Skip to main content

Über dieses Buch

This is the first book offering a systematic description of tongue image analysis and processing technologies and their typical applications in computerized tongue diagnostic (CTD) systems. It features the most current research findings in all aspects of tongue image acquisition, preprocessing, classification, and diagnostic support methodologies, from theoretical and algorithmic problems to prototype design and development of CTD systems. The book begins with a very in-depth description of CTD on a need-to-know basis which includes an overview of CTD systems and traditional Chinese medicine (TCM) in order to provide the information on the context and background of tongue image analysis. The core part then introduces algorithms as well as their implementation methods, at a know-how level, including image segmentation methods, chromatic correction, and classification of tongue images. Some clinical applications based on these methods are presented for the show-how purpose in the CTD research field. Case studies highlight different techniques that have been adopted to assist the visual inspection of appendicitis, diabetes, and other common diseases. Experimental results under different challenging clinical circumstances have demonstrated the superior performance of these techniques. In this book, the principles of tongue image analysis are illustrated with plentiful graphs, tables, and practical experiments to provide insights into some of the problems. In this way, readers can easily find a quick and systematic way through the complicated theories and they can later even extend their studies to special topics of interest. This book will be of benefit to researchers, professionals, and graduate students working in the field of computer vision, pattern recognition, clinical practice, and TCM, as well as those involved in interdisciplinary research.





Chapter 1. Introduction to Tongue Image Analysis

Tongue diagnosis is one of the most important and widely used diagnostic methods in Chinese medicine. Visual inspection of the human tongue offers a simple, immediate, inexpensive, and noninvasive solution for various clinical applications and self-diagnosis. Increasingly, powerful information technologies have made it possible to develop a computerized tongue diagnosis (CTD) system that is based on digital image processing and analysis. In this chapter, we first introduced the current state of knowledge on tongue diagnosis and CTD. Then, for the computational perspective, we provided brief surveys on the progress of tongue image analysis technologies including tongue image acquisition, preprocessing, and diagnosis classification.

David Zhang, Hongzhi Zhang, Bob Zhang

Chapter 2. Tongue Images Acquisition System Design

In order to improve the quality and consistency of tongue images acquired by current imaging devices, this research aims to develop a novel imaging system which can faithfully and precisely record human tongue information for medical analysis. A thorough demand analysis is first conducted in this chapter in order to summarize requirements for rendering all possible medical clues, i.e., color, texture, and geometric features. Then a series of system design criteria are illustrated, and following from them three hardware modules of the imaging system, including the illuminant, lighting path, and imaging camera, are optimally proposed. Moreover, one built-in software module, the color correctionColorcorrection process, is also provided to compensate for color variations caused by system components. Finally, several important performance indicators, including illumination uniformityIllumination uniformity, system reproducibility, and accuracy, were tested. Experimental results showed that captured images were of high quality and remained stable when acquisitions are repeated. The largest color differenceColordifference between the images acquired at different times was 1.6532, which is hardly distinguishable by human observation. Compared to existing devices, the proposed system could provide a much more accurate and stable solution for tongue image acquisition. Furthermore, this developed imaging system has been evaluated by doctors of Traditional Chinese MedicineTraditional Chinese Medicine (TCM) for almost 3 years and over 9000 tongue images have been collected. Analysis results based on these data also validate the effectiveness of the proposed system.

David Zhang, Hongzhi Zhang, Bob Zhang

Tongue Image Segmentation and Shape Classification


Chapter 3. Tongue Image Segmentation by Bi-elliptical Deformable Contour

Automated tongue image segmentationAutomated tongue image segmentation, in Chinese medicine, is difficult due to two special factors: (1) there are many pathological details on the surface of the tongue, which have a large influence on edge extraction, and (2) the shapes of the tongue bodies captured from various persons (with different diseases) are quite different, so it is impossible to properly describe them using a predefined deformable template. To address these problems, in this chapter we propose an original technique that is based on a combination of a bi-elliptical deformable template (BEDT)Bi-elliptical Deformable Template (BEDT) and an active contour model: the bi-elliptical deformable contour (BEDC). The BEDT captures gross shape features using the steepest decent method on its energy function in the parameter space. The BEDC is derived from the BEDT by substituting template forces for classical internal forces, and can deform to fit local details. Our algorithm features the fully automatic interpretation of tongue images and a consistent combination of global and local controls via the template force. We applied the BEDC to a large set of clinical tongue images and present experimental results.

