Full Research Paper
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.
Full Research Paper
Medical Robotics / Bio-Robotics
Elaheh Kafashi; Mohammad Ali Ahmadi Pajouh; Firooz Bakhtiari Nejad
Volume 14, Issue 4 , February 2021, Pages 277-290
Abstract
Due to the high number of patients with cerebrovascular disease and stroke, which results in paralysis of organs on one side of the body, including the hand, as well as limitations in traditional rehabilitation methods, it is necessary to build devices to help these people. In this study, initially, ...
Read More
Due to the high number of patients with cerebrovascular disease and stroke, which results in paralysis of organs on one side of the body, including the hand, as well as limitations in traditional rehabilitation methods, it is necessary to build devices to help these people. In this study, initially, given the challenges involved in designing an exoskeleton, the initial design was a mechanism for using it as a continuous passive motion to rehabilitate the fingers. This mechanism is tendon-based and covers both the flexion and extension of the fingers. For this purpose, two active and passive actuators have been used in the exoskeleton, respectively, to flex and extend the fingers. The distinctive feature of this design is its lightness, low volume, adjustability for different hands, compatibility, and comfort for the patient. Also, the kinematics and dynamics relationships modeled on the Lagrange method. The exoskeleton movement simulated in interaction with the finger with MATLAB sim-mechanics software. Finally, using simulation and modeling results, the final design was performed by considering the force of 40 N along the tendon, the exoskeleton made for the index finger. Also, the results of analytical modeling and simulation compared; the error rate of modeling obtained. In the worst case, this value was 15% for the first and second finger joints and 20% for the third joint.
Full Research Paper
Biomedical Image Processing / Medical Image Processing
Gelareh Valizadeh; Farshid Babapour Mofrad; Ahmad Shalbaf
Volume 14, Issue 4 , February 2021, Pages 291-306
Abstract
Statistical Shape Modeling is widely used in many applications of cardiac images. Many efforts have been done to generate optimized Statistical Shape Models (SSMs). In this paper, we evaluated three different 3D endocardial models constructed using different alignment procedures. From 20 healthy CMR ...
Read More
Statistical Shape Modeling is widely used in many applications of cardiac images. Many efforts have been done to generate optimized Statistical Shape Models (SSMs). In this paper, we evaluated three different 3D endocardial models constructed using different alignment procedures. From 20 healthy CMR datasets, three different endocardial models are generated by varying the surface alignment methods means based on the Center of the Apex (CoA), the Center of Mass (CoM), and the Center of the Basal (CoB) of the endocardium. Then Principle Component Analysis (PCA) is applied to show the maximum variation of the SSMs. The constructed statistical models are compared by measuring the compactness, generalization ability, and specificity. Besides, the performance of each model in the 3D endocardial segmentation application using the Active Shape Model (ASM) technique is evaluated by the Hausdorff Distance (HD) criterion. The results indicate that the CoB-based model is less compact than the CoA-based model but more compact than the CoM-based model. Although for a constant number of modes the reconstruction error is approximately the same for all models, surface alignment based on CoB leads to generate a more specific model than the others. The resulted HDs show that the CoB alignment strategy produces the ASM which has the best performance in 3D endocardial segmentation among the other models. The computed results from the quantitative analysis demonstrate that varying alignment strategies affect the quality of the constructed SSM. It is obvious that the specificity and segmentation accuracy of the proposed CoB-based model outperforms the classical CoM-based approach.
Full Research Paper
Neural Network / Biological & Artificial Neural Network / BNN & ANN
Seyedeh Sadaf Razavinezhad; Amir mohammad Fallah; Seyed Abolghasem Mirroshandel
Volume 14, Issue 4 , February 2021, Pages 307-320
Abstract
Diabetes is a common disease all around the world. It is a difficult and incurable but controllable disease, so it is important to control and prevent its complications. Thus, low error and smart methods are used to predict blood glucose levels and prevent dangerous complications to control it effectively. ...
Read More
Diabetes is a common disease all around the world. It is a difficult and incurable but controllable disease, so it is important to control and prevent its complications. Thus, low error and smart methods are used to predict blood glucose levels and prevent dangerous complications to control it effectively. In this regard, different methods were investigated. In this research, two models based on deep learning technique are used which produce efficient and optimal results. These models are composed of different combinations of long short-term memory and feed forward neural networks which predict the patient's future blood glucose levels with considerable accuracy and speed. To achieve more comprehensive model, 81,200 blood glucose data was evaluated through 203 patients. In addition, 27 effective features in patients' blood glucose levels are considered in this regard. Furthermore, cross-validation method which is suitable for time series was used for more accurate evaluation. The results showed that Autoregressive Integrated Moving Average model could not predict blood glucose levels considering this amount of data and system hardware limitations, while the models based on deep learning had good performance and good speed. Furthermore, the second proposed model for the prediction horizons of 5, 10, and 15 minutes outperformed the first one with 13.8%, 16%, and 18.9%, respectively. Therefore, the second proposed model can be more reliable for predicting blood glucose. So, it can be used in smart warning systems to prevent hypoglycemia, which is a dangerous and widespread problem of type 1 diabetes.
