KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Access type: UnknownSubject: search.filters.subject.MRI

Search Results

Now showing 1 - 5 of 5
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Deep Learning for Segmentation of Brain Tumors
    (2024-01-01)
    Tamang, Sudarshan
    ;
    Ariyametkul, Awika
    ;
    Paing, May Phu
    ;
    Bui, Toan H.
    (1) Background: Meningioma, Glioma, and Pituitary tumors are some of the three most common brain tumors that have great adverse effects on normal functionalities of the brain. These tumors are hard to detect and take a significant amount of time manually. To overcome this problem, deep learning techniques help in automating tumor detection quickly. This helps in early detection of brain tumors and patients can receive treatment before the tumor gets worse. (2) Methods: An automated segmentation model was created using UNet as a base model along variation of ResNet architecture. Magnetic resonance imaging (MRI) scans with T1-weighted contrast-enhanced images having 128 × 128 pixels in dimensions, are categorized into 3 classes- Meningioma (MEN), Glioma (GLI), and Pituitary tumor (PIT). At last, the predicted tumor by the proposed model was compared with the ground truth label of the corresponding tumor class. Dice score and IoU were used as performance metrics of the model. (3) Results: In this study, the best performing model was ResNeXt50_32x4dUNet among the 7 models used. The mean test dice score from this model was 0.835 whereas the mean validation dice score was 0. 784. Similarly, the mean IoU of the test images was 73.0% and showed an acceptable performance in the segmentation of brain tumor.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A multi-sequences MRI deep framework study applied to glioma classfication
    (2022-04-01)
    Coupet, Matthieu
    ;
    Urruty, Thierry
    ;
    Leelanupab, Teerapong
    ;
    Naudin, Mathieu
    ;
    Bourdon, Pascal
    Glioma is one of the most important central nervous system tumors, ranked 15th in the most common cancer for men and women. Magnetic Resonance Imaging (MRI) represents a common tool for medical experts to the diagnosis of glioma. A set of multi-sequences from an MRI is selected according to the severity of the pathology. Our proposed approach aims moreto create a computer-aided system that is capable of helping morethe expert diagnose the brain gliomas. moreWe propose a supervised learning regime based on a convolutional neural network based framework and transfer learning techniques. Our research morefocuses on the performance of different pre-trained deep learning models with respect to different MRI sequences. We highlight the best combinations of such model-MRI sequence couple for our specific task of classifying healthy brain against brain with glioma. moreWe also propose to visually analyze the extracted deep features for studying the existing relation of the MRI sequences and models. This interpretability analysis gives some hints for medical expert to understand the diagnosis made by the models. Our study is based on the well-known BraTS datasets including multi-sequence images and expert diagnosis.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    An Empirical Study of Deep Neural Networks for Glioma Detection from MRI Sequences
    (2020-01-01)
    Coupet, Matthieu
    ;
    Urruty, Thierry
    ;
    Leelanupab, Teerapong
    ;
    Naudin, Mathieu
    ;
    Bourdon, Pascal
    Gliomas are the most common central nervous system tumors. They represent 1.3% of cancers and are the 15th most common cancer for men and women. For the diagnosis of such pathology, doctors commonly use Magnetic Resonance Imaging (MRI) with different sequences. In this work, we propose a global framework using convolutional neural networks to create an intelligent assistant system for neurologists to diagnose the brain gliomas. Within this framework, we study the performance of different neural networks on four MRI modalities. This work allows us to highlight the most specific MRI sequences so that the presence of gliomas in brain tissue can be classified. We also visually analyze extracted features from the different modalities and networks with an aim to improve the interpretability and analysis of the performance obtained. We apply our study on the MRI sequences that are obtained from BraTS datasets.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Segmentation of magnetic resonance images using discrete curve evolution and fuzzy clustering
    (2007-12-01)
    Supot, Sookpotharom
    ;
    Thanapong, Chaichana
    ;
    Chuchart, Pintavirooj
    ;
    Manas, Sangworasil
    The region clustering of a Magnetic Resonance Imaging (MRI) image is more complicate than a Computed Topography (CT) image because a MRI image composes of three components such as T1-weighted, T2-weighted, and Proton Density (PD) in each layer. However, the MRI images provide more detail than the CT images. Therefore, we propose a technique of the region clustering of MRI image by using Fuzzy c-means (FCM). The fuzzy c-means algorithm is an iterative operation, that is very time-consuming and makes the algorithm impractical for using in image segmentation. To cope with this problem, the discrete curve evolution (DCE) technique is applied to find the actual cluster center to refine the initial value of the fuzzy c-means algorithm, which reduces the convergence time. In experimental results, the proposed technique provides the same segmentation accuracy as the fuzzy c-means technique. Moreover, this technique takes lower computational time comparing to the previous method. © 2007 IEEE.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Medical Image Compression Using Tree-Structured Vector Quantization and Fuzzy C-Means
    (2002-01-01)
    Supot, Sookpotharom
    ;
    Yuttana, Kitjaidure
    ;
    Manas, Sangworasil
    Compression of magnetic resonance images (MRI) has proved to be more difficult than other medical imaging modalities. In an average sized hospital, many tera bytes of digital imaging data (MRI) are generated every year, almost all of which has to be kept. Compression of medical images is currently being performed by using different algorithms. In this paper, Fuzzy Clustering Method is used for the image Tree Structure Vector Quantization (TSVQ). First, MR image is used for the feature vector. Then use this feature vector to design a classification tree by Fuzzy C-Means (FCM) algorithm to split two clusters. At every nonterminal, the centroid of the feature vectors clustered in each child node is computed to be the testing vector. At every leaf, the centroid of the training image blocks corresponding to their feature vectors falling on the same terminal node is calculated to be the codevector. All codevectors in the leaves are composed of a codebook. By doing so, the algorithm can preserve the edge of image, make good image quality, and reduce the processing time while constructing Tree Structured Codebook.