Multi-task deep learning-based radiomic nomogram for prognostic prediction in locoregionally advanced nasopharyngeal carcinoma

Abstract

Purpose Prognostic prediction is crucial to guide individual treatment for locoregionally advanced nasopharyngeal carcinoma (LA-NPC) patients. Recently, multi-task deep learning was explored for joint prognostic prediction and tumor segmentation in various cancers, resulting in promising performance. This study aims to evaluate the clinical value of multi-task deep learning for prognostic prediction in LA-NPC patients. Methods A total of 886 LA-NPC patients acquired from two medical centers were enrolled including clinical data, [18F]FDG PET/CT images, and follow-up of progression-free survival (PFS). We adopted a deep multi-task survival model (DeepMTS) to jointly perform prognostic prediction (DeepMTS-Score) and tumor segmentation from FDG-PET/CT images. The DeepMTS-derived segmentation masks were leveraged to extract handcrafted radiomics features, which were also used for prognostic prediction (AutoRadio-Score). Finally, we developed a multi-task deep learning-based radiomic (MTDLR) nomogram by integrating DeepMTS-Score, AutoRadio-Score, and clinical data. Harrell's concordance indices (C-index) and time-independent receiver operating characteristic (ROC) analysis were used to evaluate the discriminative ability of the proposed MTDLR nomogram. For patient stratification, the PFS rates of high- and low-risk patients were calculated using Kaplan–Meier method and compared with the observed PFS probability. Results Our MTDLR nomogram achieved C-index of 0.818 (95% confidence interval (CI): 0.785–0.851), 0.752 (95% CI: 0.638–0.865), and 0.717 (95% CI: 0.641–0.793) and area under curve (AUC) of 0.859 (95% CI: 0.822–0.895), 0.769 (95% CI: 0.642–0.896), and 0.730 (95% CI: 0.634–0.826) in the training, internal validation, and external validation cohorts, which showed a statistically significant improvement over conventional radiomic nomograms. Our nomogram also divided patients into significantly different high- and low-risk groups. Conclusion Our study demonstrated that MTDLR nomogram can perform reliable and accurate prognostic prediction in LA-NPC patients, and also enabled better patient stratification, which could facilitate personalized treatment planning.

Optimizing scan duration and tracer dose in radiomic analysis for 18F-FDG PET/MR brain cancer

“…Recent development in PET radiomics studies have shown increasing clinical value of the high order image features in predicting the chemoradiotherapy response of cancer patients [49,50]. Besides, artificial intelligence (AI) algorithms, such as neural network and support vector machine, heavily rely on the high order features of clinical image as well [51][52][53][54]. The results of our study also partially impied the impact of scan duration and tracer dose on treatment assessment and AI based analysis when using PET/MR brain imaging.…”