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
3664 - Longitudinal changes in cell-free DNA (cfDNA) methylation levels identify early non-responders to treatment in advanced solid tumors
Presenter: Andrew Davis
Session: Poster Display session 3
Resources:
Abstract
3212 - Multigene panel testing results for hereditary breast cancer in 1325 individuals: implications for gene selection and considerations for guidelines.
Presenter: Georgios Tsaousis
Session: Poster Display session 3
Resources:
Abstract
2591 - PIK3R5 genetic predictors of hypertension induced by VEGF-pathway inhibitors
Presenter: Julia Quintanilha
Session: Poster Display session 3
Resources:
Abstract
4377 - ERBB2 mRNA as a predictor in HER2-positive (HER2+)/hormone receptor-positive (HR+) metastatic breast cancer (BC) treated with HER2 blockade in combination with endocrine therapy (ET): a retrospective analysis of the ALTERNATIVE and SOLTI-PAMELA trials.
Presenter: Nuria Chic
Session: Poster Display session 3
Resources:
Abstract
3439 - Early on-treatment vs pre-treatment tumor transcriptomes as predictors of response to neoadjuvant therapy for HER2-positive inflammatory breast cancer
Presenter: Sonia Pernas
Session: Poster Display session 3
Resources:
Abstract
2512 - AXL expression predicts poor prognosis and lack of efficacy of anti-angiogenic and anti-epidermal growth factor receptor (EGFR) agents in patients (pts) with RAS wild type (WT) metastatic colorectal cancer (mCRC)
Presenter: Claudia Cardone
Session: Poster Display session 3
Resources:
Abstract
4061 - Prevalence of EGFR mutations and its correlation with Egyptian patients’ human kinetics (PEEK Study)
Presenter: Adel Ibrahim
Session: Poster Display session 3
Resources:
Abstract
2547 - Evaluation of tumor microenvironment identifies immune correlates of response to combination immunotherapy with margetuximab (M) and pembrolizumab (P) in HER2+ gastroesophageal adenocarcinoma (GEA)
Presenter: Sergio Rutella
Session: Poster Display session 3
Resources:
Abstract
4671 - Clinicopathological and molecular criteria assessment for the screening of hypermutated proficient mismatch repair (pMMR) colorectal cancers (CRC) with exonucleasic domain POLE (edPOLE) mutations (mt).
Presenter: Benoit Rousseau
Session: Poster Display session 3
Resources:
Abstract
3862 - Tumor mutation burden and microsatellite instability in colorectal cancer
Presenter: Francesca Fenizia
Session: Poster Display session 3
Resources:
Abstract