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
3988 - Basal NK activity and early Treg function inhibition predicts Nivolumab responsiveness in metastatic renal cancer patients (REVOLUTION) trial.
Presenter: Sara Santagata
Session: Poster Display session 3
Resources:
Abstract
2142 - Low NK Cell Abundance Correlates with High Expression of PD-1 in CD8+ T Cells
Presenter: Moon Hee Lee
Session: Poster Display session 3
Resources:
Abstract
5501 - Tobacco smoking is associated with the immune suppressive microenvironment in head and neck squamous cell carcinoma (HNSCC)
Presenter: Christine Chung
Session: Poster Display session 3
Resources:
Abstract
5726 - Evaluation of Antibody-Dependent Cell Cytotoxicity (ADCC) in lung cancer cell lines treated with combined anti-EGFR and anti-PD-L1 therapy.
Presenter: Francesca Sparano
Session: Poster Display session 3
Resources:
Abstract
2534 - Radiomic Signatures for Identification of Tumors Sensitive to Nivolumab or Docetaxel in Squamous Non-Small Cell Lung Cancer (sqNSCLC)
Presenter: Laurent Dercle
Session: Poster Display session 3
Resources:
Abstract
3366 - Analysis of gut microbiota in advanced non-small cell lung cancer (NSCLC) patients treated with immune-checkpoints blockers
Presenter: FEIYU ZHANG
Session: Poster Display session 3
Resources:
Abstract
2089 - Pathogenesis of Myocarditis Following Treatment with Immune Checkpoint Inhibitors in a Cynomolgus Monkey Model
Presenter: Changhua Ji
Session: Poster Display session 3
Resources:
Abstract
4463 - Effects of dietary restriction in cancer patients receiving irinotecan
Presenter: Ruben Van Eerden
Session: Poster Display session 3
Resources:
Abstract
4841 - Investigating the Link between Burn Injury and Tumorigenesis
Presenter: Lucy Barrett
Session: Poster Display session 3
Resources:
Abstract
4619 - Prognostic value of the neutrophil-lymphocyte, platelet-lymphocyte and monocyte-lymphocyte ratio in male breast cancer patients
Presenter: Joanna Huszno
Session: Poster Display session 3
Resources:
Abstract