Design and Development of 3D Brain MRI System Using Deep Neural Networks

2021 ◽  
Vol 11 (10) ◽  
pp. 2653-2659
Author(s):  
M. Vadivel ◽  
R. Ganesan
Keyword(s):  
Brain Tumor ◽  
Deep Neural Networks ◽  
Brain Mri ◽  
Research Work ◽  
Specific Region ◽  
Classification Algorithms ◽  
Normal Brain ◽  
Proposed Model ◽  
Abnormal Cells ◽  
The Brain

A Brain tumor is otherwise known as intracranial tumor. It is a formation of abnormal cells within the brain. A tumor cells grows continuously in the brain and destroys the cells in that specific region causing brain damage. The main problem in the tumor detection is that some normal brain cells tend to behave as tumor cell which leads to misclassification or unwanted brain surgery. A great challenge for the researchers is to identify the region and appropriate tumor mass. Due to this main reason, automated classifications are acquired for the early detection of brain tumor. In this research work, two standard datasets were used to test the developed classification algorithms. In this study, four different deep learning models were utilized to identify the accurate fit model to classify the brain tumor. From the results, it was observed that googlenet has achieved maximum mean classification accuracy of 98.2%, sensitivity 98.67% and specificity 96.17%. Our proposed model can be used to classify the brain tumor more accurately and effectively.

scholarly journals Brain Tumor Extraction Using Matlab

2021 ◽  
Vol 9 (VI) ◽  
pp. 4619-4625
Author(s):  
P. Chandra Sandeep
Keyword(s):  
Image Processing ◽  
Brain Tumor ◽  
Brain Mri ◽  
Continuous Growth ◽  
Infected People ◽  
Abnormal Cells ◽  
Tumor Extraction ◽  
Crucial Part ◽  
The Brain

The brain is the most crucial part of our human body which acts as central coordinating system for all the controlling and all regular functions of our body. The continuous growth of abnormal cells which creates certain mass of tissue is called as tumor. Tumor in the brain can be either formed inside the brain or gets into brain after formed at other part. But there is no clear information regarding the formation of brain tumor till date. Though the formation tumor in brain is not common or regular but the mortality rate of the infected people is very high because the brain is major part of body. So, it is very important get the treatment at the early stages of brain tumor but there is no direct procedure for detection and classification of tumor in the very first step of diagnosis. In actual medical diagnosis, mri images alone can’t be able to determine the detected tumor as either the cancerous or non-cancerous. But the tumor may be sometimes danger to life or may not be danger to life. Tumor inside the brain can be of either the benign(non- cancerous) or the malignant(cancerous). So, we need to detect the tumor from the MRI images through image processing and then to classify the detected tumor as it belongs to either the benign or malignant tumor. We are going to get the brain mri images as our dataset for our proposed method but the images we got may have the noise. So, we need to preprocess the image using the image preprocessing techniques. We are going to use several algorithms like thresholding, clustering to make the detection of tumor by using the image processing and image segmentation and after the detection of tumor we are going do feature extraction. This step involves the extraction of detected objects features using DWT. This extracted features are given as input to classifier algorithms like SVM’s and CNN after reduction of features using the PCA.

scholarly journals Detection and Classification of Brain Tumor in MRI Images Using Wavelet Transform and Convolutional Neural Network

2020 ◽  
pp. 15-26
Author(s):  
Ahmad M. Sarhan
Keyword(s):  
Brain Tumor ◽  
Wavelet Transform ◽  
Brain Tumors ◽  
Brain Mri ◽  
Discrete Wavelet ◽  
Abnormal Cells ◽  
Magnetic Resonance Imaging Mri ◽  
The Brain ◽  
Mri Image

