AUTHOR=Gu Bingxin , Meng Mingyuan , Bi Lei , Kim Jinman , Feng David Dagan , Song Shaoli 

TITLE=Prediction of 5-year progression-free survival in advanced nasopharyngeal carcinoma with pretreatment PET/CT using multi-modality deep learning-based radiomics

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.899351

DOI=10.3389/fonc.2022.899351

ISSN=2234-943X

ABSTRACT=Objective: Deep Learning-based Radiomics (DLR) has achieved great success in medical image analysis and has been considered as a replacement to conventional radiomics that relies on handcrafted features. In this study, we aimed to explore the capability of DLR for the prediction of 5-year Progression-Free Survival (PFS) in advanced Nasopharyngeal Carcinoma (NPC) using pretreatment PET/CT images.
Methods: A total of 257 patients (170/87 patients in internal/external cohorts) with advanced NPC (TNM stage III or IVa) were enrolled. We developed an end-to-end multi-modality DLR model, in which a 3D convolutional neural network was optimized to extract deep features from pretreatment PET/CT images and predict the probability of 5-year PFS. TNM stage, as a high-level clinical feature, could be integrated into our DLR model to further improve the prognostic performance. For a comparison between conventional radiomics and DLR, 1456 handcrafted features were extracted, and optimal conventional radiomics methods were selected from 54 cross-combinations of 6 feature selection methods and 9 classification methods. In addition, risk group stratification was performed with clinical signature, conventional radiomics signature, and DLR signature.
Results: Our multi-modality DLR model using both PET and CT achieved higher prognostic performance (AUC = 0.842  0.034 and 0.823  0.012 for the internal and external cohorts) than the optimal conventional radiomics method (AUC = 0.796  0.033 and 0.782  0.012). Furthermore, the multi-modality DLR model outperformed single-modality DLR models using only PET (AUC = 0.818  0.029 and 0.796  0.009) or only CT (AUC = 0.657  0.055 and 0.645  0.021). For risk group stratification, the conventional radiomics signature and DLR signature enabled significant difference between the high- and low-risk patient groups in the both internal and external cohorts (P < 0.001), while the clinical signature failed in the external cohort (P = 0.177).
Conclusion: Our study identified potential prognostic tools for survival prediction in advanced NPC, which suggests that DLR could provide complementary values to the current TNM staging.