Evaluation and Comparison of Anatomical Landmark Detection Methods for Cephalometric X-Ray Images: A Grand Challenge

• Published in: IEEE transactions on medical imaging Vol. 34; no. 9; pp. 1890 - 1900
• Main Authors: Ching-Wei Wang, Cheng-Ta Huang, Meng-Che Hsieh, Chung-Hsing Li, Sheng-Wei Chang, Wei-Cheng Li, Vandaele, Remy, Maree, Raphael, Jodogne, Sebastien, Geurts, Pierre, Cheng Chen, Guoyan Zheng, Chengwen Chu, Mirzaalian, Hengameh, Hamarneh, Ghassan, Vrtovec, Tomaz, Ibragimov, Bulat
• Format: Journal Article Web Resource
• Language: English
• Published: United States IEEE 01.09.2015
• Subjects: Adolescent; Adult; Anatomic Landmarks - diagnostic imaging; Biomedical imaging; Cephalometric analysis; Cephalometry - methods; challenge; Child; Computer science; dental X-ray images; Dentistry; Detectors; Engineering, computing & technology; evaluation; Head - anatomy & histology; Head - diagnostic imaging; Humans; Image Processing, Computer-Assisted - methods; Ingénierie, informatique & technologie; Landmark Detection; Medical Imaging; Middle Aged; Radiography, Dental; Sciences informatiques; Shape; Training; X-ray imaging; Young Adult
• ISSN: 0278-0062; 1558-254X; 1558-254X
• DOI: 10.1109/TMI.2015.2412951

Cephalometric analysis is an essential clinical and research tool in orthodontics for the orthodontic analysis and treatment planning. This paper presents the evaluation of the methods submitted to the Automatic Cephalometric X-Ray Landmark Detection Challenge, held at the IEEE International Symposium on Biomedical Imaging 2014 with an on-site competition. The challenge was set to explore and compare automatic landmark detection methods in application to cephalometric X-ray images. Methods were evaluated on a common database including cephalograms of 300 patients aged six to 60 years, collected from the Dental Department, Tri-Service General Hospital, Taiwan, and manually marked anatomical landmarks as the ground truth data, generated by two experienced medical doctors. Quantitative evaluation was performed to compare the results of a representative selection of current methods submitted to the challenge. Experimental results show that three methods are able to achieve detection rates greater than 80% using the 4 mm precision range, but only one method achieves a detection rate greater than 70% using the 2 mm precision range, which is the acceptable precision range in clinical practice. The study provides insights into the performance of different landmark detection approaches under real-world conditions and highlights achievements and limitations of current image analysis techniques.