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

Authors: Liao, Mengjia | Guo, Yi | Qin, Yajie | Wang, Yuanyuan

Article Type: Research Article

Abstract: Activities recognition using a wearable device is a very popular research field. Among all wearable sensors, the accelerometer is one of the most common sensors due to its versatility and relative ease of use. This paper proposes a novel method for activity recognition based on a single accelerometer. To process the activity information from accelerometer data, two kinds of signal features are extracted. Firstly, five features including the mean, the standard deviation, the entropy, the energy and the correlation are calculated. Then a method called empirical mode decomposition (EMD) is used for the feature extraction since accelerometer data are non-linear …and non-stationary. Several time series named intrinsic mode functions (IMFs) can be obtained after the EMD. Additional features will be added by computing the mean and standard deviation of first three IMFs. A classifier called Adaboost is adopted for the final activities recognition. In the experiments, a single sensor is separately positioned in the waist, left thigh, right ankle and right arm. Results show that the classification accuracy is 94.69%, 86.53%, 91.84% and 92.65%, respectively. These relatively high performances demonstrate that activities can be detected irrespective of the position by reducing problems such as the movement constrain and discomfort. Show more

Keywords: Activity recognition, accelerometer, empirical mode decomposition (EMD), adaboost

DOI: 10.3233/BME-151452

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1533-S1539, 2015

Authors: Cao, Peng | Liu, Xiaoli | Bao, Hang | Yang, Jinzhu | Zhao, Dazhe

Article Type: Research Article

Abstract: The false-positive reduction (FPR) is a crucial step in the computer aided detection system for the breast. The issues of imbalanced data distribution and the limitation of labeled samples complicate the classification procedure. To overcome these challenges, we propose oversampling and semi-supervised learning methods based on the restricted Boltzmann machines (RBMs) to solve the classification of imbalanced data with a few labeled samples. To evaluate the proposed method, we conducted a comprehensive performance study and compared its results with the commonly used techniques. Experiments on benchmark dataset of DDSM demonstrate the effectiveness of the RBMs based oversampling and semi-supervised learning …method in terms of geometric mean (G-mean) for false positive reduction in Breast CAD. Show more

Keywords: Breast computer aided detection, false-positive reduction, imbalanced data learning, semi-supervised learning, restricted Boltzmann machines

DOI: 10.3233/BME-151453

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1541-S1547, 2015

Authors: Yang, Jianli | Bai, Yang | Li, Guojun | Liu, Ming | Liu, Xiuling

Article Type: Research Article

Abstract: Premature ventricular contraction (PVC) is one of the most serious arrhythmias. Without early diagnosis and proper treatment, PVC can result in significant complications. In this paper, a novel feature extraction method based on a sparse auto-encoder (SAE) and softmax regression (SR) classifier was used to differentiate PVCs from other common Non-PVC rhythms, including normal sinus (N), left bundle branch block (LBBB), right bundle branch block (RBBB), atrial premature contraction (APC), and paced beat (PB) rhythms. The proposed method was analyzed using 40 ECG records obtained from the MIT-BIH Arrhythmia Database. The proposed method exhibited an overall accuracy of 99.4%, with …a PVC recognition sensitivity and positive predictability of 97.9% and 91.8%, respectively. Show more

Keywords: PVC diagnosis, sparse auto-encoder, softmax regression, feature extraction

DOI: 10.3233/BME-151454

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1549-S1558, 2015

Authors: Wei, Chang-An | Dai, Huhe

Article Type: Research Article

Abstract: P wave and T wave in human-body electrocardiogram (ECG) signals often fuse together when atrial premature contract (APC) occurs. P waves within the fused signals are valuable for the measurement of P wave parameters as well as diagnosis of supra-ventricular arrhythmias. However, the problem of extracting P wave from the fused signals is seldom addressed. In this study, a novel T wave cancellation method for P wave extraction based on maximum a posteriori (MAP) estimation is proposed. In order to accurately cancel the T wave within the fused signal, T wave and the timing point of T wave peak are …estimated simultaneously. The estimated timing point of T wave peak is used as alignment reference point for T wave subtraction. Simulation results show that the proposed method outperform the traditional T wave cancellation method in terms of both normalized mean square error and cross-correlation index. The results for real ECGs with APC demonstrate that the extracted P waves using the proposed method are more similar to the non-overlapping P waves in terms of morphology than the ones using the traditional T wave cancellation method. Show more