David Zhang, Hongzhi Zhang, Bob Zhang

Chapter 4. A Snake-Based Approach to Automated Tongue Image Segmentation

Tongue diagnosis, oneAutomated tongue image segmentation of the most important diagnosis methods of Traditional Chinese MedicineTraditional Chinese Medicine (TCM), is considered a very good candidate for remote diagnosis methods because of its simplicity and noninvasiveness. Recently, considerable research interests have been given to the development of automated tongue segmentation technologies, which is difficult due to the complexity of the pathological tongue, variance of the tongue shape, and interference of the lips. In this chapter, we propose a novel automated tongue segmentation method via combining a polar edge detector and active contour model (ACM) technique. First, a polar edge detector is presented to effectively extract the edge of the tongue body. Then we design an edge filteringEdge filtering scheme to avoid the adverse interference from the nontongue boundary. After edge filtering, a local adaptive edge bi-thresholding algorithm is introduced to perform the edge binarizationBinarization. Finally, a heuristic initialization and an ACM are proposed to segment the tongue body from the image. The experimental results demonstrate that the proposed method can accurately and effectively segment the tongue body. A quantitative evaluation on 200 images indicates that the normalized mean distanceMeandistance (MD) to the closest pointDistanceto the closest point (DCP) is 0.48%, and the average true positiveTrue positive percent of our method is 97.1%.

David Zhang, Hongzhi Zhang, Bob Zhang

Chapter 5. Tongue Segmentation in Hyperspectral Images

Automatic tongue area segmentation is crucial for computer-aided tongue diagnosis, but traditional intensity-based segmentation methods that make use of monochromatic images cannot provide accurate and robust results. We propose a novel tongue segmentation method that uses hyperspectral imagesHyperspectralimage and the support vector machineSupportvector machine. This method combines spatial and spectral information to analyze the medical tongue image and can provide much better tongue segmentation results. Promising experimental results and quantitative evaluations demonstrate that our method can provide much better performance than the traditional method.

David Zhang, Hongzhi Zhang, Bob Zhang

Chapter 6. Tongue Segmentation by Gradient Vector Flow and Region Merging

This chapter presents a region merging-based automatic tongue segmentation method. First, gradient vector flowGradient vector flow (GVF) is modified as a scalar diffusion equation to diffuse the tongue image while preserving the edge structures of the tongue body. Then the diffused tongue image is segmented into many small regions by using the watershed algorithm. Third, maximal similarity-based region merging is used to extract the tongue body area under the control of the tongue marker. Finally, the snake algorithm is used to refine the region merging result by setting the extracted tongue contour as the initial curve. The proposed method was qualitatively tested on 200 images by Traditional Chinese MedicineTraditional Chinese Medicine (TCM) practitioners and quantitatively tested on 50 tongue images using the receiver operating characteristicReceiver operating characteristic (ROC) analysis. Compared with the previous active contour model-based bi-elliptical deformable contour algorithm, the proposed method greatly enhances the segmentation performance, and it can reliably extract the tongue body from different types of tongue images.

David Zhang, Hongzhi Zhang, Bob Zhang

Chapter 7. Tongue Segmentation by Fusing Region-Based and Edge-Based Approaches

A tongue diagnosis system can offer significant information for health conditions. To ensure the feasibility and reliability of tongue diagnosis, a robust and accurate tongue segmentation method is a prerequisite. However, both of the common segmentation methods (edge-based or region-based) have limitations so that satisfactory results especially for medical use are often out of reach. In this chapter, we proposed a robust tongue segmentation method by fusing region-based and edge-based approaches. Before segmentation, the ROI (region of interest)Region of interest (ROI), which was used as input for the subsequent segmentation, was extracted in a novel way. Next, we merged adjacent regions utilizing the histogram-based color similarity criterion to get a rough tongue contour. It is essentially a region-based method and hence the results are less sensitive to cracks and fissures on the surface of the tongue. Then, we adopted a fast marching method to connect four detected reliable points together to get a close curve, which is based on edge features. The contour obtained by the region-based approach was utilized to act as a mask during the fast marching process (edge-based) and the mask added limits so that the ultimate contour would be more robust. Qualitative and quantitative comparisons showed that the proposed method is superior to the other methods for the segmentation of the tongue body in terms of robustness and accuracy.

