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
2507 - KEYLYNK-010: Phase 3 Study of Pembrolizumab (pembro) Plus Olaparib (OLA) vs Enzalutamide (ENZA) or Abiraterone (ABI) in ENZA- or ABI-Pretreated Patients (pts) With Metastatic Castration-Resistant Prostate Cancer (mCRPC) Who Had Progression on Chemotherapy (CTx)
Presenter: Evan Yu
Session: Poster Display session 3
Resources:
Abstract
2944 - PROSTRATEGY: A Spanish Genitourinary Oncology Group (SOGUG) multi-arm multistage (MAMS) phase III trial of immunotherapy strategies in high-volume metastasic hormone-sensitive prostate cancer.
Presenter: Jose Arranz Arija
Session: Poster Display session 3
Resources:
Abstract
3535 - A phase 1 study of AMG 160, a half-life extended bispecific T cell engager (HLE BiTE) immuno-oncology therapy targeting PSMA, in patients (pts) with metastatic castration-resistant prostate cancer (mCRPC)
Presenter: Ben Tran
Session: Poster Display session 3
Resources:
Abstract
4951 - ProBio: An outcome-adaptive, multi-arm, open-label, multiple assignment randomised controlled biomarker-driven trial in patients with metastatic castration-resistant prostate cancer (EudraCT: 2018-002350-78, NCT03903835)
Presenter: Johan Lindberg
Session: Poster Display session 3
Resources:
Abstract
2892 - A phase 3 randomized, placebo-controlled, double-blind study of niraparib plus abiraterone acetate and prednisone versus abiraterone acetate and prednisone in patients with metastatic prostate cancer (NCT03748641)
Presenter: Kim Chi
Session: Poster Display session 3
Resources:
Abstract
2427 - The Extended/Phase II Study of Safety And Tolerability Of Proxalutamide (GT0918) In Subjects With Metastatic Castrate Resistant Prostate Cancer (mCRPC) Who Failed Either Abiraterone (Abi) Or Enzalutamide (Enza)
Presenter: Nicholas Vogelzang
Session: Poster Display session 3
Resources:
Abstract
3224 - Addition of an oral docetaxel treatment (ModraDoc006/r) to androgen deprivation therapy (ADT) and intensity-modulated radiation therapy (IMRT) in patients with high risk N+M0 prostate cancer
Presenter: Marit Vermunt
Session: Poster Display session 3
Resources:
Abstract
3312 - A phase II randomized, open-label study comparing salvage radiotherapy in combination with 6 months of androgen-deprivation therapy with LHRH agonist or antagonist versus anti-androgen therapy with apalutamide in patients with biochemical progression after radical prostatectomy.
Presenter: Piet Dirix
Session: Poster Display session 3
Resources:
Abstract
2829 - Health-Related Quality of Life (HRQoL) and Updated Follow-Up From KEYNOTE-057: Phase 2 Study of Pembrolizumab (pembro) for Patients (pts) With High-Risk (HR) Non–Muscle Invasive Bladder Cancer (NMIBC) Unresponsive to Bacillus Calmette-Guérin (BCG)
Presenter: Ronald de Wit
Session: Poster Display session 3
Resources:
Abstract
2673 - Clinical activity of vofatamab (V), an FGFR3 selective antibody in combination with pembrolizumab (P) in metastatic urothelial carcinoma (mUC), updated interim analysis of FIERCE-22
Presenter: Arlene Siefker-Radtke
Session: Poster Display session 3
Resources:
Abstract