• International Journal of Computer Science & Network Security
• /
• v.22 no.8
• /
• pp.343-351
• /
• 2022

A brain tumor forms when some tissue becomes old or damaged but does not die when it must, preventing new tissue from being born. Manually finding such masses in the brain by analyzing MRI images is challenging and time-consuming for experts. In this study, our main objective is to detect the brain's tumorous part, allowing rapid diagnosis to treat the primary disease instantly. With image processing techniques and deep learning prediction algorithms, our research makes a system capable of finding a tumor in MRI images of a brain automatically and accurately. Our tumor segmentation adopts the U-Net deep learning segmentation on the standard MICCAI BRATS 2018 dataset, which has MRI images with different modalities. The proposed approach was evaluated and achieved Dice Coefficients of 0.9795, 0.9855, 0.9793, and 0.9950 across several test datasets. These results show that the proposed system achieves excellent segmentation of tumors in MRIs using deep learning techniques such as the U-Net algorithm.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.416-418
• /
• 2022

Glioma is a type of brain tumor that occurs in glial cells and is classified into two types: high hrade hlioma with a poor prognosis and low grade glioma. Magnetic resonance imaging (MRI) as a non-invasive method is widely used in glioma diagnosis research. Studies to obtain complementary information by combining multiple modalities to overcome the incomplete information limitation of single modality are being conducted. In this study, we developed a 3D CNN-based model that applied input-level fusion to MRI of four modalities (T1, T1Gd, T2, T2-FLAIR). The trained model showed classification performance of 0.8926 accuracy, 0.9688 sensitivity, 0.6400 specificity, and 0.9467 AUC on the validation data. Through this, it was confirmed that the grade of glioma was effectively classified by learning the internal relationship between various modalities.

• Clinical and Experimental Pediatrics
• /
• v.63 no.3
• /
• pp.88-95
• /
• 2020

Accurate localization of the seizure onset zone is important for better seizure outcomes and preventing deficits following epilepsy surgery. Recent advances in neuroimaging techniques have increased our understanding of the underlying etiology and improved our ability to noninvasively identify the seizure onset zone. Using epilepsy-specific magnetic resonance imaging (MRI) protocols, structural MRI allows better detection of the seizure onset zone, particularly when it is interpreted by experienced neuroradiologists. Ultra-high-field imaging and postprocessing analysis with automated machine learning algorithms can detect subtle structural abnormalities in MRI-negative patients. Tractography derived from diffusion tensor imaging can delineate white matter connections associated with epilepsy or eloquent function, thus, preventing deficits after epilepsy surgery. Arterial spin-labeling perfusion MRI, simultaneous electroencephalography (EEG)-functional MRI (fMRI), and magnetoencephalography (MEG) are noinvasive imaging modalities that can be used to localize the epileptogenic foci and assist in planning epilepsy surgery with positron emission tomography, ictal single-photon emission computed tomography, and intracranial EEG monitoring. MEG and fMRI can localize and lateralize the area of the cortex that is essential for language, motor, and memory function and identify its relationship with planned surgical resection sites to reduce the risk of neurological impairments. These advanced structural and functional imaging modalities can be combined with postprocessing methods to better understand the epileptic network and obtain valuable clinical information for predicting long-term outcomes in pediatric epilepsy.

• Journal of Veterinary Clinics
• /
• v.41 no.2
• /
• pp.79-87
• /
• 2024

The tarsus in dogs has a complex structure that makes its evaluation relatively challenging. Because an accurate diagnosis of the tarsus is difficult through basic examinations alone, imaging tests are essential. Previous studies have explored the anatomical and radiological features of the canine tarsus using several imaging modalities. However, the imaging utility of the tarsus across different modalities has not been thoroughly evaluated. This study aimed to visualize the tarsal structures using magnetic resonance imaging (MRI) and ultrasonography, compare their utility, and propose suitable imaging modalities and conditions for evaluating specific tarsal structures. Magnetic resonance imaging and ultrasound scans of the tarsus of four healthy dogs were performed, and two observers rated the utility of each image on a five-point scale. Although MRI is more beneficial for assessing the tarsal structures than ultrasound, ultrasound also appears clinically useful for evaluating the cranial tibialis muscle, deep digital flexor tendon, subcutaneous fat, joint space, and superficial digital flexor tendon. In addition, each structure of interest can be evaluated for optimal visibility using specific ultrasound sections, MRI sequences, and planes. In veterinary clinical practice, an initial assessment using ultrasound imaging with optimal visibility is required and if further evaluation is necessary, MRI examinations with optimal MRI sequences and planes can be performed.

• Korean Journal of Digital Imaging in Medicine
• /
• v.6 no.1
• /
• pp.51-64
• /
• 2003

This thesis describes the effective interfacing methods of PACS Modality based on the system installation andoperating experiences. PACS(Picture Archiving and Communication Systems) is a system for medical image archiving and communication using large storage device and high-speed network. The standard communication protocol of PACS is DICOM(Digital Imaging and Communication in Medicine) based on TCP/IP and point-to-point protocol. However, there are many Non-DICOM Modalities and DICOM Modalities having problems. First, we had interfaced almost modalities. Fuji CR, GE CT, MRI, Angio, Fluoro, Phillips Angio, Shimadzu Fluoro. Ultrasound PACS, with the main PACS in the Seoul S Hospital as large scale hospital. And we manipulated the intelligent image distribution and the CT. MRI Interfaces never experienced beforein the Anyang J Hospital and the Chungju C Hospital as mid or small scale hospital. Technically, we developed both the DICOM Interface and the Non-DICOM Interface. At the last, the DICOM Worklist and the DICOM Print Interface were implemented in the Seoul B Hospital, the Bucheon SJ Hospital and the Seoul K Hospital independently with PACS. The Oracle, Sybase and MS-SQL are used as database, and UNIX, Macintosh, MS Windows as operating systems. And the Visual C++ and UNIX C are the main programming tools. We have used UTP, coaxial and fiber optic cable under 10/100 mbps LAN for networking.

