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
4021 - Prospective pathological experience with research biopsies in the context of clinical trials at Vall d’Hebron Institute of Oncology
Presenter: Paolo Nuciforo
Session: Poster Display session 3
Resources:
Abstract
5603 - Development of a comprehensive next-generation targeted sequencing assay for detection of gene-fusions in solid tumors
Presenter: Vinay Mittal
Session: Poster Display session 3
Resources:
Abstract
4952 - Next-generation sequencing for better treatment strategy of cancer of unknown primary (CUP)
Presenter: Kang Kook Lee
Session: Poster Display session 3
Resources:
Abstract
4590 - Circulating-free DNA analysis from long-term surviving metastatic colorectal cancer patients undergoing surgery for resectable disease.
Presenter: Michele Ghidini
Session: Poster Display session 3
Resources:
Abstract
3696 - Ultra-sensitive detection of circulating tumor DNA identifies patients in high risk of recurrence in early stages melanoma
Presenter: Filip Janku
Session: Poster Display session 3
Resources:
Abstract
4295 - Identification of the founder BRCA1 mutation c.4117G>T (p.Glu1373*) recurring in Abruzzo and Lazio regions of Central Italy and predisposing to breast/ovarian and BRCA1-related cancers
Presenter: Daniela Di Giacomo
Session: Poster Display session 3
Resources:
Abstract
2214 - Enzalutamide (ENZA) and Apalutamide (APA) In vitro chemical reactivity studies and Activity in a Mouse Drug Allergy Model (MDAM)
Presenter: Mausumee Guha
Session: Poster Display session 3
Resources:
Abstract
5044 - Influence of genetic variation in COMT on cisplatin-induced nephrotoxicity in cancer patients.
Presenter: Bram Agema
Session: Poster Display session 3
Resources:
Abstract
3293 - Cardioprotective and anti-inflammatory effects of Empagliflozin during treatment with Doxorubicin: a cellular and preclinical study
Presenter: Vincenzo Quagliariello
Session: Poster Display session 3
Resources:
Abstract
3324 - Breast Cancer Organoids Model Treatment Response of HER2 Targeted Therapy in HER2-mutant Breast Cancer
Presenter: Xuelu Li
Session: Poster Display session 3
Resources:
Abstract