A brain tumor is a mass of abnormal cells in the brain. Brain tumors can be benign or malignant. Conventional diagnosis of a brain tumor by the radiologist, is done by examining a set of images produced by magnetic resonance imaging (MRI). Many computer-aided detection (CAD) systems have been developed in order to help the radiologist reach his goal of correctly classifying the MRI image. Convolutional neural networks (CNNs) have been widely used in the classification of medical images. This paper presents a novel CAD technique for the classification of brain tumors in MRI images The proposed system extracts features from the brain MRI images by utilizing the strong energy compactness property exhibited by the Discrete Wavelet transform (DWT). The Wavelet features are then applied to a CNN to classify the input MRI image. Experimental results indicate that the proposed approach outperforms other commonly used methods and gives an overall accuracy of 98.5%.

A Survey on Detection and Classification of Brain Tumor Using Image Processing Techniques

2020 ◽  
pp. 967-973
Author(s):  
V. Deepika ◽  
T. Rajasenbagam
Keyword(s):  
Image Processing ◽  
Brain Tumor ◽  
Soft Tissues ◽  
Tumor Detection ◽  
Tumor Classification ◽  
Normal Brain ◽  
Image Processing Techniques ◽  
Normal Brain Function ◽  
Processing Techniques ◽  
The Brain

A brain tumor is an uncontrolled growth of abnormal brain tissue that can interfere with normal brain function. Although various methods have been developed for brain tumor classification, tumor detection and multiclass classification remain challenging due to the complex characteristics of the brain tumor. Brain tumor detection and classification are one of the most challenging and time-consuming tasks in the processing of medical images. MRI (Magnetic Resonance Imaging) is a visual imaging technique, which provides a information about the soft tissues of the human body, which helps identify the brain tumor. Proper diagnosis can prevent a patient's health to some extent. This paper presents a review of various detection and classification methods for brain tumor classification using image processing techniques.

Intracranial Tumors- Overview, Histological Types, Symptoms and Treatment Plans

2021 ◽  
Vol 11 (10) ◽  
pp. 133-144
Author(s):  
Dipak Chaulagain ◽  
Volodymyr Smolanka ◽  
Andriy Smolanka
Keyword(s):  
Brain Tumor ◽  
Brain Tumors ◽  
Marital Status ◽  
Size Variation ◽  
Intracranial Tumors ◽  
Regional Center ◽  
East And Southeast Asia ◽  
Abnormal Cells ◽  
Treatment Plans ◽  
The Brain

People, in general, are affected by a brain or intracranial tumor when abnormal cells started functioning within their brain. This paper explores mainly tumors that affect the brain. Almost every type of brain tumor might create symptoms which are based on the parts of the brain affected. In order to better understand reasons of occurrence intracranial tumors in various sections of the population, the study examined the relationship between sociodemographic variables, i.e., age, gender and marital status and the relative frequency of intracranial tumors as part of a study. Samples are collected based on the information from Uzhhorod Regional Center of Neurosurgery and Neurology in Ukraine. And factors such as age, gender and marital status has been considered to examine tumor size variation. The ratios of organ cancers in Ukrainians are evidently increasing. Besides, there has been growing trend in affected rates in both the genders of CNS cancers have been noticed in all the records. The ratio of most harmful brain tumors is comparatively in minimal ratio in East and Southeast Asia, and India. On the other hand, the highest ratio has been noted in European countries and as well United States, and Ukraine is one of those countries. The major burdens of cancer frequency in Ukraine have been noticed in the lung, breast, and prostate and brain. Of these, brain tumor rate in Ukraine had been hardly studied. The major difference in frequency in Asian and European populations implies the potential influence of genetic or environmental factors in malignant brain tumors. Continuing monitoring of tumor ratio in Ukraine is essential to comprehend how best to reduce cancer burden globally and to explain the causes of provincial variations, for example access to diagnosis methods and ecological exposures. Key words: Intracranial tumors, symptoms, tumor incidence in Ukraine, treatment plans, survival rate of cancer in Ukraine.

