 0.078). The median PFS in the CCRT-C, I-CCRT, and I-CCRT-C groups was 32.5, 16.1, and 27.1 months, respectively (p = 0.464). The median OS of the CCRT-C, I-CCRT, and I-CCRT-C groups was 45.9, 35.5, and 54.0 months, respectively (p = 0.788). Cox regression analysis indicated that I-CCRT-C and I-CCRT did not significantly prolong PFS and OS compared with CCRT-C (p &gt; 0.05). Neutropenia grade ≥3 in CCRT-C, I-CCRT, and I-CCRT-C groups was 47.5%, 15%, and 33.3% of patients, respectively (p = 0.027).

Conclusions

I-CCRT and I-CCRT-C using cisplatin plus fluorouracil or docetaxel regimen are not superior to CCRT-C in survival but seem to have less severe neutropenia than CCRT-C. Further randomized controlled studies are warranted.

YAP1 amplification as a prognostic factor of definitive chemoradiotherapy in nonsurgical esophageal squamous cell carcinoma

Background

Definitive chemoradiation therapy (dCRT) is the standard treatment for patients with nonsurgical esophageal squamous cell carcinoma (ESCC), yet patients have demonstrated great variations in their responses to dCRT and inevitably progressed following treatment.

Methods

To identify prognostic biomarkers, we performed targeted next‐generation sequencing of 416 cancer‐related genes on primary tumors from 47 nonsurgical ESCC patients prior to dCRT treatment. The association between genetic alterations and patients' local recurrence‐free survival (LRFS), progression‐free survival (PFS), and overall survival (OS) was analyzed.

Results

TP53 (78% of patients), NOTCH1 (32%), ARID1A (13%), FAT1 (13%), and CDKN2A (13%) were commonly mutated in ESCC patients, while gene amplifications frequently occurred in MCL1 (36%), FGF19 (34%), MYC (32%), CCND1 (27%), ZNF217 (15%), CDKN2A (13%), and YAP1 (11%). Univariate and multivariate analyses of clinical factors and genetic alterations indicated that sex is an independent prognostic factor, with males tending to have better LRFS (hazard ratio [HR], 0.25; 95%CI, 0.08‐0.77, P = .015) and progression‐free survival (PFS) (HR, 0.35; 95%CI, 0.13‐0.93, P = .030) following dCRT. Meanwhile, YAP1 amplification (n = 7) was an adverse prognostic factor, and patients with this alteration demonstrated a tendency toward worse outcomes with shorter LRFS (HR, 4.06; 95%CI, 1.26‐13.14, P = .019) and OS (HR, 2.78; 95%CI, 0.95‐8.17, P = .062). In a subgroup analysis, while sex and M‐stage were controlled, a much stronger negative effect of YAP1 amplification vs wild‐type in LRFS was observed (log‐rank P = .0067).

Conclusion

The results suggested that YAP1 amplification is a potentially useful biomarker for predicting treatment outcomes and identifying patients with a high risk of relapse who should be closely monitored.

miRNA-200c enhances radiosensitivity of esophageal cancer by cell cycle arrest and targeting P21

Esophageal squamous cancer is one of the most fatal malignancies and often suffer recurrence after radiotherapy. Downregulation of miRNA-200c is associated with radiotolerance. We aim to investigate the role of miRNA-200c in radiosensitivity and develop a systemic treatment strategy for esophageal squamous cancer. Overexpression of miRNA-200c by transfection was determined by RT-PCR. Radiosensitizing effect of miRNA-200c on esophageal squamous cancer cells was determined by clonogenic assay and xenograft model. Cell cycle was analyzed by flow cytometry. The levels of Cyclin B1, cyclin D1, cyclin E1, CDK2, CDK4, Cdc2 and P21 protein expressions were detected by western blotting. The results of our study revealed that miRNA-200c enhanced the radiosensitivity significantly in esophageal squamous cancer cell line in vitro and in vivo. miRNA-200c induced G2/M and sub-G1 phase arrest and reduced S phase rate of the irradiated Eca-109 cells and downregulated expression levels of Cyclin B1, cdc2 and upregulated P21 expression level. Present results demonstrate that downregulation of miRNA-200c is associated with radiotolerance. miRNA-200c increases radiosensitivity by G2/M and sub-G1 phase arrest through modulating Cyclin B1, cdc2 and P21 expression levels.