David Zhang, Hongzhi Zhang, Bob Zhang

Chapter 8. Tongue Shape Classification by Geometric Features

Traditional Chinese MedicineTraditional Chinese Medicine (TCM) diagnoses a wide range of health conditions by examining features of the tongue, including its shape. This chapter presents a classification approach for automatically recognizing and analyzing tongue shapes based on geometric features. The approach corrects tongue deflection by applying three geometric criteria and then classifies tongue shapes according to seven geometric features that are defined using various measurements of the length, area, and angle of the tongue. To establish a measurable and machine-readable relationship between expert human judgments and machine classifications of tongue shapes, we used a decision support tool, the analytic hierarchy process (AHP), to weigh the relative influences of the various length/area/angle factors used in classifying a tongue, and then applied a fuzzy fusion framework that combines seven AHP modules, one for each tongue shape, to represent the uncertainty and imprecision between these quantitative features and tongue shape classes. Experimental results show that the proposed shape correctionShapecorrection method reduced the deflection of tongue shapes and that our shape classificationShapeclassification approach, tested on 362 tongue samples, achieved an accuracy of 90.3%, making it more accurate than either KNN or LDA.

David Zhang, Hongzhi Zhang, Bob Zhang

Tongue Color Correction and Classification


Chapter 9. Color Correction Scheme for Tongue Images

Color images produced by digital cameras are usually device-dependentDevice-dependent, i.e., the generated color information (usually presented in the RGB color space) is dependent on the imaging characteristics of specific cameras. This is a serious problem in computer-aided tongue image analysis because it relies on the accurate rendering of color information. In this chapter, we propose an optimized correction scheme that corrects tongue images captured in different device-dependent color spaces to the target device-independentDevice-independent color space. The correction algorithm in this scheme is generated by comparing several popular correction algorithms, i.e., polynomial-based regression, ridge regression, support-vector regressionSupportvector regression, and neural network mapping algorithms. We tested the performance of the proposed scheme by computing the CIE L*a*b* color differenceColordifference (∆Eab*) between estimated values and the target reference values. The experimental results on the colorcheckerColorchecker show that the color difference is less than 5 (∆Eab* < 5), while the experimental results on real tongue images show that the distorted tongue images (captured in various device-dependent color spaces) become more consistent with each other. In fact, the average color difference among them is greatly reduced by more than 95%.

David Zhang, Hongzhi Zhang, Bob Zhang

Chapter 10. Tongue Colorchecker for Precise Correction

In order to improve the correction accuracy of tongue colors by use of the Munsell colorcheckerColorchecker, thisMunsell colorchecker research aims to design a new colorchecker by aid of the tongue color spaceTonguecolor space. Three essential issues leading to the development of this space-based colorchecker are investigated in this chapter. First, based on a large and comprehensive tongue database, the tongue color space is established by which all visible colors can be classified as tongue or non-tongue colors. Hence, colors of the designed tongue colorchecker are selected from tongue colors to achieve high correction performance. Second, the minimum sufficient numberMinimum Sufficient Number of colors involved in the colorchecker is attained by comparing the correction accuracy when a different number (range from 10 to 200) of colors are contained. Thereby, 24 colors are included because the obtained minimum number of colors is 20. Lastly, criteria for optimal color selection and their corresponding objective function are presented. Two color selection methods, i.e., greedy and clustering-based selection methods, are proposed to solve the objective function. Experimental results show that the clustering-based methodClustering-based method outperforms its counterpart to generate the new tongue colorchecker. Compared to the Munsell colorcheckerMunsell colorchecker, this proposed space-based colorchecker can improve the correction accuracy by 48%. Further experimental results on more correction tasks also validate its effectiveness and superiority.