scholarly journals Brain Tumor Detection from MR Images using Image Process Techniques and Tools in Matlab Software

2021 ◽  
Vol 1 (4) ◽  
pp. 1-4
Author(s):  
Faisal Rehman ◽  
◽  
Syed Sheeraz Ali ◽  
Hamadullah Panhwar ◽  
Dr. Akhtar Hussain Phul ◽  
...  
Keyword(s):  
Brain Tumor ◽  
Image Quality ◽  
Research Work ◽  
Cost Effective ◽  
Image Process ◽  
Medical Sciences ◽  
Mr Images ◽  
Research Areas ◽  
Tumor Identification ◽  
The Brain

In the medical era the Brain tumor is one of the most important research areas in the field of medical sciences. Researcher are trying to find the reliable and cost effective medical equipment’s for the cancer and its type for the diagnosed, especially tumor has deferent kinds but the major two type are discussed in this research paper. Which are the benign and Pre-Malignant, this research work is proposed for these factors such as the accuracy of the MRI image for the tumor identification and actual placing were taken into consideration. In this study, an algorithm is proposed to detect the brain tumor from magnetic resonance image (MRI) data simple. As enhance the image quality for the easiness the tumor treatments and diagnosed for the patients. The proposed algorithm enhances the MR image quality and detects the Brain tumor which helps the Physician to diagnose the tumor easily. As well this algorithm automatically calculates the area of tumor, size and location of the tumor where it is present for diagnostic the Patient.

scholarly journals Classification of Tumors in Brain MRI Images With Hybrid of Global and Local DWT Features using Decision Tree

2019 ◽  
Vol 8 (12) ◽  
pp. 3072-3077
Keyword(s):  
Brain Tumor ◽  
Brain Tumors ◽  
Decision Tree ◽  
Brain Mri ◽  
Extraction Process ◽  
Discrete Wavelet ◽  
Global Features ◽  
Tumor Identification ◽  
The Brain

Automated brain tumor identification and classification is still an open problem for research in the medical image processing domain. Brain tumor is a bunch of unwanted cells that develop in the brain. This growth of a tumor takes up space within skull and affects the normal functioning of brain. Automated segmentation and detection of brain tumors are important in MRI scan analysis as it provides information about neural architecture of brain and also about abnormal tissues that are extremely necessary to identify appropriate surgical plan. Automating this process is a challenging task as tumor tissues show high diversity in appearance with different patients and also in many cases they tend to appear very similar to the normal tissues. Effective extraction of features that represent the tumor in brain image is the key for better classification. In this paper, we propose a hybrid feature extraction process. In this process, we combine the local and global features of the brain MRI using first by Discrete Wavelet Transformation and then using texture based statistical features by computing Gray Level Co-occurrence Matrix. The extracted combined features are used to construct decision tree for classification of brain tumors in to benign or malignant class.

scholarly journals Analysis on the MRI and BAEP  Results of Neonatal Brain with Different Levels of Bilirubin

2020 ◽  
Author(s):  
LU ZHONGXING ◽  
SHOULING DING ◽  
FEN WANG ◽  
Haitao Lv
Keyword(s):  
Central Nervous System ◽  
Brain Mri ◽  
Full Term ◽  
Normal Brain ◽  
Central Nervous System Damage ◽  
Severe Group ◽  
The Difference ◽  
The Brain ◽  
Abnormal Ratio ◽  
Abnormal Brain

