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
4900 - Molecular profiling and prognostic significance of TP53 mutations in Diffuse Large B Cell Lymphoma: identifying a high-risk subgroup
Presenter: Yuan-Kai Shi
Session: Poster Display session 3
Resources:
Abstract
3809 - Differential expression of various miRNAs in Pediatric Cytogenetically Normal Acute Myeloid Leukemia (CN-AML)
Presenter: Vikas Gaur
Session: Poster Display session 3
Resources:
Abstract
4750 - Circulating tumour cells in head and neck and non-small cell lung cancer
Presenter: Kenneth O'Byrne
Session: Poster Display session 3
Resources:
Abstract
3704 - OX40/OX40L protein expression in Non-small cell lung cancer and its role in clinical outcome and relationships with other immune biomarkers
Presenter: Xiaoshen Zhang
Session: Poster Display session 3
Resources:
Abstract
2235 - Effect of Serum Survivin on Survival among Non-Small Cell Lung Cancer Patients; NCI Experience
Presenter: Reham Rashed
Session: Poster Display session 3
Resources:
Abstract
2788 - Enhanced performance of prognostic estimation from TCGA RNAseq data using transfer learning.
Presenter: Helene Vanacker
Session: Poster Display session 3
Resources:
Abstract
4689 - Analysis of Circulating Tumor DNA for Early Relapse Detection in Stage III Colorectal Cancer After Adjuvant Chemotherapy
Presenter: Samuel Jacobs
Session: Poster Display session 3
Resources:
Abstract
1454 - Ascites-derived circulating microRNAs as potential diagnostic biomarkers of gastric cancer-associated malignant ascites
Presenter: Hye Sook Han
Session: Poster Display session 3
Resources:
Abstract
5574 - Results from TRIO030, a Pre-Surgical Tissue-Acquisition Study to Evaluate Molecular Alterations in Human Breast Cancer Tissue Following Short-Term Exposure to the Androgen Receptor Antagonist Darolutamide
Presenter: Hsiao-Wang Chen
Session: Poster Display session 3
Resources:
Abstract
1787 - JMJD2A is a novel epigenetic factor of chemotherapeutic susceptibility in gastric cancer
Presenter: Yasushi Sato
Session: Poster Display session 3
Resources:
Abstract