scholarly journals The Effect of Labeled/Unlabeled Prior Information for Masseter Segmentation

2013 ◽  
Vol 2013 ◽  
pp. 1-12 ◽  
Author(s):  
Yousef Rezaei Tabar ◽  
Ilkay Ulusoy
Keyword(s):  
Prior Information ◽  
Automatic Segmentation ◽  
Magnetic Resonance Images ◽  
Target Tissue ◽  
Mr Images ◽  
Mr Image ◽  
Seed Point ◽  
New Approach ◽  
Segmentation Methods ◽  
The Common

Several segmentation methods are implemented and applied to segment the facial masseter tissue from magnetic resonance images. The common idea for all methods is to take advantage of prior information from different MR images belonging to different individuals in segmentation of a test MR image. Standard atlas-based segmentation methods and probabilistic segmentation methods based on Markov random field use labeled prior information. In this study, a new approach is also proposed where unlabeled prior information from a set of MR images is used to segment masseter tissue in a probabilistic framework. The proposed method uses only a seed point that indicates the target tissue and performs automatic segmentation for the selected tissue without using labeled training set. The segmentation results of all methods are validated and compared where the influences of labeled or unlabeled prior information and initialization are discussed particularly. It is shown that if appropriate modeling is done, there is no need for labeled prior information. The best accuracy is obtained by the proposed approach where unlabeled prior information is used.

scholarly journals Automated Head Tissue Modelling Based on Structural Magnetic Resonance Images for Electroencephalographic Source Reconstruction

2021 ◽  
Author(s):  
Gaia Amaranta Taberna ◽  
Jessica Samogin ◽  
Dante Mantini
Keyword(s):  
Magnetic Resonance ◽  
Brain Structures ◽  
Magnetic Resonance Images ◽  
Head Model ◽  
Source Reconstruction ◽  
Mr Images ◽  
Tissue Segmentation ◽  
Mr Image ◽  
Eeg Recordings ◽  
Tissue Modelling

AbstractIn the last years, technological advancements for the analysis of electroencephalography (EEG) recordings have permitted to investigate neural activity and connectivity in the human brain with unprecedented precision and reliability. A crucial element for accurate EEG source reconstruction is the construction of a realistic head model, incorporating information on electrode positions and head tissue distribution. In this paper, we introduce MR-TIM, a toolbox for head tissue modelling from structural magnetic resonance (MR) images. The toolbox consists of three modules: 1) image pre-processing – the raw MR image is denoised and prepared for further analyses; 2) tissue probability mapping – template tissue probability maps (TPMs) in individual space are generated from the MR image; 3) tissue segmentation – information from all the TPMs is integrated such that each voxel in the MR image is assigned to a specific tissue. MR-TIM generates highly realistic 3D masks, five of which are associated with brain structures (brain and cerebellar grey matter, brain and cerebellar white matter, and brainstem) and the remaining seven with other head tissues (cerebrospinal fluid, spongy and compact bones, eyes, muscle, fat and skin). Our validation, conducted on MR images collected in healthy volunteers and patients as well as an MR template image from an open-source repository, demonstrates that MR-TIM is more accurate than alternative approaches for whole-head tissue segmentation. We hope that MR-TIM, by yielding an increased precision in head modelling, will contribute to a more widespread use of EEG as a brain imaging technique.

scholarly journals Multicomponent MR Image Denoising

2009 ◽  
Vol 2009 ◽  
pp. 1-10 ◽  
Author(s):  
José V. Manjón ◽  
Neil A. Thacker ◽  
Juan J. Lull ◽  
Gracian Garcia-Martí ◽  
Luís Martí-Bonmatí ◽  
...  
Keyword(s):  
Random Noise ◽  
Principal Component ◽  
Magnetic Resonance Images ◽  
Image Resolution ◽  
Single Image ◽  
Mr Images ◽  
Mr Image ◽  
Automatic Feature Extraction ◽  
Improved Performance ◽  
Multicomponent Nature

Magnetic Resonance images are normally corrupted by random noise from the measurement process complicating the automatic feature extraction and analysis of clinical data. It is because of this reason that denoising methods have been traditionally applied to improve MR image quality. Many of these methods use the information of a single image without taking into consideration the intrinsic multicomponent nature of MR images. In this paper we propose a new filter to reduce random noise in multicomponent MR images by spatially averaging similar pixels using information from all available image components to perform the denoising process. The proposed algorithm also uses a local Principal Component Analysis decomposition as a postprocessing step to remove more noise by using information not only in the spatial domain but also in the intercomponent domain dealing in a higher noise reduction without significantly affecting the original image resolution. The proposed method has been compared with similar state-of-art methods over synthetic and real clinical multicomponent MR images showing an improved performance in all cases analyzed.