Abstract Background：To explore whether there is abnormality of neonatal brains’ MRI and BAEP with different bilirubin levels, and to provide an objective basis for early diagnosis on the bilirubin induced subclinical damage on brains.Methods: To retrospectively analyze the clinical data of 103 neonatal patients, who had been hospitalized in Neonatology Department of Taicang First People’s Hospital from March 2013 to September 2015, to conduct routine brain MRI examination , BAEP testing and to analyze BAEP and MRI image results of the neonatal patients, who were divided into three groups based on the levels of total serum bilirubin concentration (TSB), 16 cases in mild group (TSB:0.0~229.0μmol/L), 49 cases in moderate group (TSB: 229.0~342.0μmol/L) and 38 cases in severe group (TSB≥342.0μmol/L); Results: We found as follows: A. Comparison of the bilirubin value of the different group : 1. The bilirubin value of the mild group is 171.99±33.50 μmol/L, the moderate group is293.98±32.09 μmol/L, and the severe group is 375.59±34.25 μmol /L . And the comparison of bilirubin values of the three groups of neonates (P＜0.01) indicates the difference is statistically significant (P＜0.01). 2. The bilirubin value of the pre-term group is 289.70±85.38μmol/Land the full-term group is 310.36±72.32 μmol/L, but the comparison of the bilirubin values between pre-term group and full-term group indicates that the difference is not statistically significant (P＞0.05).3. The bilirubin value of the normal brain MRI group(82) is 305.55±74.54 μmol/L and the abnormal brain MRI group is 303.56±83.04μmol/L; the comparison of bilirubin values between the two groups indicates that the difference is not statistically significant(P＞0.05). B. The weight value of the ﹤2500g group is 2.04±0.21 and the ≥2500ggroup is 3.39±0.46; the weight comparison of the two groups indicates that the difference is statistically significant (P＜0.01). C. Comparison of the abnormal MRI of the different groups: 1.The brain MRI result's abnormal ratio of the mild group is 31.25%, the moderate group is 16.33% and the severe group is 21.05%, but the comparison of brain MRI results of the three neonates groups indicates that the difference is not statistically significant (P＞0.05). 2.The brain MRI result's abnormal ratio of the pre-term is 30.77% and the full-term group is 16.88%, but the comparison of brain MRI results between prem-term group and full-term group indicates that the difference is not statistically significant (P＞0.05). 3.The brain MRI result's abnormal ratio of the ﹤2500g group is 37.50% and the ≥2500g group is 17.24%; but the comparison of brain MRI results of two neonates groups indicates that the difference is not statistically significant(P＞0.05). D. Comparison of abnormal MRI signal values of globus pallidus on T1WI in different groups: 1. The comparison of normal group signal values with that of mild group (p < 0.05), with that of moderate group and with that of severe group (p < 0.01) indicates that the difference is statistically significant; 2. The comparison of signal values between mild and moderate groups (p < 0.05) and between mild group and severe group (p < 0.01) indicates that the difference is statistically significant; 3. The comparison of signal values between moderate group and severe group indicates that the difference is statistically significant(p < 0.05). E. Comparison of BAEP testing results in groups: 1. There were 27(26.21%) cases in abnormalities of the BAEP results of all 103cases bilirubin patients. 2. There were 15(18.29%) cases in abnormalities of the BAEP result of the 82 cases normal brain MRL , 2(40%) cases in abnormalities of the BAEP result of the 5 cases abnormal MRI in mild bilirubin group, 4（50%） cases in abnormalities of the BAEP result of the 8 cases abnormal MRI in moderate bilirubin group and 6（75%）cases in abnormalities of the BAEP result of the 8 cases abnormal brain MRI in severe bilirubin group. 3. After one month review of the BAEP result, there was 0（0.00%） abnormal case in the normal MRI and the mild group; there were 1（20%） abnormal case in the moderate group and 2（25%） cases in the severe group. Conclusion: At low level of bilirubin, central nervous system damage may also occur and can be detected as abnormality by MRI and BAEP. Meanwhile, MRI and BAEP can also provide early abnormal information for the judgment of central nervous system damage of the children with NHB who have no acute bilirubin encephalopathy (ABE) clinical features, and provide clues for early treatment and early intervention.

scholarly journals Automated Brain Tumor Detection in MRI Images Using Efficient Deep Learning Methods

