DeepMTS: Deep Multi-Task Learning for Survival Prediction in Patients With Advanced Nasopharyngeal Carcinoma Using Pretreatment PET/CT

• Published in: IEEE journal of biomedical and health informatics 2022-09, Vol.26 (9), p.4497-4507
• Main Authors: Meng, Mingyuan, Gu, Bingxin, Bi, Lei, Song, Shaoli, Feng, David Dagan, Kim, Jinman
• Format: Article
• Language: English
• Subjects: Cancer; Deep learning; Feature extraction; Image processing; Image segmentation; Lymph nodes; Metastases; Multi-task learning; Multitasking; Nasopharyngeal carcinoma; nasopharyngeal carcinoma (NPC); Nasopharynx; Patients; PET/CT; Prediction models; Predictive models; Pretreatment; Radiomics; Survival; survival prediction; Task analysis; Throat cancer; Tumors
• ISSN: 2168-2194; 2168-2208
• DOI: 10.1109/JBHI.2022.3181791

Nasopharyngeal Carcinoma (NPC) is a malignant epithelial cancer arising from the nasopharynx. Survival prediction is a major concern for NPC patients, as it provides early prognostic information to plan treatments. Recently, deep survival models based on deep learning have demonstrated the potential to outperform traditional radiomics-based survival prediction models. Deep survival models usually use image patches covering the whole target regions (e.g., nasopharynx for NPC) or containing only segmented tumor regions as the input. However, the models using the whole target regions will also include non-relevant background information, while the models using segmented tumor regions will disregard potentially prognostic information existing out of primary tumors (e.g., local lymph node metastasis and adjacent tissue invasion). In this study, we propose a 3D end-to-end Deep Multi-Task Survival model (DeepMTS) for joint survival prediction and tumor segmentation in advanced NPC from pretreatment PET/CT. Our novelty is the introduction of a hard-sharing segmentation backbone to guide the extraction of local features related to the primary tumors, which reduces the interference from non-relevant background information. In addition, we also introduce a cascaded survival network to capture the prognostic information existing out of primary tumors and further leverage the global tumor information (e.g., tumor size, shape, and locations) derived from the segmentation backbone. Our experiments with two clinical datasets demonstrate that our DeepMTS can consistently outperform traditional radiomics-based survival prediction models and existing deep survival models.