• Korean Journal of Digital Imaging in Medicine
• /
• v.5 no.1
• /
• pp.46-63
• /
• 2002

This thesis describes the effective interfacing methods of PACS Modality based on the system installation and operating experiences. PACS(Picture Archiving and Communication Systems) is a system for medical image archiving and communication using large storage device and high-speed network. The standard communication protocol of PACS is DICOM(Digital Imaging and Communication in Medicine) based on TCP/IP and point-to-point protocol. However, there are many Non-DICOM Modalities and DICOM Modalities having problems. First, we had interfaced almost modalities, Fuji CR, GE CT, MRI, Angio, Fluoro, Phillips Angio, Shimadzu Fluoro, Ultrasound PACS, with the main PACS in the Seoul S Hospital as large scale hospital. And we manipulated the intelligent image distribution and the CT, MRI Interfaces never experienced before in the Anyang J Hospital and the Chungju C Hospital as mid or small scale hospital. Technically, we developed both the DICOM Interface and the Non-DICOM Interface. At the last, the DICOM Worklist and the DICOM Print Interface were implemented in the Seoul B Hospital, the Bucheon SJ Hospital and the Seoul K Hospital independently with PACS. The Oracle, Sybase and MS-SQL are used as database, and UNIX, Macintosh, MS Windows as operating systems. And the Visual C++ and UNIX C are the main programming tools. We have used UTP, coaxial and fiber optic Gable under 10/100 mbps LAN for networking.

• The Korean Journal of Pain
• /
• v.30 no.3
• /
• pp.165-175
• /
• 2017

Nuclear medicine imaging is widely used in pain medicine. Low back pain is commonly encountered by physicians, with its prevalence from 49% to 70%. Computed tomography (CT) or magnetic resonance imaging (MRI) are usually used to evaluate the cause of low back pain, however, these findings from these scans could also be observed in asymptomatic patients. Bone scintigraphy has an additional value in patients with low back pain. Complex regional pain syndrome (CRPS) is defined as a painful disorder of the extremities, which is characterized by sensory, autonomic, vasomotor, and trophic disturbances. To assist the diagnosis of CRPS, three-phase bone scintigraphy is thought to be superior compared to other modalities, and could be used to rule out CRPS due to its high specificity. Studies regarding the effect of bone scintigraphy in patients with extremity pain have not been widely conducted. Ultrasound, CT and MRI are widely used imaging modalities for evaluating extremity pain. However, SPECT/CT has an additional role in assessing pain in the extremities.

• Journal of Biomedical Engineering Research
• /
• v.31 no.4
• /
• pp.285-291
• /
• 2010

Recently, advance on various modalities of diagnosing, prostate volume estimation became possible not only by the existing two-dimension medical images data but also by the three-dimensional medical images data. In this study, magnetic resonance image (MRI), computer tomography (CT) and ultrasound (US) were employed to evaluate prostate phantom volume measurements for estimation, comparison and analysis. For the prostate phantoms aimed at estimating the volume, total of 17 models were developed by using devils-tongue jelly and changing each of the 5ml of capacity from 20ml to 100ml. For the volume estimation through 2D US, the calculation of the diameter with C9-5Mhz transducer was conducted by ellipsoid formula. For the volume estimation through 3D US, the Qlab software (Philips Medical) was used to calculate the volume data estimated by 3D9-3Mhz transducer. Moreover, the images by 16 channels CT and 1.5 Tesla MRI were added by the method of continuous cross-section addition and each of imaginary prostate model's volume was yielded. In the statistical analysis for comparing the availability of volume estimation, the correlation coefficient (r) was more than 0.9 for all indicating that there were highly correlated, and there were not statistically significant difference between each of the correlation coefficient (p=0.001). Therefore, the estimation of prostate phantom volume using three-dimensional modalities of diagnosing was quite closed to the actual estimation.

• Applied Microscopy
• /
• v.46 no.4
• /
• pp.179-183
• /
• 2016

Mapping brain structural and functional connections through the whole brain is essential for understanding brain mechanisms and the physiological bases of brain diseases. Although region specific structural or functional deficits cause brain diseases, the changes of interregional connections could also be important factors of brain diseases. This review will introduce common neuroimaging modalities, including structural magnetic resonance imaging (MRI), functional MRI (fMRI), diffusion tensor imaging, and other recent neuroimaging analyses methods, such as voxel-based morphometry, cortical thickness analysis, local gyrification index, and shape analysis for structural imaging. Tract-Based Spatial Statistics, TRActs Constrained by UnderLying Anatomy for diffusion MRI, and independent component analysis for fMRI also will also be introduced.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1528-1535
• /
• 1997

Many radiological modalities has been applied to medicine as a basic fundamental diagnosis and therapy recently. The prevalence of computer systems affect most images to be digitized. However conventional X-ray film images are not digital images eventhough they covers 70% of all radiologica images. This is the hinderacne of building PACS. In this paper all radiological digital imaging parts such as DSA. CR. MRI. SPECT. PET and ultrasonography were briefly introduced and the applications were described. In brief digital radiography contribute to enhance the medical service quality. And the digital substituition of conventional X-ray film image is inevitable.