International Journal of Computers in Healthcare (4 papers in press)
Special Issue on: "Health and Clinical Informatics in Chinese Medicine"
- Multiple Cues Region Growing Segmentation on Tongue Image
by Wang Chengjun, Zhao Changbo, Li Guozheng
Abstract: This paper presents an improved region growing algorithm for tongue image segmentation by integrating with symmetry, color and texture cues. The symmetry cue is calculated by symmetry affinity matrix and considered as symmetry constraint. The color constraint is computed by nonlinear transformation of HSV space, and the texture constraint is obtained by calculating a 12-dimensional texture features at each pixel based on Gabor filter with 6 orientations and 8 scales. After combining these constraints as the pixel aggregation criterion for region growing algorithm, we propose a multiple cues region growing algorithm. Then, the segmentation experiments on the TCM tongue images proceed by selecting three seed points interactively. Meanwhile, the symmetry axis would be determined with these three points and used to symmetry cue calculation. Finally, compared with the previous C2G2FSnake algorithm and the single cue based region growing on both qualitative and quantitative perspectives, the proposed algorithm shows the best segmentation accuracy and powerful stability, especially the tongue images with cracks and coatings.
Keywords: Symmetry Affinity Matrix; color feature; Texture feature; Region Growing; Traditional Chinese Medicine (TCM); Tongue Image Segmentation.
Special Issue on: "Health and Clinical Informatics in Chinese Medicine,"
- Semi-Supervised Learning Methods for Large Scale Healthcare Data Analysis
by Gang Zhang, Shan-xing Ou
Abstract: With the development of information technology in healthcare industry, more and more data has been generated and stored electronically. To fully exploit the information and knowledge, data mining and machine learning methods have been developed and studied. We notice that a large body of healthcare data are lack of supervised information which requires expense human efforts in labelling or scoring them so as to be analyzed in a data mining model. In this article, we address the problem of making use of unlabeled or unscored data, together with only a few supervised data, to improve the performance of analysis model for healthcare decision making. This kind of paradise is called semi-supervised learning in machine learning literatures. We focus on semi-supervised kernel learning and propose to apply the learned kernel in two algorithms, i.e. support vector machine (SVM) and kernel regularized least squares (KRLS). The evaluation results on two publicly available healthcare dataset illustrate the effectiveness of the proposed framework.
Keywords: machine learning; semi-supervised learning; healthcare data analysis; support vector machine; kernel regularized least squares
- Investigating the Effects of Climate Factors on Bacillary Dysentery Transmission in Harbin City, China
by Feng-Feng Shao, Hao Zhang, Chun-Pu Zou, Guo-Zheng Li
Abstract: Bacillary dysentery is an infectious disease and external environmental factors including climate factors play a significant role in its transmission. In this paper, climate-related risk factors is identified and prediction model is built for bacillary dysentery. The database used in this study is integrated monthly climate factors and incidence rates in Harbin city from 1986 to 1990. Three consecutive months' climate data are used to predicted one month's incidence in order to find the relevant factors for bacillary dysentery transmission. The least absolute shrinkage and selectionator operator is applied to select related climate factors. Then, the prediction model is built by using the selected climate factors. Through the results of the experiments, monthly accumulative precipitation, daily maximum precipitation, daily maximum precipitation of the past one month, monthly mean minimum temperature and monthly mean wind velocity are found to result in the highest relative risk for bacillary dysentery.
Keywords: Bacillary Dysentery; Climate Factors; Feature Selection; Prediction Model
- Research on Traditional Chinese Medicine CBR based on ontology
by Xiang Zhang, ShiXing Yan, Guozheng Li
Abstract: Doctors of Traditional Chinese Medicine (TCM) need to learn a lot of
knowledge of both Chinese and Western medicine, and have to diagnose and treat a
large number of patients within a very limited time, which imposes a severe stress on
them. Therefore, knowledge and assistant-decision-making (ADM) that help
determination of Zhengs, diseases and treatments is an urgent need in clinical treatment.
Case-Based Reasoning (CBR) based on ontology have gradually become a spotlight.
This article first reviewed the relevant theory and research of ontology and CBR. Then
the description language and constructing method of ontology are discussed. Finally,
this article makes analysis of methods and technology used in CBR based on ontology
from knowledge representation of clinical cases and similarity computation.
Keywords: Ontology; Case-based reasoning; TCM