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
5043 - Comprehensive results of a Phase Ib study with a HER2/neu B-cell peptide vaccine administered with cisplatin and 5-fluorouracil or capecitabine chemotherapy show safety, immunogenicity and clinical response in patients with HER2/Neu overexpressing advanced gastric cancer
Presenter: Ursula Wiedermann
Session: Poster Display session 3
Resources:
Abstract
4506 - Single intravenous preoperative administration of the oncolytic virus Pexa-Vec to prime anti-tumor immunity
Presenter: Adel Samson
Session: Poster Display session 3
Resources:
Abstract
1631 - Randomized phase 2 clinical trial of NY-ESO-1 protein vaccine combined with cholesteryl pullulan (CHP-NY-ESO-1) in resected esophageal cancer patients
Presenter: Shinichi Kageyama
Session: Poster Display session 3
Resources:
Abstract
4244 - T cell repertoire sequencing reveals dynamics of response to dendritic cell vaccine plus dasatinib for checkpoint blockade resistant metastatic melanoma
Presenter: Luca Quagliata
Session: Poster Display session 3
Resources:
Abstract
5791 - Ixovex, a novel oncolytic E1B-mutated adenovirus
Presenter: Mohiemen Anwar
Session: Poster Display session 3
Resources:
Abstract
4170 - Anti-CSPG4 DNA vaccination as a promising strategy for the treatment of CSPG4+ tumors: a comparative oncology trial
Presenter: Federica Riccardo
Session: Poster Display session 3
Resources:
Abstract
5780 - Antitumor activity, immunogenicity and safety of a novel PD-1 vaccine in combination with two chimeric HER-2 peptide vaccine in syngeneic Balb/c, C57Bl/6 models and in beagle dogs
Presenter: Pravin Kaumaya
Session: Poster Display session 3
Resources:
Abstract
5860 - Maternal immunization against ALK as a weapon to fight neuroblastoma
Presenter: Giuseppina Barutello
Session: Poster Display session 3
Resources:
Abstract
4720 - Phase 1 study evaluating safety, pharmacokinetics (PK), pharmacodynamics, and preliminary efficacy of ABBV-428, first-in-class mesothelin (MSLN)-CD40 bispecific, in patients (pts) with advanced solid tumors
Presenter: Jason Luke
Session: Poster Display session 3
Resources:
Abstract
5717 - Anti-PD-L1/IL-15 fusion protein generates robust adaptive immune gene signatures in tumors leading to tumor inhibition and memory responses
Presenter: Stella Martomo
Session: Poster Display session 3
Resources:
Abstract