A review on cephalometric landmark detection techniques. (April 2021)

• Record Type: Journal Article
• Authors: Juneja, Mamta; Garg, Poojita; Kaur, Ravinder; Manocha, Palak; Prateek, ; Batra, Shivam; Singh, Pradeep; Singh, Shaswat; Jindal, Prashant
• Is Part Of: Biomedical signal processing and control. Volume 66(2021)
• Publication Date: 2021-04
• Subjects: Cephalometric analysis -- Landmark identification -- X-ray -- Knowledge based systems -- Artificial intelligence -- Machine learning; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102486
• Languages: English
• ISSNs: 1746-8094

Abstract

Graphical abstract: Categorization of landmark identification techniques. Highlights: Distinct knowledge based, machine learning and deep learning based cephalometric landmarking techniques are explored. Different imaging modalities used for the cephalometric analysis are analysed. Various applications of cephalometric tracing are highlighted. Several commercially available cephalometric software is presented. Abstract: Landmark identification is crucial in quantifying cephalometric analysis. Manual tracing of landmarks is a tedious, laborious task and prone to human errors, thereby, necessitating a need to develop efficient automated methods for landmark identification. The advent of artificial intelligence and machine learning has made the automation of cephalometric landmarking, seemingly possible. Techniques such as active shape modelling, active appearance modelling, random forest regression-voting, Convolutional Neural Network (CNN), fuzzy systems and many others have rendered promising results in this field. This work reviews and critically analyses various techniques used for cephalometric landmark identification. This study also highlights current applications, addresses gaps in literature and presents the open challenges in this field.