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
2664 - Phase (Ph) II study of MBG453 + spartalizumab in patients (pts) with non-small cell lung cancer (NSCLC) and melanoma pretreated with anti–PD-1/L1 therapy
Presenter: Nicholas Mach
Session: Poster Display session 3
Resources:
Abstract
1285 - Preliminary results of STELLAR-001, a dose escalation phase I study of the anti-C5aR, IPH5401, in combination with durvalumab in advanced solid tumors.
Presenter: Christophe Massard
Session: Poster Display session 3
Resources:
Abstract
3808 - GOLFIG chemo-immunotherapy in metastatic colorectal cancer (mCRC) patients: A fifteen year retrospective analysis
Presenter: Pierpaolo Correale
Session: Poster Display session 3
Resources:
Abstract
5677 - Immune correlates in peripheral blood samples in a preoperative window of opportunity randomized trial of nivolumab with or without tadalafil in resectable squamous cell carcinoma of the head and neck (SCCHN)
Presenter: Larry Harshyne
Session: Poster Display session 3
Resources:
Abstract
4854 - Phase 1 evaluation of AB928, a novel dual adenosine receptor antagonist, combined with chemotherapy or AB122 (anti-PD-1) in patients (pts) with advanced malignancies
Presenter: John Powderly
Session: Poster Display session 3
Resources:
Abstract
4344 - Phase 1 Trial of CV301 in Combination with Anti-PD-1 Therapy in Non-squamous NSCLC
Presenter: Arun Rajan
Session: Poster Display session 3
Resources:
Abstract
4555 - Safety and efficacy results of the combination of DPX-Survivac, pembrolizumab and intermittent low dose cyclophosphamide (CPA) in subjects with advanced and metastatic solid tumors: preliminary results from the hepatocellular carcinoma (HCC), NSCLC, bladder cancer, & MSI-H cohorts
Presenter: Henry Conter
Session: Poster Display session 3
Resources:
Abstract
3012 - Excellent CBR and Prolonged PFS in Non-Squamous NSCLC with Oral CA-170, an Inhibitor of VISTA and PD-L1
Presenter: Vivek Radhakrishnan
Session: Poster Display session 3
Resources:
Abstract
2536 - Phase Ib/II trial of TG4001 (Tipapkinogene sovacivec), a therapeutic HPV-vaccine, and Avelumab in patients with recurrent/metastatic (R/M) HPV-16+ cancers
Presenter: Christophe Le Tourneau
Session: Poster Display session 3
Resources:
Abstract
1845 - Induction of tumor-infiltrating functional CD8 positive cells and PD-L1 expression in esophageal cancer by S-588410
Presenter: Takashi Kojima
Session: Poster Display session 3
Resources:
Abstract