scholarly journals Magnetic Resonance Imaging Image Segmentation and Brain Tumour Detection Using Pulse-Coupled Neural Networks

2021 ◽  
Vol 17 (1) ◽  
pp. 1-16
Author(s):  
Louiza Dehyadegari ◽  
Somayeh Khajehasani
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Image Processing ◽  
Image Segmentation ◽  
Magnetic Resonance ◽  
Brain Tumour ◽  
Detection System ◽  
Brain Mri ◽  
Resonance Imaging ◽  
Tumour Detection

Image processing can be defined as a functional structure to correct and change the images viewed and their interpretation. One of the applications of digital image processing is using image processing techniques in the component and image segmentation. One of these techniques is magnetic resonance imaging (MRI) in the medical world. In this article, a brain tumour detection system and various anomalies and abnormalities are presented where image pre-processing and preparation include image enhancement, filtering and noise reduction. Then image segmentation is done by a pulse neural network. Next, the image features are extracted and finally, the tumour and abnormal area are separated from the normal area by the algorithms. In this research, the feature selection and integration method are used and the most important statistical features of brain MRI images are used to improve brain tumour detection. Along with the studies done and the implementation of tumour detection systems, the following suggestions can be provided for future researches and the tumour detection system will work more efficiently. The pulse-coupled neural network (PCNN) can be used for image segmentation in the pre-processing stage, especially in the image filtering.

scholarly journals Classification on Magnetic Resonance Imaging (MRI) Brain Tumour using BPNN, SVM and CNN

2019 ◽  
Vol 8 (3) ◽  
pp. 8601-8607
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Image Segmentation ◽  
Magnetic Resonance ◽  
Brain Tumour ◽  
Support Vector ◽  
Low Grade ◽  
Resonance Imaging ◽  
Mri Brain ◽  
Magnetic Resonance Imaging Mri

In this works, the main objective is to detect the high grade gliomas (HGG) and low grade gliomas (LGG) from Magnetic Resonance Imaging (MRI) Brain Tumour images by applying the efficient image segmentation and classify among them. So hybrid image segmentation techniques applied in this work, first one is canny edge detection which is used to locate the boundary of the image and second is fuzzy c-mean clustering which is used to clubbed together of the similarity intensity value into clusters. Also further eight feature extracted using Intensity based Histogram and GrayLevel Co-occurrence Matrix (GLCM). Now three classifiers learning algorithm applied in this system, first one is backpropogation neural network (BPNN) which consists of multi-layer perceptrons to solve the complex problem for the given inputs. Second one is convolution neural network (CNN) are the part of neural networks which have very effective in areas such as image recognition and image classification. Third is Support vector machine (SVM) which can be used for both classification and regression challenges. Each of one is evaluated performance based on different techniques. It found that SVM and CNN gives 88% accuracy for this work.

scholarly journals Magnetic Resonance Imaging Image Segmentation Under Artificial Intelligence Neural Network for Evaluation of the Effect of Butyphthalide Combined With Edaravone on Neurological Function in Patients With Acute Cerebral Infarction

2021 ◽  
Vol 15 ◽  
Author(s):  
Bin Li ◽  
Guoping Liu
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Artificial Intelligence ◽  
Image Segmentation ◽  
Magnetic Resonance ◽  
Cerebral Infarction ◽  
Acute Cerebral Infarction ◽  
Resonance Imaging ◽  
Vascular Stenosis ◽  
Mri Image

This research was developed to investigate the effect of artificial intelligence neural network-based magnetic resonance imaging (MRI) image segmentation on the neurological function of patients with acute cerebral infarction treated with butylphthalide combined with edaravone. Eighty patients with acute cerebral infarction were selected as the research subjects, and the MRI images of patients with acute cerebral infarction were segmented by convolutional neural networks (CNN) upgraded algorithm model. MRI images of patients before and after treatment of butylphthalide combined with edaravone were compared to comprehensively evaluate the efficacy of this treatment. The results showed that compared with the traditional CNN algorithm, the running time of the CNN upgraded algorithm adopted in this study was significantly shorter, and the Loss value was lower than that of the traditional CNN model. Upgraded CNN model can realize accurate segmentation of cerebral infarction lesions in MRI images of patients. In addition, the degree of cerebral infarction and the degree of arterial stenosis were significantly improved after treatment with butylphthalide and edaravone. Compared with that before treatment, the number of patients with severe cerebral infarction or even vascular stenosis decreased significantly (P < 0.05), and gradually changed to mild vascular stenosis, and the neurological dysfunction of patients was also significantly improved. In short, MRI image segmentation based on artificial intelligence neural network can well-evaluate the efficacy and neurological impairment of butylphthalide combined with edaravone in the treatment of acute cerebral infarction, and it was worthy of promotion in clinical evaluation of the treatment effect of acute cerebral infarction.