Keywords: Electrocardiogram, P wave extraction, atrial premature contract, maximum a posteriori

DOI: 10.3233/BME-151455

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1559-S1568, 2015

Authors: Sánchez-González, Alain | García-Zapirain, Begoña | Maestro Saiz, Iratxe | Yurrebaso Santamaría, Izaskun

Article Type: Research Article

Abstract: Periodic activity in electroencephalography (PA-EEG) is shown as comprising a series of repetitive wave patterns that may appear in different cerebral regions and are due to many different pathologies. The diagnosis based on PA-EEG is an arduous task for experts in Clinical Neurophysiology, being mainly based on other clinical features of patients. Considering this difficulty in the diagnosis it is also very complicated to establish the prognosis of patients who present PA-EEG. The goal of this paper is to propose a method capable of determining patient prognosis based on characteristics of the PA-EEG activity. The approach, based on a parallel …classification architecture and a majority vote system has proven successful by obtaining a success rate of 81.94% in the classification of patient prognosis of our database. Show more

Keywords: Medical classification, bioinformatics, feature selection, EEG periodic activity

DOI: 10.3233/BME-151456

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1569-S1578, 2015

Authors: Li, Xu | Yang, Jiali | Ding, Mingyue | Yuchi, Ming

Article Type: Research Article

Abstract: Ultrasound (US) has emerged as a non-invasive imaging modality that can provide anatomical structure information in real time. To enable the experimental analysis of new 2-D array ultrasound beamforming methods, a pre-beamformed parallel raw data acquisition system was developed for 3-D data capture of 2D array transducer. The transducer interconnection adopted the row-column addressing (RCA) scheme, where the columns and rows were active in sequential for transmit and receive events, respectively. The DAQ system captured the raw data in parallel and the digitized data were fed through the field programmable gate array (FPGA) to implement the pre-beamforming. Finally, 3-D images …were reconstructed through the devised platform in real-time. Show more

Keywords: 2-D array transducer, 3-D imaging system, row-column scheme, real-time

DOI: 10.3233/BME-151457

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1579-S1585, 2015

Authors: Choi, Hyun Ho | Lee, Ju Hwan | Kim, Sung Min | Park, Sung Yun

Article Type: Research Article

Abstract: Here, the speckle noise in ultrasonic images is removed using an image fusion-based denoising method. To optimize the denoising performance, each discrete wavelet transform (DWT) and filtering technique was analyzed and compared. In addition, the performances were compared in order to derive the optimal input conditions. To evaluate the speckle noise removal performance, an image fusion algorithm was applied to the ultrasound images, and comparatively analyzed with the original image without the algorithm. As a result, applying DWT and filtering techniques caused information loss and noise characteristics, and did not represent the most significant noise reduction performance. Conversely, an image …fusion method applying SRAD-original conditions preserved the key information in the original image, and the speckle noise was removed. Based on such characteristics, the input conditions of SRAD-original had the best denoising performance with the ultrasound images. From this study, the best denoising technique proposed based on the results was confirmed to have a high potential for clinical application. Show more

Keywords: Ultrasound imaging, speckle noise, image fusion, discrete wavelet transform, SRAD

DOI: 10.3233/BME-151458

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1587-S1597, 2015

Authors: Hwang, Yoo Na | Lee, Ju Hwan | Kim, Ga Young | Jiang, Yuan Yuan | Kim, Sung Min