David Zhang, Hongzhi Zhang, Bob Zhang

Chapter 11. Tongue Color Analysis for Medical Application

A novel tongue color analysis system for medical applications is introduced in this chapter. Using the tongue color gamutTonguecolor gamut, tongue foreground pixels are first extracted and assigned to one of 12 colors representing this gamut. The ratio of each color for the entire image is calculated and forms a tongue color feature vectorTonguecolor feature vector. Experimenting on a large dataset consisting of 143 Healthy and 902 Disease (13 groups of more than 10 samples and one miscellaneousMiscellaneous group), a given tongue sample can be classified into one of these two classes with an average accuracy of 91.99%. Further testing showed that Disease samples can be split into three clusters, and within each cluster most if not all the illnesses are distinguished from one another. In total, 11 illnesses have a classification rate greater than 70%. This demonstrates a relationship between the state of the human body and its tongue color.

David Zhang, Hongzhi Zhang, Bob Zhang

Chapter 12. Statistical Analysis of Tongue Color and Its Applications in Diagnosis

In this chapter, an in-depth analysis of the statistical distribution characteristics of human tongue color with the aim of proposing a mathematically described tongue color spaceTonguecolor space for diagnostic feature extraction is presented. Three characteristics of tongue color space, i.e., the tongue color gamutTonguecolor gamut that defines the range of colors, color centers of 12 tongue color categories, and color distribution of typical image features in the tongue color gamut were investigated in this chapter. Based on a large database, which contains over 9000 tongue images collected by a specially designed noncontact colorimetric imaging system using a digital camera, the tongue color gamut was established in the CIE chromaticity diagram by an innovatively proposed color gamut boundary descriptor using a one-class SVM algorithmOne-class SVM algorithm. Then, the centers of 12 tongue color categories were defined. Furthermore, color distributions of several typical tongue features, such as red point and petechial point, were obtained to build a relationship between the tongue color space and color distributions of various tongue features. With the obtained tongue color space, a new color feature extraction method was proposed for diagnostic classification purposes, with experimental results validating its effectiveness.

David Zhang, Hongzhi Zhang, Bob Zhang

Chapter 13. Hyperspectral Tongue Image Classification

The human tongue is an important organ of the body, which carries information of the health status. The images of the human tongue that are currently used in computerized tongue diagnosis of traditional Chinese medicine (TCM)Traditional Chinese Medicine (TCM) are all RGB color images captured with color CCD cameras. However, this conversional method impedes the accurate analysis of the tongue surface because of the influence of illumination and tongue pose. To address this problem, this chapter presents a novel approach to analyze the tongue surface information based on hyperspectral medical tongue imagesHyperspectraltongue image with support vector machinesSupportvector machine. The experimental results based on chronic CholecystitisCholecystitis patients and healthy volunteers illustrate its effectiveness.

David Zhang, Hongzhi Zhang, Bob Zhang

Tongue Image Analysis and Diagnosis


Chapter 14. Computerized Tongue Diagnosis Based on Bayesian Networks

Tongue diagnosis is an important diagnostic method in traditional Chinese medicine (TCM)Traditional Chinese Medicine (TCM). However, due to its qualitative, subjective, and experience-based nature, traditional tongue diagnosis has a very limited application in clinical medicine. Moreover, traditional tongue diagnosis is always concerned with the identification of syndromes rather than with the connection between abnormal tongue appearances and diseases. This is not well understood in Western medicine, and thus greatly obstructs its wider use. In this chapter, we present a novel computerized tongue inspection method aimed at addressing these problems. First, two kinds of quantitative features, chromatic and textural, are extracted from tongue images by using popular digital image processing techniques. Then, Bayesian networksBayesiannetwork are employed to model the relationship between these quantitative features and diseases. The effectiveness of the method is tested on a group of 455 patients affected by 13 common diseases as well as other 70 healthy volunteers, and the diagnostic results predicted by the previously trained Bayesian network classifiersBayesiannetwork classifier(BNC) are reported.

