IEEE-EMBS Conference on Biomedical Engineering and Sciences 

About: IEEE-EMBS Conference on Biomedical Engineering and Sciences is an academic conference. The conference publishes majorly in the area(s): Image segmentation & Electroencephalography. Over the lifetime, 655 publications have been published by the conference receiving 4020 citations.

Automated breast profile segmentation for ROI detection using digital mammograms

Abstract: Mammography is currently the most effective imaging modality used by radiologists for the screening of breast cancer Finding an accurate, robust and efficient breast profile segmentation technique still remains a challenging problem in digital mammography Extraction of the breast profile region and the pectoral muscle is an essential pre-processing step in the process of computer-aided detection Primarily it allows the search for abnormalities to be limited to the region of the breast tissue without undue influence from the background of the mammogram The presence of pectoral muscle in mammograms biases detection procedures, which recommends removing the pectoral muscle during mammogram pre-processing In this paper we explore an automated technique for mammogram segmentation The proposed algorithm uses morphological preprocessing and seeded region growing (SRG) algorithm in order to: (1) remove digitization noises, (2) suppress radiopaque artifacts, (3) separate background region from the breast profile region, and (4) remove the pectoral muscle, for accentuating the breast profile region To demonstrate the capability of our proposed approach, digital mammograms from two separate sources are tested using Ground Truth (GT) images for evaluation of performance characteristics Experimental results obtained indicate that the breast regions extracted accurately correspond to the respective GT images

The Soft Extra Muscle system for improving the grasping capability in neurological rehabilitation

Abstract: This paper introduces the SEM Glove (Soft Extra Muscle Glove), a comfortable aid which automatically improves the grasping capability of a human independently of the particular task being performed The technical solution partly mimics a biological solution and at the same time functions in symbiosis with the biological system The technical invention is also applicable to other parts or regions of the human body that might need supporting forces or torques A key feature is that a controlling and strengthening effect is achieved without the need for an external mechanical structure in the form of an exoskeleton The paper includes a description of the physical design, the contents and the system design

Review of Adaptive Activation Function in Deep Neural Network

Abstract: A biological inspired algorithm from human brain known as deep neural network (DNN) containing of multiple hidden layers often occurs vanishing gradient problem due to the saturation characteristic of activation function. Thus, the choice of activation function in DNN is crucial to boost up the DNN recognition performance. Unsaturated activation functions i.e. rectified linear unit is recently proposed to prevent vanishing gradient problem happened during the training process of DNN. In this paper, DNN performance is investigated with three categories of activation functions i.e. saturated, unsaturated and adaptive activation functions. The experimental results showed that the saturation problem of hyperbolic tangent activation function can be solved by adding two trainable parameters in its function. The trainable version of rectified linear unit i.e. parametric rectified linear unit (PReLU) obtained lowest misclassification rate among all types of activation function i.e. 1.6% misclassification rate on MNIST handwritten digit dataset. This is due to the adaptive activation functions allows the network to estimate a better solution by training the activation function parameters during the training process. Therefore, adaptive activation functions improves the generalization of the network to deal with the real-world application.

CNN-LSTM: Cascaded Framework For Brain Tumour Classification

Abstract: Glioma is common type of brain tumour in adults originating from glia cell. Despite advances in medical image analysis and gliomas research, accuarte diagnosis remains a challenge. Gliomas can be in general classifed into High Grade (HG) and Low Grade (LG). The exact classification of glioma helps in evaluating the disease progression and selection of the treatment strategy. Whilst medical image classification using a Convolutional Neural Networks (CNNs) has achieved remarkable success, but it is still difficult task for CNNs to accurately classify 3D medical images. One of the major limitation is the fact that CNNs are difficult to optimize in 3D volumetric classification. In current work, we addressed this challenge by introducing a cascade of CNN with Long Short Term Memory (LSTM) Network for classification of 3D brain tumor MR images into HG and LG glioma. Features from pre-trained VGG-16 were extracted and fed into LSTM network for learning high-level feature representations to classify the 3D brain tumour volumes into HG and LG glioma. The results showed that the features extracted from VGG-16 gave better classification accuracy as compared to the features extracted from AlexNet and ResNet.

Artificial neural network for classification of depressive and normal in EEG

Abstract: Depression is one of the greatest problems nowadays which might lead to high rates of other negative health outcomes such as obesity, heart disease, and stroke. However, diagnosis of the depression is still greatly depended on the questionnaires. Hence, this project is aimed to implement the Artificial Neural Network (ANN) method to outcome a software based method to determine a subject's depression condition. EEG device was used to measure the brain waves of the subjects. The raw EEG data was used on Neural Network for training through the implementation of pattern classification network where the input of the network and the outputs of the network are depressive and non-depressive categories. From the result, it is found that 10 hidden layers Scaled Conjugate Gradient algorithm (trainscg) with inputs data from electrode C3 and C4, providing the result with 95% efficiency where out of 20 tester samples, 19 were detected correctly by the algorithm.