Biomedical Image Processing / Medical Image Processing
Dorsa Jafarkhah Seighalani; Mehran Yazdi; Mohammad Faghihi
Volume 14, Issue 4 , February 2021, , Pages 267-276
Abstract
Cancer is one of the most common diseases at the present time. Among different types of this disease, brain cancer has a high fatality rate and accurate and timely diagnosis of it, can have a major impact on the patient’s life. Doctors need MRI and CT scan of brain to diagnose this condition. A ...
Read More
Cancer is one of the most common diseases at the present time. Among different types of this disease, brain cancer has a high fatality rate and accurate and timely diagnosis of it, can have a major impact on the patient’s life. Doctors need MRI and CT scan of brain to diagnose this condition. A precise image processing technique can help the medical specialists and speed up the diagnosis process. Many methods have been proposed to recognize brain tumors in medical images; however their accuracies were not acceptable. In fact, low accuracy is a result of the similarities between brain and tumor tissue. In this paper we propose a tumor recognition method using fusion of MRI and CT Scan images. This method exploits a deep learning based feature extraction algorithm that helps to distinguish tumors from brain tissue. Tumor recognition and accuracy calculation is performed for three common types of brain tumors (glioma, meningioma, and pituitary tumor). Our results show a great improvement of performance in comparison to related works.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Reza Soleimani; Seyed Mpjtaba Rouhani
Volume 5, Issue 2 , June 2011, , Pages 89-103
Abstract
in this paper, a novel and effective algorithm for classification of important heart arrhythmia is presented. The proposed algorithm uses heart rate variation (HRV) signal which has better chaotic characteristics. In addition to commonly used linear time domain and frequency domain features, nonlinear ...
Read More
in this paper, a novel and effective algorithm for classification of important heart arrhythmia is presented. The proposed algorithm uses heart rate variation (HRV) signal which has better chaotic characteristics. In addition to commonly used linear time domain and frequency domain features, nonlinear (chaotic) features are examined, too. To increase classification accuracy and facilitate learning, two techniques are used: a) extracted features are reduced by generalized discriminant analysis (GDA) and b) by a self organizing map (SOM), the most informant data are selected. Chaotic features help to improve diagnosis accuracy from 92% up to 97%. The results indicate the importance of GDA and SOM in efficiency of proposed algorithm. MLP, SVM and PNN classifiers are examined and compared. The proposed algorithm was able to diagnose 7 arrhythmias PVC, AFL, AF, CHB, LBBB, VF, VT and normal sinus rhythm (NSR) with 97.4% accuracy.
Neuro-Muscular Engineering
Rahele Shafaei; Seyed Mohammad Reza Hashemi Golpayegani
Volume 5, Issue 3 , June 2011, , Pages 214-228
Abstract
One of main the issues in achieving to a successful FES control is using an as much as possible accurate model of the under electrical stimulation system so that it can adequately indicate the system behavior. Classical computational models that are commonly used for this purpose have a reductionism ...
Read More
One of main the issues in achieving to a successful FES control is using an as much as possible accurate model of the under electrical stimulation system so that it can adequately indicate the system behavior. Classical computational models that are commonly used for this purpose have a reductionism nature; so they cannot consider the interaction existed in biological systems. Considering these restrictions, recently behavioral black box models are mostly used. These models focus on input/output dynamic, which is certainly the necessary modeling information for control design; thus the system is dealt with as a whole, which has hidden the interactions between components inside. Such a model has notbeen presented for elbow angle movement so far. Therefore in this study, we have been to present and verify a black box model of elbow joint movement in the transverse plane, forreaching movement control in people with C5/C6 SCI using dynamic neural networks, including time-delayed feedforward and recurrent networks. Extreme flexibility of time-delayed feedforward architectures was obtainedin a 2 layer structure including 5 hidden neurons and using 1.25s of history of input with performance indexes of 89.89% & 4.85% for cross correlation coefficient and normalized mean square error respectively. The best recurrent network with NARX architecture and equal history of input & output was also occurred in a 2 layer structure having 12 neurons in the hidden layer and using 0.1s of history, with performance indexes of 89.89% & 4.85% for cross correlation coefficient and normalized mean square error respectively. Comparison between best results of training using feedforward and recurrent networks, clearly illustrates both qualitative and quantitative excellency of the latter one in identification of the under-study system.
Cardiovascular Biomechanics
Vahid Abouie; Farzad Towhidkhah; Vahid Reza Nafisi; Hani Sharifian
Volume 5, Issue 4 , June 2011, , Pages 305-311
Abstract
Today, Dialysis hypotension during hemodialysis process is the most common problems for about 20 to 30 percent of dialysis patients. In order to avoid this hypotension, blood pressure should be measured during dialysis process continuously and noninvasively But it is practically impossible and few devices ...
Read More
Today, Dialysis hypotension during hemodialysis process is the most common problems for about 20 to 30 percent of dialysis patients. In order to avoid this hypotension, blood pressure should be measured during dialysis process continuously and noninvasively But it is practically impossible and few devices for noninvasive and continuous blood pressure measurement are very expensive. Considering this subject, the parameters related to blood pressure should be used to reach this goal. The blood concentrations and heart rate changes are associated with blood pressure in dialysis patients, so in this study, we determined a model by these two parameters in order to predict the blood pressure of hemodialysis patients. After measuring blood concentration, Heart rate and blood pressure from 14 dialysis patients, using neural network model, we determined a new model that can predict blood pressure in dialysis patient by using blood concentration and heart rate data with 3.8 percent error between the real pressure and the pressure that predicted by the model.
Biomedical Image Processing / Medical Image Processing
Raheleh Kafieh; Alireza Mehri Dehnavi; Saeed Sadri; Seyed Hamid Raji
Volume 2, Issue 3 , June 2008, , Pages 233-246
Abstract
Cephalometry is the scientific measurement of head dimensions to predict craniofacial growth, plan treatment and compare different cases. There have been many attempts to automate cephalometric analysis with the aim of reducing the time required to obtain an analysis, improve the accuracy of landmark ...
Read More
Cephalometry is the scientific measurement of head dimensions to predict craniofacial growth, plan treatment and compare different cases. There have been many attempts to automate cephalometric analysis with the aim of reducing the time required to obtain an analysis, improve the accuracy of landmark identification and reduce the errors due to clinician subjectivity. This paper introduces a method for automatic landmark detection on cephalograms. We introduced a combination of model-based methods and neural networks on cephalograms. For this purpose, first some feature points were extracted using a nonlinear diffusion filter and Susan Edge Detector to model the size, rotation, and translation of skull. A neural network was used to classify the images according to their geometrical specifications. Using learning vector quantization (L VQ) for every new image, the possible coordinates of landmarks were estimated. Then a modified active shape model (ASM) was applied and a local search to find the best match to the intensity profile was used and every point was moved to get the best location. Finally, a sub-image matching procedure was applied to pinpoint the exact location of each landmark. In order to evaluate the results of this method, 20 randomly selected images were used with a drop-one-out method. Each image had a dimension of about 170x200 mm, digitized in 100 dpi (4 pixel == 1mm). On average, 24% of the 16% landmarks were within 1mm of correct coordinates, 61 percent within 2 mm, and 93 percent within 5 mm. the proposed method in this study has had a distinct improvement over the other proposed methods of automatic landmark detection.
