Computerized tongue image segmentation via the double geo-vector flow

BackgroundVisual inspection for tongue analysis is a diagnostic method in traditional Chinese medicine (TCM). Owing to the variations in tongue features, such as color, texture, coating, and shape, it is difficult to precisely extract the tongue region in images. This study aims to quantitatively evaluate tongue diagnosis via automatic tongue segmentation.MethodsExperiments were conducted using a clinical image dataset provided by the Laboratory of Traditional Medical Syndromes, Shanghai University of TCM. First, a clinical tongue image was refined by a saliency window. Second, we initialized the tongue area as the upper binary part and lower level set matrix. Third, a double geo-vector flow (DGF) was proposed to detect the tongue edge and segment the tongue region in the image, such that the geodesic flow was evaluated in the lower part, and the geo-gradient vector flow was evaluated in the upper part.ResultsThe performance of the DGF was evaluated using 100 images. The DGF exhibited better results compared with other representative studies, with its true-positive volume fraction reaching 98.5%, its false-positive volume fraction being 1.51%, and its false-negative volume fraction being 1.42%. The errors between the proposed automatic segmentation results and manual contours were 0.29 and 1.43% in terms of the standard boundary error metrics of Hausdorff distance and mean distance, respectively.ConclusionsBy analyzing the time complexity of the DGF and evaluating its performance via standard boundary and area error metrics, we have shown both efficiency and effectiveness of the DGF for automatic tongue image segmentation.

[1]  Chunming Li,et al.  Level set evolution without re-initialization: a new variational formulation , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[2]  Liang Xu,et al.  Sublingual vein extraction algorithm based on hyperspectral tongue imaging technology , 2011, Comput. Medical Imaging Graph..

[3]  Y. Leu,et al.  Kalanchoe tubiflora extract inhibits cell proliferation by affecting the mitotic apparatus , 2012, BMC Complementary and Alternative Medicine.

[4]  Lizhong Zhang,et al.  Application of Image Segmentation Technique in Tongue Diagnosis , 2009, 2009 International Forum on Information Technology and Applications.

[5]  Du Jian-qiang,et al.  A Novel Approach of Tongue Body and Tongue Coating Separation Based on FCM , 2008, 2008 2nd International Conference on Bioinformatics and Biomedical Engineering.

[6]  Fufeng Li,et al.  C2G2FSnake: automatic tongue image segmentation utilizing prior knowledge , 2013, Science China Information Sciences.

[7]  Yang Cai,et al.  A novel imaging system for tongue inspection , 2002, IMTC/2002. Proceedings of the 19th IEEE Instrumentation and Measurement Technology Conference (IEEE Cat. No.00CH37276).

[8]  G. M.,et al.  Partial Differential Equations I , 2023, Applied Mathematical Sciences.

[9]  Yang Ben Sheng,et al.  Research and Application of Image Segmentation Algorithm Based on the Shortest Path in Medical Tongue Processing , 2009, 2009 WRI World Congress on Software Engineering.

[10]  D. Zhang,et al.  Computer Aided Tongue Diagnosis System , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[11]  Jian Sun,et al.  Salient object detection by composition , 2011, 2011 International Conference on Computer Vision.

[12]  J. Sethian,et al.  FRONTS PROPAGATING WITH CURVATURE DEPENDENT SPEED: ALGORITHMS BASED ON HAMILTON-JACOB1 FORMULATIONS , 2003 .

[13]  Guanming Lu,et al.  A Novel Computerized System for Tongue Diagnosis , 2008, 2008 International Seminar on Future Information Technology and Management Engineering.

[14]  Aiping Lu,et al.  Association between tongue appearance in Traditional Chinese Medicine and effective response in treatment of rheumatoid arthritis. , 2011, Complementary therapies in medicine.

[15]  Zhi Liu,et al.  Tongue color analysis and discrimination based on hyperspectral images , 2009, Comput. Medical Imaging Graph..

[16]  Subhasis Chaudhuri,et al.  Stabilization of Parametric Active Contours Using a Tangential Redistribution Term , 2009, IEEE Transactions on Image Processing.

[17]  Wei Li,et al.  Automatic tongue location and segmentation , 2008, 2008 International Conference on Audio, Language and Image Processing.

[18]  David Zhang,et al.  Tongue image analysis for appendicitis diagnosis , 2005, Inf. Sci..

[19]  Wenshu Li,et al.  Towards the objectification of tongue diagnosis: Automatic segmentation of tongue image , 2009, 2009 35th Annual Conference of IEEE Industrial Electronics.

[20]  Guo-Zheng Li,et al.  Inquiry diagnosis of coronary heart disease in Chinese medicine based on symptom-syndrome interactions , 2012, Chinese Medicine.

[21]  Weiming Wang,et al.  Active Contour Model based on Dynamic Extern Force and Gradient Vector Flow , 2008, 2008 International Conference on BioMedical Engineering and Informatics.

[22]  Nikos Paragios,et al.  Gradient Vector Flow Fast Geodesic Active Contours , 2001, ICCV.

[23]  Ying-Ling Chen,et al.  Automatic Tongue Diagnosis System , 2009, 2009 2nd International Conference on Biomedical Engineering and Informatics.

[24]  Christopher W. Bunt,et al.  Common tongue conditions in primary care. , 2010, American family physician.

[25]  K.H. Kim,et al.  Tongue diagnosis method for extraction of effective region and classification of tongue coating , 2008, 2008 First Workshops on Image Processing Theory, Tools and Applications.

[26]  Chuang-Chien Chiu,et al.  A novel approach based on computerized image analysis for traditional Chinese medical diagnosis of the tongue , 2000, Comput. Methods Programs Biomed..