Technology and Health Care - Volume 25, issue S1

Authors: Shen, Zhe | Wu, Chao | Ding, Bin | Yuan, Zhipeng | Zhang, Naisheng | Zhao, Meng | Zhao, Yuan

Article Type: Research Article

Abstract: Near-regular texture is a common feature for both nature scene and 3D human models. However, traditional texture synthesis has only been able to produce a single result. This study proposes a parallel, and interactive, method for the texture synthesis of irregular appearance in 3D human models. The new method includes two major procedures: (1) iterative edge extraction and processing, and (2) parallel texture synthesis, which generates a texture with higher quality. In this paper, the effectiveness of near-regular texture synthesis algorithm is demonstrated experimentally.

Keywords: Interactive method, texture synthesis, 3D human model, near-regular texture, parallel computing

DOI: 10.3233/THC-171339

Citation: Technology and Health Care, vol. 25, no. S1, pp. 357-365, 2017

Authors: Seo, Hyeon-Uk | Wei, Qun | Kwon, Seong-Geun | Sohng, Kyu-Ik

Article Type: Research Article

Abstract: BACKGROUND: Medical images stored in a hospital system are generally confidential and integrated and require strict security. However, medical information stored on digital medical imaging systems, as well as picture archiving and communication systems (PACS), are vulnerable to attack when the data are transferred over wireless or wired communication networks. OBJECTIVE: To solve this problem, a watermarking algorithm for medical images is proposed using a bit threshold map based on just noticeable distortion (JND) in the discrete cosine transform (DCT) method. METHODS: The low-frequency component comprises a considerable amount of the signal energy …for most images. As a result, it has a crucial effect on the image quality. Therefore, in this paper, the proposed algorithm embeds watermarks based on the low-frequency components of the image, such as the DC coefficient of the DCT. RESULTS: When watermarks are embedded in a low frequency area, the subjective image quality is often degraded. To compensate for the degradation of the imperceptibility of the watermarking system, which results from embedding watermarks in the low-frequency component, this research considers the human visual system. In addition, the embedding strength of the JND value is used to improve the watermarking imperceptibility. CONCLUSIONS: We applied the proposed watermarking algorithm to a variety of medical images using a computer simulation. The algorithm’s performance was verified using a variety of attacks for eliminating watermarks. The simulation results show that the proposed algorithm robustly provides protection against a variety of possible attacks. Show more

Keywords: Medical image, digital image watermarking, non-destructive testing, human visual system, just noticeable distortion, discrete cosine transform, bit threshold map

DOI: 10.3233/THC-171340

Citation: Technology and Health Care, vol. 25, no. S1, pp. 367-375, 2017

Authors: Zhan, Tianming | Feng, Piaopiao | Hong, Xunning | Lu, Zhenyu | Xiao, Liang | Zhang, Yudong

Article Type: Research Article

Abstract: BACKGROUND: An accurate assessment of tumor malignancy grade in the preoperative situation is important for clinical management. However, the manual grading of gliomas from MRIs is both a tiresome and time consuming task for radiologists. Thus, it is a priority to design an automatic and effective computer-aided diagnosis (CAD) tool to assist radiologists in grading gliomas. OBJECTIVE: To design an automatic computer-aided diagnosis for grading gliomas using multi-sequence magnetic resonance imaging. METHODS: The proposed method consists of two steps: (1) the features of high and low grade gliomas are extracted from multi-sequence magnetic …resonance images, and (2) then, a KNN classifier is trained to grade the gliomas. In the feature extraction step, the intensity, volume, and local binary patterns (LBP) of the gliomas are extracted, and PCA is used to reduce the data dimension. RESULTS: The proposed "Intensity-Volume-LBP-PCA-KNN" method is validated on the MICCAI 2015 BraTS challenge dataset, and an average grade accuracy of 87.59% is obtained. CONCLUSIONS: The proposed method is an effective method for automatically grading gliomas and can be applied to real situations. Show more

Keywords: Glioma grade, feature extraction, local binary pattern, k-nearest neighbor classifier, magnetic resonance image, computer-aided diagnosis

DOI: 10.3233/THC-171341

Citation: Technology and Health Care, vol. 25, no. S1, pp. 377-385, 2017

Authors: Gong, Feixiang | Wei, Zhiqiang | Cong, Yanping | Chi, Haokun | Yin, Bo | Sun, Mingui

Article Type: Research Article

Abstract: In this paper, a novel wireless power transfer antenna system was designed for human head implantable devices. The antenna system used the structure of three plates and four coils and operated at low frequencies to transfer power via near field. In order to verify the electromagnetic radiation safety on the human head, the electromagnetic intensity and specific absorption rate (SAR) were studied by finite-difference-time-domain (FDTD) method. A three-layer model of human head including skin, bone and brain tissues was constructed. The transmitting and receiving antenna were set outside and inside the model. The local and average SAR were simulated at …the resonance frequency of 18.67 MHz in two situations, in one scenario both transmitting and receiving coil worked, while in the other scenario only the transmitting coil worked. The results showed that the maximum of 10 g SAR average value of human thoracic were 0.142 W/kg and 0.148 W/kg, respectively, both were lower than the international safety standards for human body of the ICNIRP and FCC, which verified the safety of the human body in wireless power transmission based on magnetic coupling resonance. Show more

