No Abstract No Abstract

Purpose: Magnetic Resonance Fingerprinting (MRF) is a novel framework that uses a random acquisition to acquire a unique tissue response, or fingerprint. Through a pattern-matching algorithm, every voxel-vise fingerprint is matched with a pre-calculated dictionary of simulated fingerprints to obtain MR parameters of interest. Currently, a correlation algorithm performs the MRF matching, which is time-consuming. Moreover, MRF suffers from highly undersampled k-space data, thereby reconstructed images have aliasing artifact, propagated to the estimated quantitative maps. We propose using a distance metric learning method as a matching algorithm and a Singular Value Decomposition (SVD) to compress the dictionary, intending to promote the accuracy of MRF and expedite the matching process.
Material and Methods: In this investigation, a distance metric learning method, called the Relevant Component Analysis (RCA) was used to match the fingerprints from the undersampled data with a compressed dictionary to create quantitative maps accurately and rapidly. An Inversion Recovery Fast Imaging with Steady-State (IR-FISP) MRF sequence was simulated based on an Extended Phase Graph (EPG) on a digital brain phantom. The performance of our work was compared with the original MRF paper.
Results: Effectiveness of our method was evaluated with statistical analysis. Compared with the correlation algorithm and full-sized dictionary, this method acquires tissue parameter maps with more accuracy and better computational speed.
Conclusion: Our numerical results show that learning a distance metric of the undersampled training data accompanied by a compressed dictionary improves the accuracy of the MRF matching and overcomes the computation complexity.

Purpose: This study was conducted aiming at evaluating some risk factors in patients with Chronic Kidney Disease (CKD) in Djamaa (El Oued, Algeria) region.
Materials and Methods: Our study is based on 77 voluntary individuals divided into healthy man and women reserved as a control with average age of 46.61± 2.84 years old and CKD patients with average age of 46.03± 2.95 years old; their origin covers the whole Djamaa (El Oued, Algeria) region and they were selected from the dialysis service of SAAD DEHLEB hospital Djamaa (El Oued Algeria). Risk of certain socio-clinical factors has been estimated by the determination of the value of Odd Ratio (OR).
Results: Our study reports show a strong association between clinical factors such as Diabetes, urinary problems and Arterial hyper pressure (OR= 5.135, 6.60 and 78.276; P ≤0.05) with chronic kidney disease, respectively, but in this study we show that the Renal herbal medicine and History of kidney disease are the most dangerous risk factors, (OR = 20.00, OR =25,45 ; p≤0.001), respectively, for spices and Amount of water (OR ranging from 0.232 to 0.352; P ≤0.032) are important protective factors against this disease.
Conclusion: Lifestyle is a contributing factor in CKD attainment in the region of Djamaa (El Oued, Algeria), which requires high sensitivity to modify these behaviors for limited progression of the disease in this region.

Purpose: Automated segmentation of abnormal tissues in medical images is considered as an essential part of those computer-aided detection and diagnosis systems which analyze medical images. However, automated segmentation of abnormalities is a challenging task due to the limitations of imaging technologies and complex structure of abnormalities, including low contrast between normal and abnormal tissues, shape diversity, appearance inhomogeneity, and the vague boundaries of abnormalities. Therefore, more intelligent segmentation techniques are required to tackle these challenges.
Materials and Methods: In this study, a method, which is called MMTDNN, is proposed to segment and detect medical image abnormalities. MMTDNN, as a multi-view learning machine, utilizes convolutional neural networks in a massive training strategy. Moreover, the proposed method has four phases of preprocessing, view generation, pixel-level segmentation, and post-processing. The International Symposium on Biomedical Imaging (ISBI)-2016 dataset is used for the evaluation of the proposed method.
Results: The performance of the proposed method has been evaluated on the task of skin lesion segmentation as one of the challenging applications of abnormal tissue segmentation. Both qualitative and quantitative results demonstrate outstanding performance. Meanwhile, the accuracy of 0.973, the Jaccard index of 0.876, and the Dice similarity coefficient of 0.931 have been achieved.
Conclusion: In conclusion, the experimental result demonstrates that the proposed method outperforms state-of-the-art methods of skin lesion segmentation.

