Bio-Medical Materials and Engineering - Volume 26, issue s1

Authors: Liu, Fei | Zhang, Xi | Jia, Yan

Article Type: Research Article

Abstract: In this paper, we propose a computer information processing algorithm that can be used for biomedical image processing and disease prediction. A biomedical image is considered a data object in a multi-dimensional space. Each dimension is a feature that can be used for disease diagnosis. We introduce a new concept of the top ( k 1 , k 2 ) outlier. It can be used to detect abnormal data objects in the multi-dimensional space. This technique focuses on uncertain space, …where each data object has several possible instances with distinct probabilities. We design an efficient sampling algorithm for the top ( k 1 , k 2 ) outlier in uncertain space. Some improvement techniques are used for acceleration. Experiments show our methods’ high accuracy and high efficiency. Show more

Keywords: Biomedical image, disease diagnosis, computer information processing, abnormal detection, outlier, uncertain

DOI: 10.3233/BME-151422

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1249-S1255, 2015

Authors: Xia, Peng | Hu, Jie | Qi, Jin | Gu, Chaochen | Peng, Yinghong

Article Type: Research Article

Abstract: Retinal prostheses have the potential to restore some level of visual function to the patients suffering from retinal degeneration. In this paper, an epiretinal approach with active stimulation devices is presented. The MEMS-based processing system consists of an external micro-camera, an information processor, an implanted electrical stimulator and a microelectrode array. The image processing strategy combining image clustering and enhancement techniques was proposed and evaluated by psychophysical experiments. The results indicated that the image processing strategy improved the visual performance compared with direct merging pixels to low resolution. The image processing methods assist epiretinal prosthesis for vision restoration.

Keywords: Retinal prosthesis, MEMS, image processing, simulated prosthetic vision

DOI: 10.3233/BME-151423

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1257-S1263, 2015

Authors: Wang, Xin | Guo, Yi | Wang, Yuanyuan

Article Type: Research Article

Abstract: Due to the inherent speckling and low contrast of ultrasonic images, the accurate and efficient location of regions of interest (ROIs) is still a challenging task for breast ultrasound (BUS) computer-aided diagnosis (CAD) systems. In this paper, a fully automatic and efficient ROI generation approach is proposed. First, a BUS image is preprocessed to improve image quality. Second, a phase of max-energy orientation (PMO) image of the preprocessed image is calculated. Otsu’s threshold selection method is then used to binarize the preprocessed image, the phase image and the composed image obtained by adding and normalizing the set of two images. …Finally, a region selection algorithm is developed to select the true tumor region from these three binary images before generating a final ROI. The method was validated on a BUS database with 168 cases (81 benign and 87 malignant); the accuracy, average precision rate and average recall rate are calculated and compared with conventional method. The results indicate that the proposed method is more accurate and efficient in locating ROIs. Show more

Keywords: breast tumor, ultrasound image, region of interest, phase in max-energy orientation, region selection

DOI: 10.3233/BME-151424

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1265-S1273, 2015

Authors: Chang, Yu-Ning | Chang, Herng-Hua

Article Type: Research Article

Abstract: Noise is one of the main sources of quality deterioration not only for visual inspection but also in computerized processing in brain magnetic resonance (MR) image analysis such as tissue classification, segmentation and registration. Accordingly, noise removal in brain MR images is important for a wide variety of subsequent processing applications. However, most existing denoising algorithms require laborious tuning of parameters that are often sensitive to specific image features and textures. Automation of these parameters through artificial intelligence techniques will be highly beneficial. In the present study, an artificial neural network associated with image texture feature analysis is proposed to …establish a predictable parameter model and automate the denoising procedure. In the proposed approach, a total of 83 image attributes were extracted based on four categories: 1) Basic image statistics. 2) Gray-level co-occurrence matrix (GLCM). 3) Gray-level run-length matrix (GLRLM) and 4) Tamura texture features. To obtain the ranking of discrimination in these texture features, a paired-samples t-test was applied to each individual image feature computed in every image. Subsequently, the sequential forward selection (SFS) method was used to select the best texture features according to the ranking of discrimination. The selected optimal features were further incorporated into a back propagation neural network to establish a predictable parameter model. A wide variety of MR images with various scenarios were adopted to evaluate the performance of the proposed framework. Experimental results indicated that this new automation system accurately predicted the bilateral filtering parameters and effectively removed the noise in a number of MR images. Comparing to the manually tuned filtering process, our approach not only produced better denoised results but also saved significant processing time. Show more