scholarly journals Automatic segmentation with detection of local segmentation failures in cardiac MRI

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Jörg Sander ◽  
Bob D. de Vos ◽  
Ivana Išgum
Keyword(s):  
Automatic Segmentation ◽  
Magnetic Resonance Images ◽  
Anatomical Structures ◽  
Diagnosis And Prognosis ◽  
Fold Reduction ◽  
Segmentation Methods ◽  
Complete Set ◽  
And Performance ◽  
The Impact ◽  
Manual Correction

AbstractSegmentation of cardiac anatomical structures in cardiac magnetic resonance images (CMRI) is a prerequisite for automatic diagnosis and prognosis of cardiovascular diseases. To increase robustness and performance of segmentation methods this study combines automatic segmentation and assessment of segmentation uncertainty in CMRI to detect image regions containing local segmentation failures. Three existing state-of-the-art convolutional neural networks (CNN) were trained to automatically segment cardiac anatomical structures and obtain two measures of predictive uncertainty: entropy and a measure derived by MC-dropout. Thereafter, using the uncertainties another CNN was trained to detect local segmentation failures that potentially need correction by an expert. Finally, manual correction of the detected regions was simulated in the complete set of scans of 100 patients and manually performed in a random subset of scans of 50 patients. Using publicly available CMR scans from the MICCAI 2017 ACDC challenge, the impact of CNN architecture and loss function for segmentation, and the uncertainty measure was investigated. Performance was evaluated using the Dice coefficient, 3D Hausdorff distance and clinical metrics between manual and (corrected) automatic segmentation. The experiments reveal that combining automatic segmentation with manual correction of detected segmentation failures results in improved segmentation and to 10-fold reduction of expert time compared to manual expert segmentation.

scholarly journals An Automated Framework for Brain Tumour Class Detection

2018 ◽  
Vol 7 (4) ◽  
pp. 2463
Author(s):  
B Nandan ◽  
Kunjam Nageswara Rao
Keyword(s):  
Image Processing ◽  
Human Brain ◽  
Brain Tumour ◽  
Brain Tumours ◽  
Magnetic Resonance Images ◽  
Disease Detection ◽  
Growth Stages ◽  
Mr Images ◽  
Capture Process ◽  
Segmentation Methods

With the significant growth in medical imaging techniques and the demand for better processing of medical information, the mandate of automation in disease detection is also increasing. In the modern time, the nature of the diseases has also changed. The highly mortal diseases are becoming difficult to detect due to the high involvements of medical individual and high dependency of human knowledges. The human knowledge is prone to error and often criticized for longer time delay for processing information in disease detections. Thus, the demand from the modern computing and implementation based computational algorithms are to automate the medical disease detection processes with greater accuracy. One such disease with superior mortal rate is brain tumours or cancerous growth in the brain tissues. The regular medical practice approaches have demonstrated the challenges in detection of the tumours and more so the nature of the tumours. Ill detection of the tumour type or the shape of the tumour or the size of the tumours can lead to life threats. Thus, the need for automation in detection is the most expected form of replacements in place of manual diagnosis. Another challenge is the available data formats for such disease reports. The available reports for brain tumour are only in the form of magnetic resonance images or MR Images. The MR Images can cause higher obstacles for further processing as due to the capture process of the patient data. Often, it is observed that the noise present in the MR images makes the processing vulnerable in accuracy. A number of parallel research outcomes have demonstrated significant outcomes of detection of available tumours in the human brain using segmentation methods. Nonetheless, all parallel attempts are criticized for not able to model the growth or the nature of the tumours presents in the human brain. Thus, this work proposes a novel automated framework for detection of tumour types by deploying progressive segmentation and model the growth stages based on features. The parallel outcomes have outrun on detection accuracy due to the use of standard segmentation methods, which is designed for generic image processing and bound not to match the specificity of medical image processing. Thus, this work introduces a novel segmentation method, which is progressive in nature for higher accuracy. This work also outcomes into an automated feature extraction model for brain tumours. The major contribution of the work is to determine the nature of tumour and a sustainable prediction model for tumour stages inside the human brain. The work demonstrates high accuracy for correct detection and prediction of the patient’s life threats in in real time order to take timely medication for making the precious human life more precious.  