Magnetic resonance imaging findings and its association to electroencephalogram in children with partial epilepsy (Preprint)

2020 ◽  
Author(s):  
Huynh Quang Huy
Keyword(s):  
Magnetic Resonance Imaging ◽  
Preschool Children ◽  
Magnetic Resonance ◽  
Brain Mri ◽  
Partial Epilepsy ◽  
Small Sample ◽  
Normal Brain ◽  
Resonance Imaging ◽  
Normal Children ◽  
Eeg Abnormalities

BACKGROUND It is important to identify the neuroimaging features that are associated with partial epilepsy in preschool children. Advances in technology recently to localize focal epileptogenic lesions, especially that of high-resolution structural imaging with magnetic resonance imaging (MRI). The recommendation that electroencephalography (EEG) should be gold criteria and that M.R.I should be optional has been questioned. OBJECTIVE The present study aims to to explore the brain lesions on MRI and its association to electroencephalogram in children with partial epilepsy. METHODS The present study was conducted among 112 preschool children with history of partial seizures. All patients underwent EEG and brain MRI. The epileptogenic lesions were identified on the basis of the signal intensities and morphological abnormalities seen on MRI. The correlation between MRI and EEG abnormalities was explored using a chi-square test. RESULTS Abnormal MRI were found in 34.8% (n = 39) of the sample. The EEG and MRI agreed with respect to classify into abnormal or normal in 48.2% (n = 54). Of the 27 patients with a normal EEG, six (22.2%) were seen to have an abnormal MRI. CONCLUSIONS A number of MRI abnormalities was found in our study of otherwise normal children, although the correlation between these results was not clear. Follow-up of these children will help us identify the important abnormalities. Despite of small sample, our results showed that a normal E.E.G findings does not predict a normal brain MRI in children with partial epilepsy.

scholarly journals Differential Deep Convolutional Neural Network Model for Brain Tumor Classification

2021 ◽  
Vol 11 (3) ◽  
pp. 352
Author(s):  
Isselmou Abd El Kader ◽  
Guizhi Xu ◽  
Zhang Shuai ◽  
Sani Saminu ◽  
Imran Javaid ◽  
...  
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Brain Tumor ◽  
Magnetic Resonance ◽  
Brain Tumors ◽  
Medical Image ◽  
Resonance Imaging ◽  
Feature Maps ◽  
Deep Cnn

The classification of brain tumors is a difficult task in the field of medical image analysis. Improving algorithms and machine learning technology helps radiologists to easily diagnose the tumor without surgical intervention. In recent years, deep learning techniques have made excellent progress in the field of medical image processing and analysis. However, there are many difficulties in classifying brain tumors using magnetic resonance imaging; first, the difficulty of brain structure and the intertwining of tissues in it; and secondly, the difficulty of classifying brain tumors due to the high density nature of the brain. We propose a differential deep convolutional neural network model (differential deep-CNN) to classify different types of brain tumor, including abnormal and normal magnetic resonance (MR) images. Using differential operators in the differential deep-CNN architecture, we derived the additional differential feature maps in the original CNN feature maps. The derivation process led to an improvement in the performance of the proposed approach in accordance with the results of the evaluation parameters used. The advantage of the differential deep-CNN model is an analysis of a pixel directional pattern of images using contrast calculations and its high ability to classify a large database of images with high accuracy and without technical problems. Therefore, the proposed approach gives an excellent overall performance. To test and train the performance of this model, we used a dataset consisting of 25,000 brain magnetic resonance imaging (MRI) images, which includes abnormal and normal images. The experimental results showed that the proposed model achieved an accuracy of 99.25%. This study demonstrates that the proposed differential deep-CNN model can be used to facilitate the automatic classification of brain tumors.

