• Proceedings of the KOSOMBE Conference
• /
• v.1998 no.11
• /
• pp.60-61
• /
• 1998

In this paper, we propose an algorithm for automatic segmentation of 3-dimesional brain MR images. In order to segment 3-dimensional brain MR images, we start segmentation from a mid-sagittal brain MR image. Then the segmented mid-sagittal brain MR image is used as a mask that is applied to the remaining lateral slices. Then we apply preprocessing, which includes thresholding and region-labeling, to the lateral slices, resulting in simplified 3-D brain MR images. Finally, we remove remaining problematic regions in the 3-dimensional brain MR image using the connectivity-based thresholding segmentation algorithm. Experiments show satisfactory results.

• Journal of Korean Neurosurgical Society
• /
• v.47 no.3
• /
• pp.203-209
• /
• 2010

Objective : The purpose of study was to evaluate the feasibility of brain magnetic resonance (MR) images of the rat obtained using a 1.5T MR machine in several blood-brain barrier (BBB) experiments. Methods : Male Sprague-Dawley rats were used. MR images were obtained using a clinical 1.5T MR machine. A microcatheter was introduced via the femoral artery to the carotid artery. Normal saline (group 1, n = 4), clotted autologous blood (group 2, n = 4), triolein emulsion (group 3, n = 4), and oleic acid emulsion (group 4, n = 4) were infused into the carotid artery through a microcatheter. Conventional and diffusion-weighted images, the apparent coefficient map, perfusion-weighted images, and contrast-enhanced MR images were obtained. Brain tissue was obtained and triphenyltetrazolium chloride (TTC) staining was performed in group 2. Fluorescein isothiocyanate (FITC)-labeled dextran images and endothelial barrier antigen (EBA) studies were performed in group 4. Results : The MR images in group 1 were of good quality. The MR images in group 2 revealed typical findings of acute cerebral infarction. Perfusion defects were noted on the perfusion-weighted images. The MR images in group 3 showed vasogenic edema and contrast enhancement, representing vascular damage. The rats in group 4 had vasogenic edema on the MR images and leakage of dextran on the FITC-labeled dextran image, representing increased vascular permeability. The immune reaction was decreased on the EBA study. Conclusion : Clinical 1.5T MR images using a rat depicted many informative results in the present study. These results can be used in further researches of the BBB using combined clinical MR machines and immunohistochemical examinations.

• Transactions on Electrical and Electronic Materials
• /
• v.15 no.4
• /
• pp.230-234
• /
• 2014

Automatic detection of disease helps medical institutions that are introducing digital images to read images rapidly and accurately, and is thus applicable to lesion diagnosis and treatment. The aim of this study was to apply a symmetry contribution algorithm to unsharp mask filter-applied MR images and propose an analysis technique to automatically recognize brain tumor and edema. We extracted the skull region and drawed outline of the skull in database of images obtained at P University Hospital and detected an axis of symmetry with cerebral characteristics. A symmetry contribution algorithm was then applied to the images around the axis of symmetry to observe intensity changes in pixels and detect disease areas. When we did not use the unsharp mask filter, a brain tumor was detected in 60 of a total of 95 MR images. The disease detection rate for the brain was 63.16%. However, when we used the unsharp mask filter, the tumor was detected in 87 of a total of 95 MR images, with a disease detection rate of 91.58%. When the unsharp mask filter was used in the pre-process stage, the disease detection rate for the brain was higher than when it was not used. We confirmed that unsharp mask filter can be used to rapidly and accurately to read many MR images stored in a database.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.343-344
• /
• 2009

The aim in this paper is to show how to extract scalp of a series of brain MR images by using region growing segmentation algorithm. Most researches are all forces on the segmentation of skull, gray matter, white matter and CSF. Prior to the segmentation of these inner objects in brain, we segmented the scalp and the brain from the MR images. The scalp mask makes us to quickly exclude background pixels with intensities similar those of the skull, while the brain mask obtained from our brain surface. We make use of connected threshold method (CTM) and confidence connected method (CCM). Both of them are two implementations of region growing in Insight Toolkit (ITK). By using these two methods, the results are displayed contrast in the form of 2D and 3D scalp images.

• The Journal of the Korea Contents Association
• /
• v.2 no.3
• /
• pp.1-15
• /
• 2002

A noel automated brain region extraction method in single channel MR images for visualization and analysis of a human brain is presented. The method generates a volume of brain masks by automatic thresholding using a dual curve fitting technique and by 3D morphological operations. The dual curve fitting can reduce an error in clue fitting to the histogram of MR images. The 3D morphological operations, including erosion, labeling of connected-components, max-feature operation, and dilation, are applied to the cubic volume of masks reconstructed from the thresholded Drain masks. This method can automatically extract a brain region in any displayed type of sequences, including extreme slices, of SPGR, T1-, T2-, and PD-weighted MR image data sets which are not required to contain the entire brain. In the experiments, the algorithm was applied to 20 sets of MR images and showed over 0.97 of similarity index in comparison with manual drawing.