Keywords: Image feature, image texture, image denoising, neural network, MRI

DOI: 10.3233/BME-151425

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1275-S1282, 2015

Authors: Zhang, Yudong | Wang, Shuihua | Sun, Ping | Phillips, Preetha

Article Type: Research Article

Abstract: With the aim of developing an accurate pathological brain detection system, we proposed a novel automatic computer-aided diagnosis (CAD) to detect pathological brains from normal brains obtained by magnetic resonance imaging (MRI) scanning. The problem still remained a challenge for technicians and clinicians, since MR imaging generated an exceptionally large information dataset. A new two-step approach was proposed in this study. We used wavelet entropy (WE) and Hu moment invariants (HMI) for feature extraction, and the generalized eigenvalue proximal support vector machine (GEPSVM) for classification. To further enhance classification accuracy, the popular radial basis function (RBF) kernel was employed. The …10 runs of k -fold stratified cross validation result showed that the proposed “WE + HMI + GEPSVM + RBF” method was superior to existing methods w.r.t. classification accuracy. It obtained the average classification accuracies of 100%, 100%, and 99.45% over Dataset-66, Dataset-160, and Dataset-255, respectively. The proposed method is effective and can be applied to realistic use. Show more

Keywords: Wavelet entropy, Hu’s moment invariant, magnetic resonance imaging, support vector machine, computer-aided diagnosis, radial basis function

DOI: 10.3233/BME-151426

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1283-S1290, 2015

Authors: Zhang, Yaonan | Gao, Yuan | Li, Hong | Teng, Yueyang | Kang, Yan

Article Type: Research Article

Abstract: Level set method has been widely used in medical image analysis, but it has difficulties when being used in the segmentation of left ventricular (LV) boundaries on echocardiography images because the boundaries are not very distinguish, and the signal-to-noise ratio of echocardiography images is not very high. In this paper, we introduce the Active Shape Model (ASM) into the traditional level set method to enforce shape constraints. It improves the accuracy of boundary detection and makes the evolution more efficient. The experiments conducted on the real cardiac ultrasound image sequences show a positive and promising result.

Keywords: Level set method, image segmentation, active shape model

DOI: 10.3233/BME-151427

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1291-S1296, 2015

Authors: Liu, Hao | Qian, Hongbo | Zhao, Jianning

Article Type: Research Article

Abstract: 3D anatomical feature curves (AFC) on bone models reconstructed from CT/MRI images are important in some fields, such as preoperative planning, intra-operative navigation, patient-specific prosthesis design, etc . Interactive extraction of feature curves on patient-specific bone models is time-consuming, has low repeatability and accuracy. This paper presents a computer graphics method to automatically extract AFC from 3D hip bone models reconstructed from CT images. A DCSS (direct curvature scale space)-based technique is firstly used to extract anatomical feature points (AFP) in every contour, using anatomical structure information as prior knowledge so that AFP are extracted and only extracted. Then, corresponding …AFP are linked in different contours and AFC is generated. AFC obtained by our method were compared with those interactively extracted by three surgeons, which showed that our method is feasible (Dice coefficient: 0.94; Average symmetric surface distance: 3.97 mm). The method was also applied to identify anatomical landmarks, which showed that our method is superior to the curvature-based methods that fail to identify landmark regions or have too many redundant regions, which results in failures to subsequently label landmark regions using pre-defined spatial adjacency matrices. Show more