Purpose: Gamma Knife is applied as a superseded tool for inaccessible lesions surgery delivering a single high dose to a well-defined target through 201 small beams. Monte Carlo simulations can be an appropriate supplementary tool to determine dosimetric parameters in small fields due to the related dosimetry hardships.
Materials and Methods: EGSnrc/BEAMnrc Monte Carlo code was implemented to model Gamma Knife 4C. Single channel geometry comprising stationary and helmet collimators was simulated. A point source was considered as a cylindrical Cobalt source based on the simplified source channel mode. All of the 201 source channels were arranged in spherical coordinate by EGSnrc/DOSXYZnrc code to calculate dose profiles. The simulated profiles at the isocentre point in a spherical head phantom 160 mm in diameter along three axes for 4, 8, 14, and 18 mm field sizes were compared to those obtained by another work using MCNP code.
Results: Based on the results, the BEAMnrc and MCNP dose profiles matched well apart from the 18 mm profiles along X and Y directions with the average gamma index of 1.36 and 1.18, respectively. BEAMnrc profiles for 14 and 18 mm field sizes along X and Y axes were entirely flat in plateau region, whereas MCNP profiles represented variations as well as round shape. Besides, considering the identical results, radioactive source can be modeled by a point source instead of cylindrical one.
Conclusion: Thus, the EGSnrc/BEAMnrc code is recommended to simulate Gamma Knife machine as it is regarded as the most accurate computer program to simulate photon and electron interactions.

Purpose: The present study aimed to assess structural asymmetry in patients with mesial Temporal Lobe Epilepsy (mTLE) in the diffusion properties of brain white matter and subcortical gray matter tracts using Diffusion Tensor Imaging (DTI) and Diffusion Kurtosis Imaging (DKI). We considered a lower order DTI measure, Fractional Anisotropy (FA), and a higher-order DKI measure, Kurtosis Anisotropy (KA), as quantitative measures of the white matter diffusion properties in facing mTLE. We also made a comparison between these two measures in terms of the sensitivity to capture microstructural changes in concordance with TLE. 
Materials and Methods: Thirty-two subjects with mTLE participated in this study. All the cases underwent multi-shell diffusion MRI acquisition. The subjects were grouped according to their epileptogenic side of the brain (19 Left-sided and 13 Right-sided TLE). Each group were analyzed separately using FSL package, then laterality analysis based on Tract-Based Spatial Statistics (TBSS) was performed on FA and KA images. After each analysis the left side of the patients’ brain was flipped and subtracted from the right side of the patients’s brain, and a voxel-wise z-score comparison was applied to find the significantly different areas.  
Results: The results showed a considerable laterality effect on the temporal lobe white matters both in FA and KA, more emphasized in patients with Right-sided mTLE.
Conclusion: It can be concluded that these two measures, even though extracted from skeletonized images, can serve as decent biomarkers of laterality in case of mTLE, when the conventional MRI fails to capture the laterality.

Functional Magnetic Resonance Imaging (fMRI) is a technique widely used to probe brain function, and has shown many research and clinical applications. Despite its popularity and strength, performing an fMRI study needs careful consideration of the design of the experiment, as well as the techniques and methodologies implemented in it, due to the high potential of these factors to alter the outputs of the study. The influences of the demographics of the participants, stimuli design, image acquisition, and data analysis methods on the fMRI results are illustrated previously. Therefore, it is of utmost significance to have an understanding of the critical considerations when designing an fMRI study. In this manuscript, by reviewing the methodology of over one hundred task-based fMRI studies, around 300 substantial tips regarding the different stages of an fMRI experiment are gathered. These could only be found scattered through the literature, and such a collection would act as a guideline for the beginners in the field of fMRI. 

Purpose: Lumbar Puncture (LP) is widely used for spinal and epidural anesthesia or Cerebrospinal fluid (CSF) sampling procedures. As this procedure is highly complicated and needs high experience to be performed correctly, it is necessary to teach this skill to the physicians. Considering the limitation of number of usage of rubber models and advantages of Virtual Reality (VR) environment for digital training of skills, we tried to investigate the capability of VR environment to train the LP procedures. 
Materials and Methods: Geometrical model of the lumbar area of L2 to L5 are extracted from fusion of MR and CT imaging modalities. Also physical model of resistance of each layers against needle insertion at lumbar area are investigated through specially designed sensorized handle for LP needle and recorded from a 41-year-old female patient. Then geometrical and physical models of lumbar area are fused together and the VR model of it, with insertion force rendering capability is extracted. Then the model is integrated with a haptic device and the complete VR environment is investigated.  
Results: In this work we introduced a robotic Lumbar Puncture Simulator (LP Sim) with force feedback which may be used for training the LP procedures. Using the LP Sim, when a trainee inserts the needle inside the lumbar area at the provided virtual reality environment, he/she may feel the insertion forces against his/her movement inside the virtual lumbar area.
Conclusion: The LP Sim is a virtual reality-enabled environment, with force feedback, that provides an appropriate framework for training this skill.