• Journal of Multimedia Information System
• /
• v.8 no.2
• /
• pp.79-84
• /
• 2021

Detecting brain tumors of different sizes is a challenging task. This study aimed to identify brain tumors using detection algorithms. Most studies in this area use segmentation; however, we utilized detection owing to its advantages. Data were obtained from 64 patients and 11,200 MR images. The deep learning model used was RetinaNet, which is based on ResNet152. The model learned three different types of pre-processing images: normal, general histogram equalization, and contrast-limited adaptive histogram equalization (CLAHE). The three types of images were compared to determine the pre-processing technique that exhibits the best performance in the deep learning algorithms. During pre-processing, we converted the MR images from DICOM to JPG format. Additionally, we regulated the window level and width. The model compared the pre-processed images to determine which images showed adequate performance; CLAHE showed the best performance, with a sensitivity of 81.79%. The RetinaNet model for detecting brain tumors through deep learning algorithms demonstrated satisfactory performance in finding lesions. In future, we plan to develop a new model for improving the detection performance using well-processed data. This study lays the groundwork for future detection technologies that can help doctors find lesions more easily in clinical tasks.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2002.09a
• /
• pp.322-323
• /
• 2002

Partial volume averaging effect of PET data influences on the accuracy of quantitative measurements of regional brain metabolism because spatial resolution of PET is limited. The purpose of this study was to evaluate the accuracy of partial volume correction carried out on $^{18}$ F-PET images using Hoffman brain phantom. $^{18}$ F-PET Hoffman phantom images were co-registered to MR slices of the same phantom. All the MR slices of the phantom were then segmented to be binary images. Each of these binary images was convolved in 2 dimensions with the spatial resolution of the PET. The original PET images were then divided by the smoothed binary images in slice-by-slice, voxel-by-voxel basis resulting in larger PET image volume in size. This enlarged partial volume corrected PET image volume was multiplied by original binary image volume to exclude extracortical region. The evaluation of partial volume corrected PET image volume was performed by region of interests (ROI) analysis applying ROIs, which were drawn on cortical regions of the original MR image slices, to corrected and original PET image volume. From the ROI analysis, range of regional mean values increases of partial volume corrected PET images was 4 to 14%, and average increase for all the ROIs was about 10% in this phantom study. Hoffman brain phantom study was useful for the objective evaluation of the partial volume correction method. This MR-based correction method would be applicable to patients in the. quantitative analysis of FDG-PET studies.

• Proceedings of the KSMRM Conference
• /
• 2003.10a
• /
• pp.99-99
• /
• 2003

To exhibit our clinical experience of diffusion-weighted (DW) MR imaging for various brain pathologies and to determine its role in characterizing brain pathologies in children. DW images in 177 children (M：F＝96：81, mean age, 4.7 years) with various brain pathologies were retrospectively collected over past 3 years. DW images (b value： 1000 s/mm) were reviewed along with corresponding apparent diffusion coefficient (ADC) maps. Brain pathologies included cystic or solid brain tumor (n = 55), cerebral infarct (n = 32), cerebritis with or without brain abscess (n = 21), metabolic or toxic brain disorder (n = 19), demyelinating disease (n = 16), hypoxic-ischemic encephalopathy (n = 16), intracerebral hemorrhage including traumatic brain lesion (n = 15), and posterior reversible leukoencephalopathy (n = 3). We reviewed whether DW images and ADCmaps contribute to further characterization of brain pathologies by defining a chronological age of lesions, the presence of cytotoxic edema in lesions, and the nature of cystic lesions.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.11
• /
• pp.2425-2431
• /
• 1997

The increased usage of Magnetic Resonance Image (MRI) required the method for automatic segmentation of medical image that is more useful so as to diagnose the dissecitive information of a atient quickly and effectively through MR scans.The use of neural networks may give much hep to solving the complex problems concerned the matter. This paper proposes the new method for automatic segmentation of magnetic resonance (MR) images of the brain by using neural networks brained by back-propagation algorithm. The trained neural networks by the segmenting MR images of a patient produce an output that networks can segment MR images of the other patients automatically, too and show a clear image of the brain.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.1167-1187
• /
• 2020

With the development of medical imaging technology, image registration has been widely used in the field of disease diagnosis. The registration between different modal images of brain magnetic resonance (MR) is particularly important for the diagnosis of brain diseases. However, previous registration methods don't take advantage of the prior knowledge of bilateral brain symmetry. Moreover, the difference in gray scale information of different modal images increases the difficulty of registration. In this paper, a multimodal medical image registration method based on image segmentation and symmetric self-similarity is proposed. This method uses modal independent self-similar information and modal consistency information to register images. More particularly, we propose two novel symmetric self-similarity constraint operators to constrain the segmented medical images and convert each modal medical image into a unified modal for multimodal image registration. The experimental results show that the proposed method can effectively reduce the error rate of brain MR multimodal medical image registration with rotation and translation transformations (average 0.43mm and 0.60mm) respectively, whose accuracy is better compared to state-of-the-art image registration methods.