Abstract 3607
Background
We aimed to establish a prognostic model based on magnetic resonance imaging using deep learning to predict disease-free survival in patients with non-metastatic nasopharyngeal carcinoma.
Methods
In this retrospective, cohort study, we included 1636 patients who were diagnosed with non-metastatic nasopharyngeal carcinoma and underwent radical treatment at the Sun Yat-sen University Cancer Center. Patients from October 2010 to March 2015 were randomly divided into training cohort (n = 878) and validation cohort (n = 376); 382 patients from April 2015 to September 2015 were separated as test cohort. 3D DenseNet models learned deep representations of pre-treatment MRI and risk scores were extracted to predict PFS in the training cohort. We evaluated the accuracy of the prognostic model in validation and test cohorts. The primary endpoint was DFS, and the secondary endpoint was distant metastasis-free survival (DMFS).
Results
A series of risk scores for each patient were extracted from 3D DenseNet models, and an optimal cut-off value of risk scores was generated to classify patients into low-risk and high-risk group in the training cohort. Patients with low-risk scores had better DFS (hazard ratio [HR] 0.62, 95% CI 0.55 -0.70; p < 0.0001) and DMFS (HR 0.62, 95% CI 0.48 -0.81; p < 0.0003) than patients with low-risk scores. And we validated the prognostic accuracy of risk scores in the validation and test cohorts. In addition, patients who received concurrent chemotherapy had a poorer DFS (hazard ratio [HR] 7.79, 95% CI 1.08 -56.00; p < 0.041) compared with those who did not receive concurrent chemotherapy in low-risk group, meanwhile, patients with or without concurrent chemotherapy had similar outcomes in the high-risk group (HR 2.39, 95% CI 0.59 -9.62; p = 0.22). We also developed a nomogram based on risk scores and several clinical factors that predicted an individual’s risk of DFS.
Conclusions
MRI-based 3D DenseNet models are effective tools to learn deep representations and extract risk scores of DFS. Risk scores can be reliable prognostic factors to select which patients benefit from concurrent chemotherapy.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
The National Natural Science Foundation of China.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
2108 - Biomarker analyses of ramucirumab in patients with platinum refractory urothelial cancer from RANGE, a global, randomized, double-blind, phase 3 study.
Presenter: Michiel Van der Heijden
Session: Poster Display session 3
Resources:
Abstract
3090 - Comparison of Immuno-Oncology (IO) Biomarkers in Adenocarcinoma (ACB), Urothelial Carcinoma (UCB) and Squamous Cell Carcinoma (SCCB) of the Bladder, with interim results from PURE01
Presenter: Daniele Raggi
Session: Poster Display session 3
Resources:
Abstract
5211 - Potential role of a clinical, taxonomical classification and RNA expression integrated signature to predict response to neoadjuvant platinum-based chemotherapy in muscle-invasive bladder cancer (MIBC) patients
Presenter: Albert Font
Session: Poster Display session 3
Resources:
Abstract
3206 - Hyperphosphatemia due to Erdafitinib (a Pan-FGFR Inhibitor) and Anti-tumor Activity Among Patients (Pts) with Advanced Urothelial Carcinoma (UC)
Presenter: Scott Tagawa
Session: Poster Display session 3
Resources:
Abstract
3110 - Prognostic role of FGFR Mutations and FGFR mRNA expression in metastatic urothelial cancer treated with anti-PD(L1) inhibitors in first and second line setting
Presenter: Florian Roghmann
Session: Poster Display session 3
Resources:
Abstract
3564 - Circulating tumour DNA (ctDNA) utility as a biomarker for metastatic urothelial carcinoma (mUC)
Presenter: Jean-Michel Lavoie
Session: Poster Display session 3
Resources:
Abstract
2760 - Comparative analysis of tumor mutational burden (TMB) prediction methods and its association with determinants of the tumor immune microenvironment of urothelial bladder cancer (UBC)
Presenter: Markus Eckstein
Session: Poster Display session 3
Resources:
Abstract
2513 - The Immunoscore in patients with urothelial carcinoma treated with neoadjuvant chemotherapy: clinical significance for pathological response and survival
Presenter: Elise Nassif
Session: Poster Display session 3
Resources:
Abstract
2835 - Genomic analysis of urothelial cancer and associations with treatment choice and outcome
Presenter: David Sarid
Session: Poster Display session 3
Resources:
Abstract
5763 - cfDNA is an acceptable but insufficient means of characterizing FGFR3 mutation in patients with metastatic urothelial cancer (mUC)
Presenter: Sumanta Pal
Session: Poster Display session 3
Resources:
Abstract