Skip to main content
. Author manuscript; available in PMC: 2016 Dec 21.
Published in final edited form as: Phys Med Biol. 2015 Nov 18;60(24):9377–9401. doi: 10.1088/0031-9155/60/24/9377

TABLE XII.

Quantitative comparison between the multi-resolution classification based method [3], joint landmark detection (Joint), individual landmark detection (Individual), and confidence-based landmark detection (Confidence) in the CT head & neck dataset.

Error (mm) chin mand_r mand_l odont_proc occ_bone Average p-value
Classification [3] 2.1±1.0 3.6±2.4 3.7±2.3 2.3±1.3 6.5±4.2 3.6±2.9 1.2 × 10−14
Joint 2.2±1.0 2.8±1.9 2.9±1.7 2.1±1.3 6.5±4.0 3.3±2.7 3.6 × 10−7
Individual 1.6±0.7 2.2±1.2 2.4±1.1 1.7±1.1 5.1±3.6 2.6±2.2 1.9 × 10−5
Confidence 1.6±0.7 2.2±1.2 2.4±1.1 1.7±1.1 2.3±1.4 2.0±1.2 N/A

p-values are computed between “Confidence” and the other methods. Bold numbers indicate the best performance.