• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.6
• /
• pp.1333-1342
• /
• 2018

Until now, Electroencephalography(: EEG) has been the most important and convenient method for the diagnosis and treatment of epilepsy. However, it is difficult to identify the wave characteristics of an epileptic EEG signals because it is very weak, non-stationary and has strong background noise. In this paper, we analyse the effect of dimensionality reduction methods on Epileptic EEG feature selection and classification. Three dimensionality reduction methods: Pincipal Component Analysis(: PCA), Kernel Principal Component Analysis(: KPCA) and Linear Discriminant Analysis(: LDA） were investigated. The performance of each method was evaluated by using Support Vector Machine SVM, Logistic Regression(: LR), K-Nearestneighbor(: K-NN), Decision Tree(: DR) and Random Forest(: RF). From the experimental result, PCA recorded 75% of highest accuracy in SVM, LR and K-NN. KPCA recorded 85% of best performance in SVM and K-KNN while LDA achieved 100% accuracy in K-NN. Thus, LDA dimensionality reduction is found to provide the best classification result for epileptic EEG signal.

• The Journal of Internal Korean Medicine
• /
• v.43 no.2
• /
• pp.191-200
• /
• 2022

Intractable hiccups are those which persist for more than one month and can often occur in patients with disorders of the central nervous system, such as stroke, epilepsy, or brain tumor. An 80-year-old male patient undergoing conservative hemodialysis for diabetic nephropathy, recently developed paralysis and dysphagia due to central nervous system complications including stroke and epilepsy. He was admitted to the ◯◯ Oriental Medicine Hospital, and treated with herbal medicine (Gyulpijugyeo-tang, Jeonssiigong-san, and Ijin-tang) and electrical acupuncture for 30 days. No side effects were observed during hospitalization. The frequency and duration of hiccups were measured daily and found to reduce, and the effect persisted during his admission. The patient took no other nervous system drugs. In conclusion, Korean medicine like gyulpijugyeo-tang and acupuncture can be effective for patients with intractable hiccups who cannot use alternative drugs or treatment, because of other complications.

• Pediatric Infection and Vaccine
• /
• v.30 no.2
• /
• pp.91-96
• /
• 2023

Infection with enterovirus (EV) 71 is usually associated with hand-foot-and-mouth disease and herpangina. The most frequent neurologic complication is brainstem encephalitis. A 30-month-old boy visited the pediatric emergency department with fever, lethargy, and abnormal eye contact. His mental status was slightly drowsy. On hospitalization day 2, the patient experienced respiratory arrest with apnea. Brain magnetic resonance imaging revealed bilateral symmetric T2-high signal lesions without enhancement in the posterior aspect of the brainstem and left medial temporal lobe. Electroencephalography was indicative of diffuse cerebral dysfunction with diffuse high amplitude and irregular delta activities. He underwent a gene study and was diagnosed with myoclonic epilepsy with ragged red fibers syndrome. We report a case of EV 71 brainstem encephalitis by polymerase chain reaction for nasopharyngeal aspirates and feces with rapid progression within one day of fever without the manifestation of throat and skin lesions because of his underlying mitochondrial disease.

• The Korean Journal of Nuclear Medicine
• /
• v.38 no.3
• /
• pp.233-240
• /
• 2004

Purpose: We developed a computer-aided classifier using artificial neural network (ANN) to discriminate the cerebral metabolic pattern of medial and lateral temporal lobe epilepsy (TLE). Materials and Methods: We studied brain F-18-FDG PET images of 113 epilepsy patients sugically and pathologically proven as medial TLE (left 41, right 42) or lateral TLE (left 14, right 16). PET images were spatially transformed onto a standard template and normalized to the mean counts of cortical regions. Asymmetry indices for predefined 17 mirrored regions to hemispheric midline and those for medial and lateral temporal lobes were used as input features for ANN. ANN classifier was composed of 3 independent multi-layered perceptrons (1 for left/right lateralization and 2 for medial/lateral discrimination) and trained to interpret metabolic patterns and produce one of 4 diagnoses (L/R medial TLE or L/R lateral TLE). Randomly selected 8 images from each group were used to train the ANN classifier and remaining 51 images were used as test sets. The accuracy of the diagnosis with ANN was estimated by averaging the agreement rates of independent 50 trials and compared to that of nuclear medicine experts. Results: The accuracy in lateralization was 89% by the human experts and 90% by the ANN classifier Overall accuracy in localization of epileptogenic zones by the ANN classifier was 69%, which was comparable to that by the human experts (72%). Conclusion: We conclude that ANN classifier performed as well as human experts and could be potentially useful supporting tool for the differential diagnosis of TLE.