scholarly journals A Robust Method for MR Image Segmentation and Multiple Scleroses Detection

2019 ◽  
Vol 9 (6) ◽  
pp. 1119-1130
Author(s):  
H. Zouaoui ◽  
A. Moussaoui ◽  
M. Oussalah ◽  
A. Taleb-Ahmed
Keyword(s):  
White Matter ◽  
Automatic Segmentation ◽  
Fuzzy Model ◽  
Mr Images ◽  
New Approach ◽  
Magnetic Resonance Imaging Mri ◽  
Mr Image Segmentation ◽  
The Brain

In the present article, we propose a new approach for the segmentation of the MR images of the Multiple Sclerosis (MS). The Magnetic Resonance Imaging (MRI) allows the visualization of the brain and it is widely used in the diagnosis and the follow-up of the patients suffering from MS. Aiming to automate a long and tedious process for the clinician, we propose the automatic segmentation of the MS lesions. Our algorithm of segmentation is composed of three stages: segmentation of the brain into regions using the algorithm Fuzzy Particle Swarm Optimization (FPSO) in order to obtain the characterization of the different healthy tissues (White matter, grey matter and cerebrospinal fluid (CSF)) after the extraction of white matter (WM), the elimination of the atypical data (outliers) of the white matter by the algorithm Fuzzy C-Means (FCM), finally, the use of a Mamdani-type fuzzy model to extract the MS lesions among all the absurd data.

Automatic segmentation of the temporomandibular joint disc on magnetic resonance images using a deep learning technique

2021 ◽  
pp. 20210185
Author(s):  
Michihito Nozawa ◽  
Hirokazu Ito ◽  
Yoshiko Ariji ◽  
Motoki Fukuda ◽  
Chinami Igarashi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Magnetic Resonance ◽  
Temporomandibular Joint ◽  
Test Data ◽  
Automatic Segmentation ◽  
Learning Model ◽  
Magnetic Resonance Images ◽  
Mr Images ◽  
Validity Test ◽  
Deep Learning Model

Objectives: The aims of the present study were to construct a deep learning model for automatic segmentation of the temporomandibular joint (TMJ) disc on magnetic resonance (MR) images, and to evaluate the performances using the internal and external test data. Methods: In total, 1200 MR images of closed and open mouth positions in patients with temporomandibular disorder (TMD) were collected from two hospitals (Hospitals A and B). The training and validation data comprised 1000 images from Hospital A, which were used to create a segmentation model. The performance was evaluated using 200 images from Hospital A (internal validity test) and 200 images from Hospital B (external validity test). Results: Although the analysis of performance determined with data from Hospital B showed low recall (sensitivity), compared with the performance determined with data from Hospital A, both performances were above 80%. Precision (positive predictive value) was lower when test data from Hospital A were used for the position of anterior disc displacement. According to the intra-articular TMD classification, the proportions of accurately assigned TMJs were higher when using images from Hospital A than when using images from Hospital B. Conclusion: The segmentation deep learning model created in this study may be useful for identifying disc positions on MR images.

The learning-based automatic segmentation algorithm of brain MR images based on 7T

2020 ◽  
Vol 16 ◽  
Author(s):  
Minghui Deng ◽  
Zhenhao Jin ◽  
Ran Yu ◽  
Qingshuang Zeng
Keyword(s):  
Automatic Segmentation ◽  
Ground Truth ◽  
Segmentation Algorithm ◽  
Mr Images ◽  
Tissue Segmentation ◽  
Mr Image ◽  
Image Intensity ◽  
Automated Method ◽  
Brain Mr Images ◽  
Intensity Contrast

Background: The learning-based algorithms provide an ability to automatically estimate and refine GM, WM and CSF. The ground truth manually achieved from the 3T MR image may not be accurate and reliable with poor image intensity contrast. It will seriously influence the classification performance because the supervised learning-based algorithms extremely rely on the ground truth. Recently, the 7T MR images brings about the excellent image intensity contrast, while Structured Random Forest (SRF) performs the pixel-level classification and achieves structural and contextual information in images. Materials and Methods: In this paper, a automatic segmentation algorithm is proposed based on ground truth achieved by the corresponding 7T subjects for segmenting the 3T&1.5T brain tissues using SRF classifiers. Through taking advantage of the 7T brain MR images, we can achieve the highly accuracy and reliable ground truth and then implement the training of SRF classifiers. Our proposed algorithm effectively integrates the T1-weighed images along with the probability maps to train the SRF classifiers for brain tissue segmentation. Results: Specifically, for the mean Dice ratio of all 10 subjects, the proposed method achieved 95.14%±0.9%, 90.17%±1.83%, and 81.96%± 4.32% for WM, GM, and CSF. With the experiment results, the proposed algorithm can achieve better performances than other automatic segmentation methods. Further experiments are performed on the 200 3T&1.5T brain MR images of ADNI dataset and our proposed method shows promised performances. Conclusions: The authors have developed and validated a novel fully automated method for 3T brain MR image segmentation.

