螺旋CT薄层骨算法重建技术对前颅窝骨折的诊断价值

目的:探讨螺旋CT薄层骨算法重建技术对诊断前颅窝骨折的诊断价值。方法:回顾分析47例脑外伤临床高度怀疑前颅窝骨折患者行CT常规扫描及薄层骨算法重建,并对其诊断结果进行分析、比较。结果:在对前颅窝骨折的CT诊断中,薄层骨算法重建阳性显示率为100%,与常规CT扫描的74.47%相比,2种方法比较有显著性差异。结论:CT薄层骨算法重建明显优于常规扫描,它可以明确显示前颅窝骨质损伤情况,为临床诊断提供可靠而客观的影像学资料。     

A review on current advances in machine learning based diabetes prediction

Diabetes is a metabolic disorder comprising of high glucose level in blood over a prolonged period in the body as it is not capable of using it properly. The severe complications associated with diabetes include diabetic ketoacidosis, nonketotic hypersmolar coma, cardiovascular disease, stroke, chronic renal failure, retinal damage and foot ulcers. There is a huge increase in the number of patients with diabetes globally and it is considered a major health problem worldwide. Early diagnosis of diabetes is helpful for treatment and reduces the chance of severe complications associated with it. Machine learning algorithms (such as ANN, SVM, Naive Bayes, PLS-DA and deep learning) and data mining techniques are used for detecting interesting patterns for diagnosing and treatment of disease. Current computational methods for diabetes diagnosis have some limitations and are not tested on different datasets or peoples from different countries which limits the practical use of prediction methods. This paper is an effort to summarize the majority of the literature concerned with machine learning and data mining techniques applied for the prediction of diabetes and associated challenges. This report would be helpful for better prediction of disease and improve in understanding the pattern of diabetes. Consequently, the report would be helpful for treatment and reduce risk of other complications of diabetes.     

Effective algorithm-based triage and self-care protocols: quality medicine at lower costs

The triage phase of an algorithm-based medical care system was analyzed in three military patient environments. Combat medics triaged 4,799 patients using a physician-prepared triage manual which specified levels of initial health care based on the patient's presenting complaints and a brief history. Evaluation indicated that 36% of those reporting for sick call were eligible for treatment by medically appropriate self-care protocols. Of the remaining 64%, all but 4% could receive initial evaluation by non-physician health care extenders. The study demonstrates that personnel receiving basic medical training and orientation to an algorithm-directed triage system can direct military patients to appropriate levels of health care.     

基于遗传算法的模糊综合评价法在地下水质评价中的应用

利用模糊综合评价矩阵构造适用于确定权重的判断矩阵,并用遗传算法对判断矩阵的一致性进行检验、修正和计算各指标权重的新模型。通过对乌审旗图克镇地下水监测资料进行对比分析,确定评价指标体系,并应用此模型进行实例计算。分析表明,该方法具有普遍性、可靠性和客观性,在地下水质评价中具有广泛应用价值。     

Generalization ability of fractional polynomial models

In this paper, the problem of learning the functional dependency between input and output variables from scattered data using fractional polynomial models (FPM) is investigated. The estimation error bounds are obtained by calculating the pseudo-dimension of FPM, which is shown to be equal to that of sparse polynomial models (SPM). A linear decay of the approximation error is obtained for a class of target functions which are dense in the space of continuous functions. We derive a structural risk analogous to the Schwartz Criterion and demonstrate theoretically that the model minimizing this structural risk can achieve a favorable balance between estimation and approximation errors. An empirical model selection comparison is also performed to justify the usage of this structural risk in selecting the optimal complexity index from the data. We show that the construction of FPM can be efficiently addressed by the variable projection method. Furthermore, our empirical study implies that FPM could attain better generalization performance when compared with SPM and cubic splines.     

Design of hybrid radial basis function neural networks (HRBFNNs) realized with the aid of hybridization of fuzzy clustering method (FCM) and polynomial neural networks (PNNs)

In this study, we propose Hybrid Radial Basis Function Neural Networks (HRBFNNs) realized with the aid of fuzzy clustering method (Fuzzy C-Means, FCM) and polynomial neural networks. Fuzzy clustering used to form information granulation is employed to overcome a possible curse of dimensionality, while the polynomial neural network is utilized to build local models. Furthermore, genetic algorithm (GA) is exploited here to optimize the essential design parameters of the model (including fuzzification coefficient, the number of input polynomial fuzzy neurons (PFNs), and a collection of the specific subset of input PFNs) of the network. To reduce dimensionality of the input space, principal component analysis (PCA) is considered as a sound preprocessing vehicle. The performance of the HRBFNNs is quantified through a series of experiments, in which we use several modeling benchmarks of different levels of complexity (different number of input variables and the number of available data). A comparative analysis reveals that the proposed HRBFNNs exhibit higher accuracy in comparison to the accuracy produced by some models reported previously in the literature.     

Determination of vessel cross-sectional area by thresholding in Radon space

The cross-sectional area of a blood vessel determines its resistance, and thus is a regulator of local blood flow. However, the cross-sections of penetrating vessels in the cortex can be non-circular, and dilation and constriction can change the shape of the vessels. We show that observed vessel shape changes can introduce large errors in flux calculations when using a single diameter measurement. Because of these shape changes, typical diameter measurement approaches, such as the full-width at half-maximum (FWHM) that depend on a single diameter axis will generate erroneous results, especially when calculating flux. Here, we present an automated method—thresholding in Radon space (TiRS)—for determining the cross-sectional area of a convex object, such as a penetrating vessel observed with two-photon laser scanning microscopy (2PLSM). The thresholded image is transformed back to image space and contiguous pixels are segmented. The TiRS method is analogous to taking the FWHM across multiple axes and is more robust to noise and shape changes than FWHM and thresholding methods. We demonstrate the superior precision of the TiRS method with in vivo 2PLSM measurements of vessel diameter.     

基于比率距离的自适应超声图像去噪方法

针对超声图像噪声的瑞利分布特性,使用一种新的自适应超声图像去噪方法,改进固定窗口包含边缘时无法做到沿边缘方向滤波的不足。采用可自由伸缩的自适应滤波窗口,首先针对瑞利分布的噪声引入比率距离,得到超声图像像素间的相似度距离,然后考虑像素的邻域图像块均值,解决相似度距离之间比较的问题,最后像素根据新的相似度距离进行八方向伸展,得到不规则形状的滤波窗口进行去噪。用仿真超声图像和临床超声图像进行实验,图像评价指标结果表明该算法优于经典算法,更适用于去除超声图像的斑点噪声,在去除噪声的同时能够较好地保留细节边缘。