Article Type: Research Article

Abstract: This paper focuses on the improvement of the diagnostic accuracy of focal liver lesions by quantifying the key features of cysts, hemangiomas, and malignant lesions on ultrasound images. The focal liver lesions were divided into 29 cysts, 37 hemangiomas, and 33 malignancies. A total of 42 hybrid textural features that composed of 5 first order statistics, 18 gray level co-occurrence matrices, 18 Law’s, and echogenicity were extracted. A total of 29 key features that were selected by principal component analysis were used as a set of inputs for a feed-forward neural network. For each lesion, the performance of the diagnosis …was evaluated by using the positive predictive value, negative predictive value, sensitivity, specificity, and accuracy. The results of the experiment indicate that the proposed method exhibits great performance, a high diagnosis accuracy of over 96% among all focal liver lesion groups (cyst vs. hemangioma, cyst vs. malignant, and hemangioma vs. malignant) on ultrasound images. The accuracy was slightly increased when echogenicity was included in the optimal feature set. These results indicate that it is possible for the proposed method to be applied clinically. Show more

Keywords: Ultrasound, focal liver lesions, classification, artificial neural network

DOI: 10.3233/BME-151459

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1599-S1611, 2015

Authors: Aliabadi, Saeid | Yu, Jinhua | Wang, Yuanyuan

Article Type: Research Article

Abstract: The contrast and resolution have trade-off in medical ultrasound imaging. Most of adaptive beamformer can enhance the imaging resolution significantly but not improve the contrast at the same time. The principal component analysis (PCA) based beamformers such as the eigenspace-based minimum variance (ESBMV) beamformer provide a good imaging resolution. Neighbors of the focal point include the common noise, interface and signal components. Echo signal of the neighbor points can be used to suppress the noise and extract the signal component of the focal point. Based on this idea, in order to improve the quality of PCA based beamformers both in …the imaging contrast and resolution, a novel beamforming method is proposed. This proposed beamformer utilizes a kernel to select neighbor points. The number of eigenvectors is estimated by using any PCA method. Then the number of selected eigenvectors for each focal point is compared with the number of selected eigenvectors of its neighbor points and is changed to a new value. The selected eigenvectors of the covariance matrix is used to construct the signal subspace. The estimated signal subspace is projected onto the minimum variance (MV) weight vector to calculate the desire weight vector. Results of experiments show that the proposed beamformer can improve the imaging contrast significantly while keeping the resolution quality similar to ESBMV beamformer. Show more

Keywords: Ultrasound imaging, beamforming, minimum variance, eigenvalue

DOI: 10.3233/BME-151460

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1613-S1621, 2015

Authors: He, Xiaonian | Liu, Weixiang | Chen, Siping | Qin, Zhengdi

Article Type: Research Article

Abstract: In the field of ultrasonic imaging technology, the problem of geometric distortion is often encountered, especially in the ultrasonic near-field. In this study, a new approach is proposed to compensate for geometric distortion in the synthetic aperture ultrasonic imaging system. This approach is based on the synthetic aperture ultrasonic holographic B-scan (UHB) imaging system, which is a combination of ultrasonic holography based on the backward propagation principle and the conventional B-scan technique. To solve the geometric distortion problem, the operation of the spatial compression and resampling in the frequency domain are introduced. The main advantage of the approach is that …the real holographic value can be calculated without distortion by using the spatial interpolation function after the spatial frequency compression. After the compensation for geometric distortion is performed, the synthetic aperture technique based on the backward propagation principle is then applied in the process of the two-dimensional numerical imaging reconstruction. Both the simulation and measurement experiment show that the approach is promising. The geometric distortion that is dependent on the wave front angle can be effectively compensated. The spatial resolution is practically uniform throughout the depth range and close to the theoretical limit in the experiments. Show more

Keywords: Synthetic aperture ultrasonic imaging, geometric distortion, spatial compression, re-sampling, numerical imaging reconstruction

DOI: 10.3233/BME-151461

Citation: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1623-S1632, 2015