Yield of Brain Magnetic Resonance Imaging in Epilepsy Diagnosis from 1998 to 2020: A Large Retrospective Cohort Study

2021 ◽  
Author(s):  
Tomer Stern ◽  
Liora Kornreich ◽  
Hadassa Goldberg
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Focal Epilepsy ◽  
Brain Mri ◽  
Brain Magnetic Resonance Imaging ◽  
Infantile Spasms ◽  
Mesial Temporal Sclerosis ◽  
Resonance Imaging ◽  
Brain Abnormalities ◽  
Epilepsy Diagnosis

Abstract Background We aimed to find the clinical significance of brain abnormalities on magnetic resonance imaging (MRI) in epilepsy and the lateralization of these findings with electroencephalogram (EEG). Methods We retrospectively analyzed the results of all EEGs and brain MRIs of 600 consecutive epilepsy patients from 1998 to 2020. Results Data were available for 563 cases (267 females). Ninety percent of the patients were 18 years old or younger. A total of 345 patients (61.3%) had focal epilepsy, 180 (32%), generalized, and 38 (6.7%), inconclusive. In 187 (33.2%), the first MRI was abnormal and in 81 (out of 108 repeated MRI), the second was pathological. The most frequent brain abnormalities were cortical dysplasia in 41 (18.1%), other structural abnormalities in 25 (11%), various phacomatoses in 23 (10.1%), and mesial temporal sclerosis in 17 (7.5%). Among 226 patients with abnormal MRI, 171 (75.6%) had focal epilepsy when compared with 36 (15.9%) with generalized epilepsy (p <0.001). In 121 patients (53.5%), the result of the abnormal MRI contributed significantly to the understanding of the epilepsy etiology. The side of abnormality was lateralized to the EEG focus in 120 cases (53%); in 10/15 cases with infantile spasms (66%), MRI was significantly abnormal. In 33, in whom the first MRI was normal, a second MRI revealed a significant abnormality. Conclusion Brain MRI is an important tool in epilepsy diagnosis, mainly in focal seizures and infantile spasms. A repeat MRI is mandatory in intractable focal cases to improve the yield of this test.

U mỡ trong xương bướm: một trường hợp hiếm gặp

2021 ◽  
Author(s):  
Thu Hien Trinh Thi
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Rare Case ◽  
Imaging Techniques ◽  
Brain Mri ◽  
Brain Magnetic Resonance Imaging ◽  
Sphenoid Bone ◽  
Resonance Imaging ◽  
Large Tumor ◽  
Intraosseous Lipoma

TÓM TẮT U mỡ trong xương là khối u lành tính hiếm gặp, thường gặp ở các xương dẹt, hiếm gặp ở xương nền sọ, đặc biệt là xương bướm. Trong đa số các trường hợp, u mỡ trong xương bướm thường được phát hiện tình cờ qua chụp cắt lớp vi tinh (CLVT) hoặc cộng hưởng từ (CHT) sọ não. Đây là một khối u phát triển chậm, ít gây ra triệu chứng, một số trường hợp gây triệu chứng khi khối u to chèn ép vào cấu trúc lân cận như tuyến yên hoặc dây thần kinh thị. Trong bài này, chúng tôi báo cáo một trường hợp u mỡ trong xương bướm không triệu chứng được phát hiện tình cờ và được chẩn đoán dựa vào phim chụp cộng hưởng từ sọ não. Bệnh nhân được khuyến nghị theo dõi định kỳ bằng cộng hưởng từ mà không phải tiến hành bất kỳ phương pháp điều trị nào. Từ khóa: U mỡ, xương bướm, MRI, cộng hưởng từ sọ não, chẩn đoán hình ảnh. ABSTRACT INTRAOSSEOUS LIPOMA OF SPHENOID BONE: A RARE CASE REVIEW Intraosseous lipoma is very rare, usually benign tumor of flat bones. The incidence of an intraosseous lipomalocated basal skull bones is extremely rare, especially in sphenoid bone. Radiological imaging techniques such as magnetic resonance imaging (MRI) and computed tomography (CT) are used to detect the intraosseous lipoma by accident. These tumors are slow growing and usually asymptomatic, in some cases causing symptoms when the large tumor presses on nearby structures such as pituitary gland or the optic nerve. We present a rare case of lipomaof the sphenoid bone discovered incidentally with brain magnetic resonance imaging. The patient has been followed-up by magnetic resonance imaging without the need for surgery. Keywords: Intraosseous lipoma, sphenoid bone, MRI, brain MRI, diagnostic radiology

Sign in / Sign up

Export Citation Format

Share Document