RATIONALE AND OBJECTIVES: In quantifying medical images, length-based measurements are still obtained manually. Due to possible human error, a measurement protocol is required to guarantee the consistency of measurements. In this work, we review various statistical techniques that can be used in determining measurement consistency. The focus is on detecting a possible measurement bias and determining the robustness of the procedures to outliers. MATERIALS AND METHODS: We review correlation analysis, linear regression, Bland-Altman method, paired t-test, and analysis of variance (ANOVA). These techniques were applied to measurements, obtained by two raters, of head and neck structures from magnetic resonance images. RESULTS: The correlation analysis and the linear regression were shown to be insufficient for detecting measurement inconsistency. They are also very sensitive to outliers. The widely used Bland-Altman method is a visualization technique, so it lacks the numeric quantification. The paired t-test tends to be sensitive to small measurement bias. In contrast, ANOVA performs well even under small measurement bias. CONCLUSIONS: In almost all cases, using only one method is insufficient and it is recommended that several methods be used simultaneously. In general, ANOVA performs the best.
RATIONALE AND OBJECTIVES: In quantifying medical images, length-based measurements are still obtained manually. Due to possible human error, a measurement protocol is required to guarantee the consistency of measurements. In this work, we review various statistical techniques that can be used in determining measurement consistency. The focus is on detecting a possible measurement bias and determining the robustness of the procedures to outliers. MATERIALS AND METHODS: We review correlation analysis, linear regression, Bland-Altman method, paired t-test, and analysis of variance (ANOVA). These techniques were applied to measurements, obtained by two raters, of head and neck structures from magnetic resonance images. RESULTS: The correlation analysis and the linear regression were shown to be insufficient for detecting measurement inconsistency. They are also very sensitive to outliers. The widely used Bland-Altman method is a visualization technique, so it lacks the numeric quantification. The paired t-test tends to be sensitive to small measurement bias. In contrast, ANOVA performs well even under small measurement bias. CONCLUSIONS: In almost all cases, using only one method is insufficient and it is recommended that several methods be used simultaneously. In general, ANOVA performs the best.
Authors: Houri K Vorperian; Ray D Kent; Mary J Lindstrom; Cliff M Kalina; Lindell R Gentry; Brian S Yandell Journal: J Acoust Soc Am Date: 2005-01 Impact factor: 1.840
Authors: E Vallejo; D P Dione; W L Bruni; R T Constable; P P Borek; J P Soares; J G Carr; S G Condos; F J Wackers; A J Sinusas Journal: J Nucl Med Date: 2000-05 Impact factor: 10.057
Authors: Thor Edvardsen; Bernhard L Gerber; Jérôme Garot; David A Bluemke; João A C Lima; Otto A Smiseth Journal: Circulation Date: 2002-07-02 Impact factor: 29.690
Authors: Michael P Kelly; Houri K Vorperian; Yuan Wang; Katelyn K Tillman; Helen M Werner; Moo K Chung; Lindell R Gentry Journal: Arch Oral Biol Date: 2017-01-23 Impact factor: 2.633
Authors: Houri K Vorperian; Shubing Wang; E Michael Schimek; Reid B Durtschi; Ray D Kent; Lindell R Gentry; Moo K Chung Journal: J Speech Lang Hear Res Date: 2010-11-24 Impact factor: 2.297
Authors: Houri K Vorperian; Shubing Wang; Moo K Chung; E Michael Schimek; Reid B Durtschi; Ray D Kent; Andrew J Ziegert; Lindell R Gentry Journal: J Acoust Soc Am Date: 2009-03 Impact factor: 1.840
Authors: Brian J Whyms; Houri K Vorperian; Lindell R Gentry; Eugene M Schimek; Edward T Bersu; Moo K Chung Journal: Oral Surg Oral Med Oral Pathol Oral Radiol Date: 2013-05