scholarly journals Automated 2D Segmentation of Prostate in T2-weighted MRI Scans

2016 ◽  
Vol 12 (1) ◽  
pp. 53
Author(s):  
Justinas Jucevicius ◽  
Povilas Treigys ◽  
Jolita Bernataviciene ◽  
Ruta Briediene ◽  
Ieva Naruševiciute ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Magnetic Resonance ◽  
Automatic Segmentation ◽  
Magnetic Resonance Images ◽  
Mr Image ◽  
Prostate Segmentation ◽  
Image Appearance ◽  
Mri Scans ◽  
Magnetic Resonance Imaging Mri ◽  
Mr Image Segmentation

The prostate cancer is the second most frequent tumor amongst men. Statistics shows that biopsy reveals only 70-80% clinical cancer cases. Multiparametric magnetic resonance imaging (MRI) technique comes to play and is used to help to determine the location to perform a biopsy. With the aim to automating the biopsy localization, prostate segmentation has to be performed in magnetic resonance images. Computer image analysis methods play the key role here. The problem of automated prostate magnetic resonance (MR) image segmentation is burdened by the fact that MRI signal intensity is not standardized: field of view and image appearance is for a large part determined by acquisition protocol, field strength, coil profile and scanner type. Authors overview the most recent Prostate MR image segmentation challenge results and provide insights on T2-weighted MRI scan images automated prostate segmentation problem by comparing the best obtained automatic segmentation algorithms and applying them to 2D prostate segmentation case. The most important benefit of this research will have medical doctors involved in the management of the cancer.

Visual enhancement of brain cancer MRI using multiscale dyadic filter and Hilbert transformation

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Ankit Vidyarthi
Keyword(s):  
Decision Making ◽  
Medical Images ◽  
Spectral Information ◽  
Mr Images ◽  
Mr Image ◽  
New Approach ◽  
Visual Enhancement ◽  
Signal Image ◽  
Better Than

AbstractThe quality of the medical image plays a major role in decision making by the radiologists. There exists a visual differentiation between the normal scene color images and medical images. Due to the low illumination and unavailability of the color parameter, medical images require more attention by radiologists for decision making. In this paper a new approach is proposed that enhances the quality of the Magnetic Resonance (MR) images. Proposed approach uses the spectral information present in form of Amplitude and Frequency within the MR image slices for an enhancement. The extracted enhanced spectral information gives better visualization as compared with original signal image generated from MR scanner. The quantitative analysis of the proposed approach suggests that the new method is far better than the traditional state-of-art image enhancement methods.

Assessment of automatic segmentation accuracy with various point cloud density

2020 ◽  
Vol 961 (7) ◽  
pp. 47-55
Author(s):  
A.G. Yunusov ◽  
A.J. Jdeed ◽  
N.S. Begliarov ◽  
M.A. Elshewy
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Reference Data ◽  
Automatic Segmentation ◽  
Geometric Accuracy ◽  
Segmentation Method ◽  
Segmentation Methods ◽  
Segmentation Accuracy ◽  
Number Of Segments ◽  
Cloud Density

Laser scanning is considered as one of the most useful and fast technologies for modelling. On the other hand, the size of scan results can vary from hundreds to several million points. As a result, the large volume of the obtained clouds leads to complication at processing the results and increases the time costs. One way to reduce the volume of a point cloud is segmentation, which reduces the amount of data from several million points to a limited number of segments. In this article, we evaluated effect on the performance, the accuracy of various segmentation methods and the geometric accuracy of the obtained models at density changes taking into account the processing time. The results of our experiment were compared with reference data in a form of comparative analysis. As a conclusion, some recommendations for choosing the best segmentation method were proposed.

Sign in / Sign up

Export Citation Format

Share Document