2019 ◽  
Vol 8 (11) ◽  
pp. 286-291
Keyword(s):  
Brain Tumor ◽  
Soft Tissues ◽  
Early Stage ◽  
Brain Mri ◽  
Tumor Detection ◽  
Computational Time ◽  
Learning Methods ◽  
Artificial Bee Colony Optimization ◽  
Skull Stripping ◽  
The Brain

Brain tumor is an unusual intensification of cells inside the skull. The brain MRI scanned images is segmented to extract brain tumor to analyze type and depth of tumor. In order to reduce the time consumption of brain tumor extraction, an automatic method for detection of brain tumor is highly recommended. Deep machine learning methods are used for automatic detection of the brain tumor in soft tissues at an early stage which involves the following stages namely: image pre-processing, clustering and optimization. This paper addresses previously adduced pre-processing (Skull stripping, Contrast stretching, clustering (k-Means, Fuzzy c-means) and optimization (Cuckoo search optimization, Artificial Bee Colony optimization) strategies for abnormal brain tumor detection from MRI brain images. Performance evaluation is done based on computational time of clustering output and optimization algorithms are analyzed in terms of sensitivity, specificity, and accuracy

scholarly journals BRAIN TUMOR SEGMENTATION BASED ON U-NET WITH IMAGE DRIVEN LEVEL SET LOSS

2021 ◽  
Vol 59 (5) ◽  
Author(s):  
Truong Van Pham ◽  
Thao Thi Tran
Keyword(s):  
Brain Tumor ◽  
Level Set ◽  
Loss Function ◽  
High Performance ◽  
Deep Neural Networks ◽  
Brain Mri ◽  
Tumor Segmentation ◽  
Dice Coefficient ◽  
Brain Tumor Segmentation ◽  
Mri Scans

This paper presents an approach for brain tumor segmentation based on deep neural networks. The paper proposes to utilize U-Net as an architecture of the approach to capture the fine and soars information from input images. Especially, to train the network, instead of using commonly used cross-entropy loss, dice loss or both, in this study, we propose to employ a new loss function including Level set loss and Dice loss function. The level set loss is inspired from Mumford-Shah functional for unsupervised task. Meanwhile, the Dice loss function measures the similarity between the predicted mask and desired mask. The proposed approach is then applied to segment brain tumor from MRI images as well as evaluated and compared with other approaches on a dataset of nearly 4000 brain MRI scans. Experiment results show that the proposed approach achieves high performance in terms of Dice coefficient and Intersection over Union (IoU) scores.

scholarly journals Design of Two-Dimensional Photonic Crystal Based Biosensors for Abnormal Tissues Analysis

2021 ◽  
Author(s):  
A Asuvaran ◽  
G Elatharasan
Keyword(s):  
Refractive Index ◽  
Photonic Crystal ◽  
Research Work ◽  
Normal Brain ◽  
Normal Tissues ◽  
Amplitude Spectra ◽  
Two Dimensional Photonic Crystal ◽  
The Brain ◽  
Different Tissues ◽  
Brain Tissues

Abstract The recognition of different classifications of brain irregular tissues is an incredible test in robot-helped Minimally Invasive Surgery (MIS) that includes connection with the tissues. In this paper, an optical sensor was designed in order to assess the Refractive Index (RI) of various brain tissues while the robotic surgery is performed. This research work is based on the 2-Dimensional (2D) Photonic Crystal (PC) bio-sensor powered by electromagnetic radiation. It reaches the range from UV to IR and is deeply intended to profoundly touch the changes in the refractive index of different tissues. Due to the fact that the refractive index of the abnormal tissues is very different from the normal tissues, the sensor can easily be distinguished the tumors, cancer-infected brain tissues, and normal brain tissues. As a result, the sensor exhibits a different range of frequency, wavelength and amplitude spectra which respond to the small changes that occur in the refractive index of the brain tissue.

Sign in / Sign up

Export Citation Format

Share Document