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
3611 - Phase II trial of SM 88 in Non-Metastatic Biochemical Recurrent Prostate Cancer.
Presenter: Benjamin Gartrell
Session: Poster Display session 3
Resources:
Abstract
2492 - A phase 1 study of Ad5 PSA/MUC-1/Brachyury Vaccine in Patients with Metastatic Castration Resistant Prostate Cancer (mCRPC)
Presenter: Marijo Bilusic
Session: Poster Display session 3
Resources:
Abstract
3142 - Multicenter Phase I Trial of a DNA Vaccine Encoding the Androgen Receptor Ligand Binding Domain (pTVG-AR, MVI-118) in Patients with Metastatic Prostate Cancer
Presenter: Douglas McNeel
Session: Poster Display session 3
Resources:
Abstract
4327 - Impact of germline mutations in Homologous Recombination (HR) genes on the response to Radium-223 for metastatic castration resistant prostate cancer (mCRPC)
Presenter: Elena Castro
Session: Poster Display session 3
Resources:
Abstract
3600 - Serum biomarkers of bone metabolism in metastatic castration-resistant prostate cancer (mCRPC) patients (pts) treated with Radium-223 (Ra223): Results from a prospective multicentre study
Presenter: Nuria Romero Laorden
Session: Poster Display session 3
Resources:
Abstract
3742 - Prognostic value of tumor suppression genes (TP53, PTEN, Rb) in metastatic hormone sensitive prostate cancer
Presenter: Miguel Gonzalez Velez
Session: Poster Display session 3
Resources:
Abstract
2643 - Germline sequencing of advanced prostate cancer patients in the BARCODE2 trial
Presenter: Sarah Benafif
Session: Poster Display session 3
Resources:
Abstract
4349 - Impact of treatment sequence in patients (pts) with metastatic castration-resistant prostate cancer (mCRPC): data from the prospective PROREPAIR-B study.
Presenter: Carlo Cattrini
Session: Poster Display session 3
Resources:
Abstract
3301 - Implications of Single Nucleotide Polymorphisms (SNPs) in Androgen Related-Genes in Outcome of metastatic castration-resistant prostate cancer (mCRPC) patients treated with Abiraterone (Abi) and Enzalutamide (Enza)
Presenter: Isabel Aragon
Session: Poster Display session 3
Resources:
Abstract
2275 - Activating mutations in AKT1/PIK3CA are associated with poor clinical outcomes in metastatic prostate cancer (mPC)
Presenter: Simon Fu
Session: Poster Display session 3
Resources:
Abstract