• The Korean Journal of Nuclear Medicine
• /
• v.36 no.3
• /
• pp.155-165
• /
• 2002

Purpose: The aim of this study was to identify the brain areas whose regional cerebral blood flow (rCBF) was changed in medial temporal lobe epilepsy (mTLE) using ${H_2}^{15}O-PET$. Materials and Methods: 12 patients with mTLE (6 left, 6 right mTLE) and 6 normal controls were scanned during a fixation baseline period and a sensory-motor condition where subjects pressed a button to an upward arrow. A voxel-based analysis using SPM99 software was peformed to compare the patient groups with the normal controls for the rCBF during fixation baseline period and for relative changes of rCBF during the sensory-motor task relative to fixation. Results: During the fixation baseline, a significant reduction of rCBF was found posterior insula bilaterally and right frontopolar regions in right mTLE patients compared to the normal controls. In left mTLE patients, the reduction was found in left frontopolar and temporal legions. During the sensory-motor task, rCBF increase over the fixation period, was reduced in left frontal and superior temporal legions in the right mTLE patients whereas in various areas of right hemisphere in left mTLE patients, relative to normal controls. However, the increased rCBF was also found in the left inferior parietal and anterior thalamic/fornix regions in both right and left mTLE patients compared to normal controls. Conclusion: Epilepsy induced changes were found not only in relative increase/decrease of rCBF during a simple sensory-motor control condition relative to a fixation rest condition but also in the relative rCBF distribution during the rest period.

• Journal of Biomedical Engineering Research
• /
• v.19 no.5
• /
• pp.455-468
• /
• 1998

For the objective interpretation of cerebral metabolic patterns in epilepsy patients, we developed computer-aided classifier using artificial neural network. We studied interictal brain FDG PET scans of 257 epilepsy patients who were diagnosed as normal(n=64), L TLE (n=112), or R TLE (n=81) by visual interpretation. Automatically segmented volume of interest (VOI) was used to reliably extract the features representing patterns of cerebral metabolism. All images were spatially normalized to MNI standard PET template and smoothed with 16mm FWHM Gaussian kernel using SPM96. Mean count in cerebral region was normalized. The VOls for 34 cerebral regions were previously defined on the standard template and 17 different counts of mirrored regions to hemispheric midline were extracted from spatially normalized images. A three-layer feed-forward error back-propagation neural network classifier with 7 input nodes and 3 output nodes was used. The network was trained to interpret metabolic patterns and produce identical diagnoses with those of expert viewers. The performance of the neural network was optimized by testing with 5~40 nodes in hidden layer. Randomly selected 40 images from each group were used to train the network and the remainders were used to test the learned network. The optimized neural network gave a maximum agreement rate of 80.3% with expert viewers. It used 20 hidden nodes and was trained for 1508 epochs. Also, neural network gave agreement rates of 75~80% with 10 or 30 nodes in hidden layer. We conclude that artificial neural network performed as well as human experts and could be potentially useful as clinical decision support tool for the localization of epileptogenic zones.

• Korean Journal of Radiology
• /
• v.1 no.1
• /
• pp.25-32
• /
• 2000

Objective: The purpose of our study was to determine the ability of H-1 MR spectroscopy (MRS) to lateralize the lesion in patients with hippocampal sclerosis. Materials and Methods: Twenty healthy volunteers and 25 patients with intractable temporal lobe epilepsy whose MR imaging diagnosis was unilateral hippocampal sclerosis were included. This diagnosis was based on the presence of unilateral atrophy and/or high T2 signal intensity of the hippocampus. Single-voxel H-1 MRS was carried out on a 1.5-T unit using PRESS sequence (TE, 136 msec). Spectra were obtained from hippocampal areas bilaterally with volumes of interest (VOIs) of 6.0 cm³ and 2.25 cm³ in healthy volunteers, and of either 6.0 cm³ (n = 14) or 2.25 cm³ (n = 11) in patients. Metabolite ratios of NAA/Cho and NAA/Cr were calculated from relative peak height measurements. The capability of MRS to lateralize the lesion and to detect bilateral abnormalities was compared with MR imaging diagnosis as a standard of reference. Results: In healthy volunteers, NAA/Cho and NAA/Cr ratios were greater than 0.8 and 1.0, respectively. In patients, the mean values of these ratios were significantly lower on the lesion side than on the contralateral side, and lower than those of healthy volunteers (p < .05). The overall correct lateralization rate of MRS was 72% (18/25); this rate was lower with a VOI of 6.0 cm³ than of 2.25 cm³ (64% versus 82%, p < .05). Bilateral abnormalities on MRS were found in 24% (6/25) of cases. Conclusion: Although its rate of correct lateralization is low, single-voxel H-1 MRS is a useful and promising diagnostic tool in the evaluation of hippocampal sclerosis, particularly for the detection of bilateral abnormalities. To improve the diagnostic accuracy of H-1 MRS, further investigation, including the use of a smaller VOI and measurement of the absolute amount of metabolites, are needed.

