Introduction
Nasopharyngeal carcinoma (NPC) is endemic to Eastern and South-Eastern Asia, and, in 2020, 77% of global cases were diagnosed in these regions. Apart from its distinct epidemiology, the natural behavior, treatment, and prognosis are different from other head and neck cancers. With the growing trend of artificial intelligence (AI), especially deep learning (DL), in head and neck cancer care, we sought to explore the unique clinical application and implementation direction of AI in the management of NPC.
Methods
The search protocol was performed to collect publications using AI, machine learning (ML) and DL in NPC management from PubMed, Scopus and Embase. The articles were filtered using inclusion and exclusion criteria, and the quality of the papers was assessed. Data were extracted from the finalized articles.
Results
A total of 78 articles were reviewed after removing duplicates and papers that did not meet the inclusion and exclusion criteria. After quality assessment, 60 papers were included in the current study. There were four main types of applications, which were auto-contouring, diagnosis, prognosis, and miscellaneous applications (especially on radiotherapy planning). The different forms of convolutional neural networks (CNNs) accounted for the majority of DL algorithms used, while the artificial neural network (ANN) was the most frequent ML model implemented.
Conclusion
There is an overall positive impact identified from AI implementation in the management of NPC. With improving AI algorithms, we envisage AI will be available as a routine application in a clinical setting soon.
Background The current recommendation for locoregionally advanced nasopharyngeal carcinoma (NPC) patients is cisplatin-based induction (IC) or adjuvant (AC) chemotherapy plus concurrent chemoradiotherapy (CRT). However, data on the optimal platinum doses for each phase of combined regimens are lacking. Patients and Methods 742 NPC patients in the NPC-0501 Trial treated with CRT plus IC/AC and irradiated with intensity-modulated radiotherapy (IMRT) were analyzed. The optimal platinum dose to achieve the best overall survival (OS) in the concurrent and induction/adjuvant phases were studied. Results Evaluation of the whole series shows the optimal platinum dose was 160 mg/m2 in the concurrent and 260 mg/m2 in the induction/adjuvant phase. Repeating the analyses on 591 patients treated with cisplatin throughout (no replacement by carboplatin) confirmed the same results. The cohort with optimal platinum doses in both phases had better OS than the cohort suboptimal in both phases (Stage III: 90% vs 75%, Stage IVA-B: 80% vs 56%, at 5-year). Multivariable analyses confirmed optimal platinum doses in both phases vs. suboptimal dose in each phase are significant independent factors for OS, with hazard ratio of 0.61 (95% confidence interval [CI]=0.41-0.91) and 0.67 (95% CI=0.48-0.94), respectively. Treatment sequence was statistically insignificant after adjusting for platinum doses. Conclusion Both concurrent and IC/AC are needed for locoregionally advanced NPC, even for patients irradiated by IMRT; the concurrent platinum dosage could be set at {greater than or equal to}160 mg/m2 when coupled with adequate induction/adjuvant dosage at {greater than or equal to}260 mg/m2 (or at least {greater than or equal to}240 mg/m2). To achieve these optimal dosages, IC-CRT at conventional fractionation is favored.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.