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
4634 - Comparative molecular analyses between microsatellite stable BRAFV600E mutant colorectal cancers and BRAFV600E mutant melanomas.
Presenter: Mohamed Salem
Session: Poster Display session 3
Resources:
Abstract
3264 - A novel preclinical model of RAF-independent MEK1 mutant tumors and its treatment with novel ATP competitive MEK inhibitor
Presenter: Luca Hegedus
Session: Poster Display session 3
Resources:
Abstract
4918 - HER2 inhibition in Aggressive Squamous Cell Carcinomas driven by a common MET Sema Domain Polymorphism
Presenter: Nur Afiqah Mohamed Salleh
Session: Poster Display session 3
Resources:
Abstract
2426 - ADAM9 as a target for lung cancer treatment
Presenter: Yuh-pyng Sher
Session: Poster Display session 3
Resources:
Abstract
5537 - Novel polyurea/polyurethane nanocapsules loaded with a tambjamine analog to improve cancer chemotherapy delivery and safety in lung cancer
Presenter: Marta Perez Hernandez
Session: Poster Display session 3
Resources:
Abstract
1597 - Discovery of Clinical Candidate DBPR112, a Furanopyrimidine-based Epidermal Growth Factor Receptor Inhibitor for the Treatment of Non-Small Cell Lung Cancer
Presenter: Hsing-pang Hsieh
Session: Poster Display session 3
Resources:
Abstract
3543 - Molecular characteristics in lung squamous cell carcinomas dependent on TP53 status – putative targets
Presenter: Vilde Haakensen
Session: Poster Display session 3
Resources:
Abstract
4111 - Comparison of molecular profiles between primary tumour and matched metastasis in non-small cell lung cancer
Presenter: Asuka Kawachi
Session: Poster Display session 3
Resources:
Abstract
4559 - Treatment with BLU-667, a potent and selective RET inhibitor, provides rapid clearance of ctDNA in Patients with RET-altered Non-Small Cell Lung Cancer (NSCLC) and Thyroid Cancer
Presenter: Giuseppe Curigliano
Session: Poster Display session 3
Resources:
Abstract
2501 - Triple MET/SRC/PIM inhibition in MET addicted tumors
Presenter: Ilaria Attili
Session: Poster Display session 3
Resources:
Abstract