Keywords: SAR (specific absorption rates), magnetic resonance, FDTD, WPT (wireless power transfer), four-layer

DOI: 10.3233/THC-171342

Citation: Technology and Health Care, vol. 25, no. S1, pp. 387-397, 2017

Authors: Liu, Qi | Zhao, Xiaoguang | Hou, Zengguang | Liu, Hongguang

Article Type: Research Article

Abstract: This paper presents a pattern recognition model using multiple features and the kernel extreme learning machine (ELM), improving the accuracy of automatic epilepsy diagnosis. After simple preprocessing, temporal- and wavelet-based features are extracted from epileptic EEG signals. A combined kernel-function-based ELM approach is then proposed for feature classification. To further reduce the computation, Cholesky decomposition is introduced during the process of calculating the output weights. The experimental results show that the proposed method can achieve satisfactory accuracy with less computation time.

Keywords: Epileptic EEG, multiple features, ELM, kernel function, Cholesky decomposition

DOI: 10.3233/THC-171343

Citation: Technology and Health Care, vol. 25, no. S1, pp. 399-409, 2017

Authors: Yue, Shihong | Wang, Yaru | Wang, Jianpei | Chen, Jun

Article Type: Research Article

Abstract: BACKGROUND: Statistics on lung cancer incidences and air pollutants show a strong correlation between air pollutant concentrations and pulmonary diseases. And environmental effects on lung cancer incidences remain highly unknown and uncertain in China. OBJECTIVE: This study aims to measure the relationships between different air pollutants and lung cancer incidences in Tianjin. METHODS: One thusand five hundred patients across 27 districts in Tianjin were studied for lung cancer incidences. The patients had come into contact with various air pollutants such as PM 2.5 , PM 10 , …SO 2 , NO 2 , CO, and O 3 . These pollutants were measured daily and were published via a Geographic Information System across the 27 districts of Tianjin. The air pollutant compositions of environments the patients lived in were determined using the nearest air monitoring station to the patient. And we used rough set theory to measure the relationships between different air pollutants and lung cancer incidences. RESULTS: Different air pollutants and combinations of pollutants impacted lung cancer incidences differently across different districts, sexes, and lung cancer types in Tianjin. CONCLUSIONS: Based on data analysis and interpretation, rough set theory provided data relationships that were objective and interpretable. The method is simple, general, and efficient, and lays the foundation for further applications in other cities. Show more

Keywords: Air pollutant compositions, lung cancer incidences, geographic information system, rough set theory

DOI: 10.3233/THC-171344

Citation: Technology and Health Care, vol. 25, no. S1, pp. 411-422, 2017

Authors: Huang, Xiaoguang | Yue, Shihong | Wang, Chuanlei | Wang, Huaxiang

Article Type: Research Article

Abstract: The existing three-dimensional (3D) x-ray reconstruction methods for lung cancer tissue reconstruct the investigated objects based on a series of two-dimensional (2D) image sections and a chosen 3D reconstruction algorithm. However, because these procedures apply the same segmentation method for all 2D image sections, they may not achieve the optimal segmentation for each section. As a result, the reconstructed 3D images have limited spatial resolution. Furthermore, the existing 3D reconstruction method is time-consuming and results in a limited time resolution. This research presents an innovation of 3D reconstruction by reformulating two main components of the method. First, a validity index …for fuzzy clustering is used to obtain the optimal segmentations of any 2D x-ray image. The process is realized by automatically determining the optimal number of clusters for the image. Second, unlike the existing 3D reconstruction methods, a fast-FCM algorithm is used to speed up the 2D image segmenting process, thereby raising the time resolution of the 3D reconstruction process. With the aid of commonly used VTK software, the proposed method has been used to visualize four classes of typical lung cancer tissues: adenocarcinoma, large cell carcinoma, small cell carcinoma, and squamous cell carcinoma. Experimental results validate the effectiveness and efficiency of the proposed algorithm. Thus, the method contributes a useful tool for x-ray-based 3D image reconstruction. Show more

Keywords: X-ray computed tomography, lung cancer tissue, fuzzy image segmentation, three-dimensional (3D) reconstruction

DOI: 10.3233/THC-171345

Citation: Technology and Health Care, vol. 25, no. S1, pp. 423-434, 2017

Authors: Zhang, Bing | Hu, Hong | Ye, Aipeng | Zhang, Peng

Article Type: Research Article

Abstract: BACKGROUND: Intracranial pressure (ICP) monitoring is very important for assessing and monitoring hydrocephalus, head trauma and hypertension patients, which could lead to elevated ICP or even devastating neurological damage. The mortality rate due to these diseases could be reduced through ICP monitoring, because precautions can be taken against the brain damage. OBJECTIVE: This paper presents a surface acoustic wave (SAW) pressure sensor to realize ICP monitoring, which is capable of wireless and passive transmission with antenna attached. METHODS: In order to improve the temperature stability of the sensor, two methods were adopted. First, …the ST cut quartz was chosen as the sensor substrate due to its good temperature stability. Then, a differential temperature compensation method was proposed to reduce the effects of temperature. Two resonators were designed based on coupling of mode (COM) theory and the prototype was fabricated and verified using a system established for testing pressure and temperature. RESULTS: The experiment result shows that the sensor has a linearity of 2.63% and hysteresis of 1.77%. CONCLUSIONS: The temperature stability of the sensor has been greatly improved by using the differential compensation method, which validates the effectiveness of the proposed method. Show more

