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
5218 - Elevated driver mutational burden or number of perturbed pathways and poor response to abiraterone or enzalutamide in metastatic castration-resistant prostate cancer
Presenter: Bram De Laere
Session: Poster Display session 3
Resources:
Abstract
2452 - High proportion of multiple KRAS mutations in circulating tumor DNA and tumor tissue of pancreatic ductal adenocarcinoma
Presenter: Min Kyeong Kim
Session: Poster Display session 3
Resources:
Abstract
3328 - Biological difference of tumor mutational burden (TMB) and microsatellite instability (MSI) status in patients (pts) with somatic vs. germline BRCA1/2-mutated advanced gastrointestinal (GI) cancers using cell-free DNA (cfDNA) sequencing analysis in the GOZILA study
Presenter: Yasuyuki Kawamoto
Session: Poster Display session 3
Resources:
Abstract
3022 - Cell-Free DNA to Detect Focal Versus Non-Focal MET Amplification in Metastatic Colorectal Cancer Patients: Combined Analysis from Japan and the United States
Presenter: Mishima Saori
Session: Poster Display session 3
Resources:
Abstract
2833 - Presence of circulating tumor DNA in surgically resected renal cell carcinoma is associated with advanced disease and poor patient prognosis
Presenter: Andres Correa
Session: Poster Display session 3
Resources:
Abstract
1376 - Combined genomic and epigenomic assessment of cell-free circulating tumor DNA (cfDNA) for cancer diagnosis and recurrence-risk assessment in early-stage lung cancer
Presenter: Junghee Lee
Session: Poster Display session 3
Resources:
Abstract
4050 - DEMo: a prospective evaluation of a prognostic clinico-molecular composite score in NSCLC patients treated with immunotherapy.
Presenter: Arsela Prelaj
Session: Poster Display session 3
Resources:
Abstract
4727 - Bespoke circulating tumor DNA (ctDNA) analysis as a predictive biomarker in solid tumor patients (pts) treated with single agent pembrolizumab (P)
Presenter: Cindy Yang
Session: Poster Display session 3
Resources:
Abstract
3662 - Dynamic changes in whole-genome cell-free DNA (cfDNA) to identify disease progression prior to imaging in advanced solid tumors
Presenter: Andrew Davis
Session: Poster Display session 3
Resources:
Abstract
3817 - Evaluation of Microsatellite Instability Testing Through cell-free DNA sequencing
Presenter: Shile Zhang
Session: Poster Display session 3
Resources:
Abstract