Keywords: Anatomical, feature, curve, landmark, hip

DOI: 10.3233/BME-151428

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1297-S1314, 2015

Authors: Lu, Min | Zhang, Xiaojie | Zhang, Mingyu | Chen, Hongyan | Dou, Weibei | Li, Shaowu | Dai, Jianping

Article Type: Research Article

Abstract: For quantitative analysis of glioma, multimodal Magnetic Resonance Imaging (MRI) signals are required in combination to perform a complementary analysis of morphological, metabolic, and functional changes. Most of the morphological analyses are based on T1-weighted and T2-weighted signals, called traditional MRI. But more detailed information about tumorous tissues could not be explained. An information combination scheme of Diffusion-Weighted Imaging (DWI) and Blood-Oxygen-Level Dependent (BOLD) contrast Imaging is proposed in this paper. This is a non-model segmentation scheme of brain glioma tissues in a particular perspective of combining multi-parameters of DWI and BOLD contrast functional Magnetic Resonance Imaging (fMRI). Compared with …traditional MRI, a promising advantage of our work is to provide an effective and adequate subdivision of the related pathological regions with glioma, by incorporating both knowledge of image graylevel and spatial structure. Furthermore, it is an automatic segmentation method without needs of parameter selection and model fitting for the extracted tissues. By the experiments in patients with glioma, the proposed method has achieved the average overlap ratios of 83.6% in the whole tumor region and 82.5% in the peritumoral edema region with the manual segmentation as “ground truth”. Show more

Keywords: Automatic segmentation, brain glioma, DWI, functional MRI

DOI: 10.3233/BME-151429

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1315-S1324, 2015

Authors: Xu, Mengjia | Yang, Jinzhu | Zhao, Dazhe | Zhao, Hong

Article Type: Research Article

Abstract: In this study, we develop a new algorithm based on fractional operators of variable-order in order to enhance image quality. First, three kinds of popular high-order discrete formulas are adopted to obtain the coefficients, and subsequently, a mask optimization method for selecting the fractional order adaptively is applied to construct a variable-order fractional differential mask along with the coefficients generated from the first step. We carry out experiments on OCT thoracic aorta images and some nature images with low contrast and noise, demonstrating that the high-order discrete method leads to significantly better performance in enhancing the edge information nonlinearly compared …to the standard first-order discrete method. Moreover, the optimized mask with variable-order of the fractional derivative not only can preserve the edge information of the processed images adequately, but it also effectively suppresses the noise in the smooth area. Show more

Keywords: Image enhancement, fractional differential operator, variable-order, mask optimization

DOI: 10.3233/BME-151430

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1325-S1333, 2015

Authors: Nagase, Akito | Takahashi, Masanobu | Nakano, Masayuki

Article Type: Research Article

Abstract: An automatic method for estimating the density of cell nuclei in whole slide images (WSI’s) of hepatic histological sections is presented. The method can be applied to hematoxylin-eosin (H&E) stained sections with slight histological atypism, such as early well-differentiated hepatocellular carcinoma (ewHCC). It is shown that measured nuclear density is affected by the nuclear size due to fragments of nuclei. This size-dependent problem has been solved by estimating the standard nuclear area for each image patch. The method extracts typical nuclei, which are used to automatically adjust the parameters, including the standard nuclear area. The method is robust for variations …in contrast, color, and nuclear size. 40 image patches sampled from 20 WSI’s of surgical sections were used for accuracy evaluation. The mean absolute percentage error of estimated nuclear densities was 8.2%. It was also confirmed that the distributions of nuclear density were successfully estimated and visualized for all 20 WSI’s. The computation time for a WSI of typical surgical section (754 mm2 , about 1,280,000 nuclei) was about 57 minutes on a PC. Show more

Keywords: Whole slide image, histopathology, liver, nuclear density, segmentation

DOI: 10.3233/BME-151431

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1335-S1344, 2015