Keywords: ICP monitoring, surface acoustic wave sensor, COM theory, differential temperature compensation

DOI: 10.3233/THC-171346

Citation: Technology and Health Care, vol. 25, no. S1, pp. 435-441, 2017

Authors: Li, Yifeng | Zhang, Lihui | Zhang, Tao | Li, Baohui

Article Type: Research Article

Abstract: The purposes of this study were to utilize Brain Atlas to investigate the fluctuations in the characteristics of human EEG, with and without +Gz acceleration produced by human centrifuge, and also to examine the G load endurance of human body. The Brain Atlas of the EEG signal with and without +Gz acceleration in a static state were compared in order to reveal the correlation and differences. When compared with those in a static state, it was found that for the EEG readings of the subjects undergoing +Gz acceleration conditions, the energy and gray scale values of the low-frequency component-delta rhythm …showed significant increases, while the energy and gray scale values of the high-frequency component-beta rhythm showed significant decreases. Among these, the beta2 rhythm was determined to be significantly inhibited. These fluctuations suggested that the ischemia conditions of brain had been improved. Also, the recoveries in the energy and gray-scale values were determined to be faster, which suggested that the G load endurance of human body had been enhanced. The Brain Atlas was found to show observable changes in color. The experimental results indicated that the Brain Atlas was able to provide assistance during the exploration of the fluctuations in the characteristics of EEG, and provided a criterion to assist in the observations of the function state fluctuations of human brain with +Gz acceleration. It also assisted in the evaluations of the G load endurance of human body. Show more

Keywords: Brain Atlas, +Gz, change characteristics

DOI: 10.3233/THC-171347

Citation: Technology and Health Care, vol. 25, no. S1, pp. 443-448, 2017

Authors: Wang, Tianle | Zhu, Li | Hu, Chunhong | Gong, Shenchu | Jiang, Hongbiao | Chen, Haitao | Li, Jia

Article Type: Research Article

Abstract: BACKGROUND: The ischemia penumbra area is not easy to be detected accurately using noninvasive imaging methods. OBJECTIVE: We aim to assess the diagnostic value of susceptibility-weighted imaging (SWI) for ischemic penumbra in patients with acute ischemic stroke. METHODS: A retrospective analysis was carried out in 47 patients with ischemic stroke involving the middle cerebral artery. Mean transit time (MTT), time to peak, relative cerebral blood flow, and relative cerebral blood volume maps were created after image processing. RESULTS: No significant difference was found in the mismatch between the SWI and …diffusion-weighted imaging (SWI-DWI) or in the MTT-DWI mismatch scores (P = 0.056, Kappa = 0.864). CONCLUSIONS: SWI provides information comparable to PWI and, thus, could serve as a reliable magnetic resonance technique for assessing ischemic penumbrae. Show more

Keywords: Susceptibility-weighted imaging, perfusion-weighted imaging, ischemic penumbra

DOI: 10.3233/THC-171348

Citation: Technology and Health Care, vol. 25, no. S1, pp. 449-457, 2017

Authors: Pan, Xiaoguang | Qi, Buer | Yu, Hongfei | Wei, Haiping | Kang, Yan

Article Type: Research Article

Abstract: BACKGROUND: Mammography is currently the most effective technique for breast cancer. Lesions distribution can provide support for clinical diagnosis and epidemiological studies. OBJECTIVE: We presented a new idea to help radiologists study breast lesions distribution conveniently. We also developed an automatic tool based on this idea which could show visualization of lesions distribution in a standard mammogram. METHODS: Firstly, establishing a lesion database to study; then, extracting breast contours and match different women’s mammograms to a standard mammogram; finally, showing the lesion distribution in the standard mammogram, and providing the distribution statistics. The …crucial process of developing this tool was matching different women’s mammograms correctly. We used a hybrid breast contour extraction method combined with coherent point drift method to match different women’s mammograms. RESULTS: We tested our automatic tool by four mass datasets of 641 images. The distribution results shown by the tool were consistent with the results counted according to their reports and mammograms by manual. We also discussed the registration error that was less than 3.3 mm in average distance. CONCLUSIONS: The new idea is effective and the automatic tool can provide lesions distribution results which are consistent with radiologists simply and conveniently. Show more

Keywords: Lesions distribution, mammogram, breast contour extraction, coherent point drift, registration

DOI: 10.3233/THC-171349

Citation: Technology and Health Care, vol. 25, no. S1, pp. 459-467, 2017