Full Research Paper
Biological Systems Modeling
Seyede Fatemeh Ghoreishian Amiri; Mohammad Pooyan
Volume 14, Issue 4 , February 2021, Pages 321-331
Abstract
Parkinson's disease (PD) is a neurological disorder that mainly affects dopamine-producing neurons and motor system. The most obvious symptoms of PD are tremor, slow movement, stiffness and difficulty with walking. Walking in PD is slower than normal walking. In this paper, the gait in patients ...
Read More
Parkinson's disease (PD) is a neurological disorder that mainly affects dopamine-producing neurons and motor system. The most obvious symptoms of PD are tremor, slow movement, stiffness and difficulty with walking. Walking in PD is slower than normal walking. In this paper, the gait in patients with PD is modeled by a mathematical and computational method. This model includes structures which are involved in PD, such as basal ganglia, thalamus, cortex, supplementary motor area (SMA), muscle and joint-load dynamics. The output of the model is walking speed in PD. The output value is 0.83 m/s, which is in the range reported by clinical results (0.18-1.21 m/s). Some methods which increase the gait speed in PD are investigated too. These methods include deep brain stimulation, drug prescription and strengthening the muscles. The results show that each of these methods will improve the gait speed, in fact, by using these methods, the value of output increases and approaches the walking speed range in healthy individuals (1.36-1.30 m/s). Moreover, the effect of rigidity on gait speed is studied; it has been observed that the stiffness and speed of the gait are inversely related. Finally a control method is offered which improve the gait speed by increasing the magnitude response of the closed-loop system.
Full Research Paper
Computational Neuroscience
Maryam Sadeghi Talarposhti; Mohammad Ali Ahmadi-Pajouh; Frazad Towhidkhah
Volume 14, Issue 4 , February 2021, Pages 333-344
Abstract
Human being is capable of performing more than one task simultaneously. This ability has been investigated in many researches. Performing more than one task at the same time has always been a challenging topic in psychology and human perception fields. The output and the effect of two tasks have been ...
Read More
Human being is capable of performing more than one task simultaneously. This ability has been investigated in many researches. Performing more than one task at the same time has always been a challenging topic in psychology and human perception fields. The output and the effect of two tasks have been studied in previous researches for understanding the brain’s performance and also the disease origin and the symptoms. The influence of different difficulty levels has been explored via discrete-continuous motor-cognitive dual-task (DT). To this aim, a manual tracking task combined with discrete auditory stimuli to establish DT procedure. Twenty-five participants in this paradigm were asked to track the target on screen while reacting to the auditory task at the same time. Two levels of difficulty in manual tracking plus a single auditory task (ST) were considered for the experiment. The variability of output via different difficulties was investigated by analyzing factors of error rate and the response time (RT). For this analysis, a Drift Diffusion Model (DDM) method was used. In this 4-parameter model, the drift parameter is assumed to show the difficulty levels. The results show that by applying different drift rates (the average of 0.5, 0.3, and 0.2), the model is consistent with experimental output RT and the drift factor has the potential to be considered as the difficulty factor in the DT procedure.
Full Research Paper
Biofluid Mechanics / Biofluids
Milad Mahdinezhad Asiyabi; Bahman Vahidi
Volume 14, Issue 4 , February 2021, Pages 345-355
Abstract
It is possible to replace or repair damaged tissue with regenerative medicine. Most tissues in the body rely on blood vessels to supply oxygen and nutrients to individual cells. New blood vessels are essential to grow tissue longer than 100-200 mm due to limited oxygen delivery; This restriction also ...
Read More
It is possible to replace or repair damaged tissue with regenerative medicine. Most tissues in the body rely on blood vessels to supply oxygen and nutrients to individual cells. New blood vessels are essential to grow tissue longer than 100-200 mm due to limited oxygen delivery; This restriction also applies to engineered tissues. Therefore, one of the prerequisites for tissue survival and growth is the presence of vasculature. One way to overcome this limitation is to use microfluidic channels that are created by planting a layer of endothelial cells on the channel wall and applying in vitro flow. In this study, the channels were placed inside a type 1 collagen scaffold with 81% porosity, and a drainage channel was considered for the scaffold with lymphatic function. The geometry of the perfusion channel was based on Murray’s law. The effect of parameters such as drainage channel radius, perfusion channel pressure difference, scaffold hydraulic conductivity, and vascular hydraulic conductivity on transmural pressure and shear stress was investigated. The effect of the bifurcation angle on shear stress was also studied. The finite element method was used to solve the problem. In the simulation on a vessel with a diameter of 100 mm, the maximum interstitial velocity was 50E-9 m/s, the maximum interstitial pressure was 1.34E+3 Pa, and the minimum transmural pressure was 1.49E+3 Pa. The average shear stress on the vessel walls was 10 dyn/cm2. It was noted that reducing the pressure at the drainage channel outlet, the internal insulation of the scaffold from the pressure difference within the perfusion channel, reducing the vascular hydraulic conductivity, increasing the scaffold hydraulic conductivity, and increasing the radius of the drainage channel will create and maintain positive transmural pressure. The results of this study can be used in creating implantable tissue consisting of vascular network and drainage.