David Zhang, Hongzhi Zhang, Bob Zhang

Chapter 15. Tongue Image Analysis for Appendicitis Diagnosis

Medical diagnosis using the tongue is a unique and important diagnostic method of traditional Chinese medicine (TCM)Traditional Chinese Medicine (TCM). However, the clinical applications of tongue diagnosis have been limited due to three factors: (1) tongue diagnosis is usually based on the capacity of the eye for detailed discrimination. (2) the correctness of tongue diagnosis depends on the experience of physicians, and (3) traditional tongue diagnosis is always dedicated to the identification of syndromes rather than diseases. To address these problems, in this chapter, we present a tongue-computing model (TCoM)Tonguecomputing model (TCoM) for the diagnosis of appendicitisAppendicitis based on quantitative measurements that include chromatic and textural metrics. These metrics are computed from true color tongue images using appropriate techniques of image processing. When our approach was applied to clinical tongue images, the results of the experiments were encouraging.

David Zhang, Hongzhi Zhang, Bob Zhang

Chapter 16. Diagnosis Using Quantitative Tongue Feature Classification

This chapter focuses on relationships between diseases and the appearance of the human tongue in terms of quantitative features. The experimental samples are digital tongue images captured from three groups of candidates: one group in normal health, one suffering with appendicitisAppendicitis, and a third suffering with pancreatitisPancreatitis. For the purposes of diagnostic classification, we first extracted chromatic and textural measurements from the original tongue images. A feature selection procedure then identified the measures most relevant to the classifications, based on the three tongue image categories. The study in this chapter validates the use of tongue inspection by means of quantitative feature classification in medical diagnosis.

David Zhang, Hongzhi Zhang, Bob Zhang

Chapter 17. Detecting Diabetes Mellitus and Nonproliferative Diabetic Retinopathy Using CTD

Diabetes mellitus (DM)Diabetes mellitus and its complications leading to diabetic retinopathy (DR)Diabetic retinopathy (DR) will soon become one of the twenty-first century’s major health problems. This represents a huge financial burden to healthcare officials and governments. To combat this approaching epidemic, this chapter presents a noninvasive method to detect DM and nonproliferative diabetic retinopathy (NPDR)Nonproliferative diabetic retinopathy (NPDR), the initial stage of DR-based on three groups of features extracted from tongue images. They include color, texture, and geometry. A noninvasive capture device with image correction first captures the tongue images. A tongue color gamutTonguecolor gamut was established with 12 colors representing the tongue color featuresTonguecolor features. The texture values of eight blocks strategically located on the tongue surface, with the additional mean of all eight blocks were used to characterize the nine tongue texture featuresTonguetexture features. Finally, 13 features extracted from tongue images based on measurements, distances, areas, and their ratios represent the geometric features. Applying a combination of the 34 features, the proposed method can separate Healthy and DM-tongues as well as NPDR/DM-sans NPDR (DM samples without NP-DR) tongues using features from each of the three groups with average accuracies of 80.52 and 80.33%, respectively. This is based on a database consisting of 130 Healthy and 296 DM samples, where 29 of those in DM are NPDR.

David Zhang, Hongzhi Zhang, Bob Zhang

Book Recapitulation


Chapter 18. Book Review and Future Work

In this book, four types of tongue image analysis technologies were elaborated by including the most current research findings in all aspects of tongue image acquisition, preprocessing, classification, and diagnostic support methodologies. In this chapter, we summarized these technologies from a systemic point of view and presented our thoughts on future work in the CDT research field.

David Zhang, Hongzhi Zhang, Bob Zhang


Weitere Informationen

Premium Partner

Neuer Inhalt

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.



Best Practices für die Mitarbeiter-Partizipation in der Produktentwicklung

Unternehmen haben das Innovationspotenzial der eigenen Mitarbeiter auch außerhalb der F&E-Abteilung erkannt. Viele Initiativen zur Partizipation scheitern in der Praxis jedoch häufig. Lesen Sie hier  - basierend auf einer qualitativ-explorativen Expertenstudie - mehr über die wesentlichen Problemfelder der mitarbeiterzentrierten Produktentwicklung und profitieren Sie von konkreten Handlungsempfehlungen aus der Praxis.
Jetzt gratis downloaden!