Application of Artificial Intelligence for Nasopharyngeal Carcinoma Management - A Systematic Review

• Type of Material: Article
• Authors: Wai Tong Ng, University of Hong Kong; Barton But, University of Hong Kong; Horace CW Choi, University of Hong Kong; Remco de Bree, University Medical Center Utrecht; Anne WM Lee, University of Hong Kong; Victor HF Lee, University of Hong Kong; Fernando Lopez, University of Oviedo; Antti A Makitie, HUS Helsinki Univ Hosp; Juan P Rodrigo, University of Oviedo; Nabil Saba, Emory University; Raymond KY Tsang, University of Hong Kong; Alfio Ferlito, Head and Neck Scientific Group
• Language: English
• Date: 2022-01-01
• Publisher: DOVE MEDICAL PRESS LTD
• Publication Version: Final Published Version
• Copyright Statement: © 2022 Ng et al.
• License: Creative Commons Attribution-Noncommercial 3.0 Unported
• Final Published Version (URL): http://dx.doi.org/10.2147/CMAR.S341583
• Title of Journal or Parent Work: CANCER MANAGEMENT AND RESEARCH
• Volume: 14
• Start Page: 339
• End Page: 366
• Keywords: RADIOTHERAPY; Oncology; auto; Science & Technology; contouring; deep learning; MRI; NEURAL-NETWORKS; STAGE; prognosis; Life Sciences & Biomedicine; FEATURES; diagnosis; SEGMENTATION; neural network; MODEL; machine learning; VOLUME
• Research Categories: Health Sciences, Oncology; Health Sciences, Public Health

Abstract

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.