Limits...
Relationship between Hyperuricemia and Haar-Like Features on Tongue Images.

Cui Y, Liao S, Wang H, Liu H, Wang W, Yin L - Biomed Res Int (2015)

Bottom Line: The sensitivity of the feature with the maximum AUC value was 0.800 and specificity was 0.826 when the Youden index was maximized.Features that performed well were concentrated in the tongue root region.The locations of these discriminative features were in agreement with the interpretation of tongue appearance in traditional Chinese and Western medicine.

View Article: PubMed Central - PubMed

Affiliation: School of Computer Science and Technology, Tianjin University, 92 Weijin Road, Nankai District, Tianjin 300072, China ; Department of Common Required Courses, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Nankai District, Tianjin 300193, China.

ABSTRACT

Objective: To investigate differences in tongue images of subjects with and without hyperuricemia.

Materials and methods: This population-based case-control study was performed in 2012-2013. We collected data from 46 case subjects with hyperuricemia and 46 control subjects, including results of biochemical examinations and tongue images. Symmetrical Haar-like features based on integral images were extracted from tongue images. T-tests were performed to determine the ability of extracted features to distinguish between the case and control groups. We first selected features using the common criterion P < 0.05, then conducted further examination of feature characteristics and feature selection using means and standard deviations of distributions in the case and control groups.

Results: A total of 115,683 features were selected using the criterion P < 0.05. The maximum area under the receiver operating characteristic curve (AUC) of these features was 0.877. The sensitivity of the feature with the maximum AUC value was 0.800 and specificity was 0.826 when the Youden index was maximized. Features that performed well were concentrated in the tongue root region.

Conclusions: Symmetrical Haar-like features enabled discrimination of subjects with and without hyperuricemia in our sample. The locations of these discriminative features were in agreement with the interpretation of tongue appearance in traditional Chinese and Western medicine.

No MeSH data available.


Related in: MedlinePlus

Three features on the green color plain examined in this study. Panel (a) contains 5950 pixels, (b) contains 300 pixels, and (c) contains 200 pixels.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4414229&req=5

fig5: Three features on the green color plain examined in this study. Panel (a) contains 5950 pixels, (b) contains 300 pixels, and (c) contains 200 pixels.

Mentions: Initial screening of features using the criterion P < 0.05 yielded a sample of 239,035 features. Selection based on color plains reduced the number of features to several fractions of the original, yielding 97,124 features on the red plain, 26,228 features on the green plain, and 115,683 features on the blue plain that were useful for the diagnosis of hyperuricemia (all P < 0.05). The largest features on the red, green, and blue color plains, all of which were in the centers of tongue images, were feature (11,21,40,85) (P = 1.72 × 10−2; Figure 4(a)), feature (12,11,35,85) (P = 3.11 × 10−2; Figure 5(a)), and feature (11,21,40,85) (P = 1.19 × 10−3; Figure 6(a)), respectively (Table 1). The smallest P values were obtained for feature (30,23,10,30) (P = 2.09 × 10−7; Figure 4(b)), feature (33,24,10,15) (P = 1.16 × 10−4; Figure 5(b)), and feature (29,11,20,30) (P = 4.85 × 10−11; Figure 6(b)) on the red, green, and blue color plains, respectively (Table 1). Features with the largest df values in the red, green, and blue plains were feature (30,23,10,30) (df = 1.19; Figure 4(b)), feature (38,24,10,10) (df = 8.48 × 10−1; Figure 5(c)), and feature (30,11,20,30) (df = 1.58; Figure 6(c)), respectively (Table 1). Feature (30,23,10,30) in the red plain had both the smallest P value and largest df value.


Relationship between Hyperuricemia and Haar-Like Features on Tongue Images.

Cui Y, Liao S, Wang H, Liu H, Wang W, Yin L - Biomed Res Int (2015)

Three features on the green color plain examined in this study. Panel (a) contains 5950 pixels, (b) contains 300 pixels, and (c) contains 200 pixels.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4414229&req=5

fig5: Three features on the green color plain examined in this study. Panel (a) contains 5950 pixels, (b) contains 300 pixels, and (c) contains 200 pixels.
Mentions: Initial screening of features using the criterion P < 0.05 yielded a sample of 239,035 features. Selection based on color plains reduced the number of features to several fractions of the original, yielding 97,124 features on the red plain, 26,228 features on the green plain, and 115,683 features on the blue plain that were useful for the diagnosis of hyperuricemia (all P < 0.05). The largest features on the red, green, and blue color plains, all of which were in the centers of tongue images, were feature (11,21,40,85) (P = 1.72 × 10−2; Figure 4(a)), feature (12,11,35,85) (P = 3.11 × 10−2; Figure 5(a)), and feature (11,21,40,85) (P = 1.19 × 10−3; Figure 6(a)), respectively (Table 1). The smallest P values were obtained for feature (30,23,10,30) (P = 2.09 × 10−7; Figure 4(b)), feature (33,24,10,15) (P = 1.16 × 10−4; Figure 5(b)), and feature (29,11,20,30) (P = 4.85 × 10−11; Figure 6(b)) on the red, green, and blue color plains, respectively (Table 1). Features with the largest df values in the red, green, and blue plains were feature (30,23,10,30) (df = 1.19; Figure 4(b)), feature (38,24,10,10) (df = 8.48 × 10−1; Figure 5(c)), and feature (30,11,20,30) (df = 1.58; Figure 6(c)), respectively (Table 1). Feature (30,23,10,30) in the red plain had both the smallest P value and largest df value.

Bottom Line: The sensitivity of the feature with the maximum AUC value was 0.800 and specificity was 0.826 when the Youden index was maximized.Features that performed well were concentrated in the tongue root region.The locations of these discriminative features were in agreement with the interpretation of tongue appearance in traditional Chinese and Western medicine.

View Article: PubMed Central - PubMed

Affiliation: School of Computer Science and Technology, Tianjin University, 92 Weijin Road, Nankai District, Tianjin 300072, China ; Department of Common Required Courses, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Nankai District, Tianjin 300193, China.

ABSTRACT

Objective: To investigate differences in tongue images of subjects with and without hyperuricemia.

Materials and methods: This population-based case-control study was performed in 2012-2013. We collected data from 46 case subjects with hyperuricemia and 46 control subjects, including results of biochemical examinations and tongue images. Symmetrical Haar-like features based on integral images were extracted from tongue images. T-tests were performed to determine the ability of extracted features to distinguish between the case and control groups. We first selected features using the common criterion P < 0.05, then conducted further examination of feature characteristics and feature selection using means and standard deviations of distributions in the case and control groups.

Results: A total of 115,683 features were selected using the criterion P < 0.05. The maximum area under the receiver operating characteristic curve (AUC) of these features was 0.877. The sensitivity of the feature with the maximum AUC value was 0.800 and specificity was 0.826 when the Youden index was maximized. Features that performed well were concentrated in the tongue root region.

Conclusions: Symmetrical Haar-like features enabled discrimination of subjects with and without hyperuricemia in our sample. The locations of these discriminative features were in agreement with the interpretation of tongue appearance in traditional Chinese and Western medicine.

No MeSH data available.


Related in: MedlinePlus