• Korean Journal of Psychosomatic Medicine
• /
• v.19 no.2
• /
• pp.101-108
• /
• 2011

Objectives:We conduct this study to investigate the common features between Attention Deficit Hyperactivity Disorder(ADHD) and epileptic patients compared to normal control. Methods:Epileptic patients were recruited from the department of pediatic in Jesus Hospital. ADHD patients were recruited from the department of neuropsychiatry in Jesus Hospital. We excluded mental retardation or brain organic pathology. We use ADHD Diagnostic System and Korean-Child Behavior Checklist(K-CBCL) to assess features of ADHD. Electroencephalogram(EEG) of ADHD, epileptic patients and normal control were analyzed and compared. Results:Compared to normal control group, inattention, reaction time deviation were increased in both ADHD and epilepsy group. EEG abnormalities(control 13.8%, epilepsy 97.1%, ADHD 40%) in three groups were reported. Conclusion:There are common features of ADHD and epileptic patients.

• The Korean Journal of Nuclear Medicine
• /
• v.32 no.1
• /
• pp.20-31
• /
• 1998

A robust algorithm to disclose and display the difference of ictal and interictal perfusion may facilitate the detection of ictal hyperfusion foci. Diagnostic performance of localizing epileptogenic zones with subtracted SPECT images was compared with the visual diagnosis using ictal and interictal SPECT, MR, or PET. Ietal and interictal Tc-99m-HMPAO cerebral perfusion SPECT images of 48 patients(pts) were processed to get parametric subtracted images. Epileptogenic foci of all pts were diagnosed by seizure free state after resection of epileptogenic zones. In subtraction SPECT, we used normalized difference ratio of pixel counts(ictal-interictal)/interictal ${\times}100%$) after correcting coordinates of ictal and interictal SPECT in semi-automatized 3-dimensional fashion. We found epileptogenic zones in subtraction SPECT and compared the performance with visual diagnosis of ictal and interictal SPECT, MR and PET using post-surgical diagnosis as gold standard. The concordance of subtraction SPECT and ictal-interictal SPECT was moderately good(kappa=0.49). The sensitivity of ictal-interictal SPECT was 73% and that of subtraction SPECT 58%. Positive predictive value of ictal-interictal SPECT was 76% and that of subtraction SPECT was 64%. There was no statistical difference between sensitivity or positive predictive values of subtraction SPECT and ictal-interictal SPECT, MR or PET. Such was also the case when we divided patients into temporal lobe epilepsy and neocortical epilepsy. We conclude that subtraction SPECT we produced had equivalent diagnostic performance compared with ictal-interictal SPECT in localizing epileptogenic zones. Additional value of these subtraction SPECT in clinical interpretation of ictal and interictal SPECT should be further evaluated.

• Clinical and Experimental Pediatrics
• /
• v.51 no.4
• /
• pp.420-425
• /
• 2008

Purpose : The purpose of this study was to evaluate acute childhood seizures, one of the most important causes of emergency room visits, to provide appropriate medical services. Methods : We reviewed the medical records of 433 (4.6%) pediatric patients with acute seizures that visited the emergency room at Masan Samsung hospital from 2004 to 2006. Results : The male to female ratio was 1.4:1 and the mean age was $40.9{\pm}34.9$ months range. The order of geographical distribution was Masan, Changwon, Haman, and others. Fever was present in 40.6% of patients; December (14.8%) was the most frequent month for visits and generalized tonic clonic seizures (62.7%) were the most common type of seizure. The average frequency and duration of the seizure was $1.5{\pm}1.0$ and $6.7{\pm}13.2$ minutes respectively. Febrile seizures were present in 69.7% of patients and afebrile seizures in 30.3%. The causes of the febrile seizures were acute pharyngotonsillitis (44.6%), acute bronchitis, gastroenteritis, pneumonia, urinary tract infection, and unknown origin, in order of frequency. The most common cause of an afebrile seizure was epilepsy (71.5%) followed by a benign convulsion with mild gastroenteritis (BCwMG), sequela of a perinatal brain injury or brain malformation, and acute CNS infection. Evaluation of the causes of an acute seizure according to age showed that febrile seizures, epilepsy, and the sequela of perinatal brain injuries were more common between 2 and 6 years of age and epilepsy, febrile seizures and acute CNS infection, in order of frequency, were common between 6 and 15 years of age. Many patients, 49.4%, were discharged without admission. Conclusion : The common characteristics of pediatric patients presenting to the emergency room were male gender, an age between 2-6 years, presenting during the month of December, with generalized tonic clonic seizures due to acute pharyngitis. The most common presentation for the group less than 6 years of age was a febrile seizure and in the group more than 6 years of age, it was epilepsy. In many cases, the seizures stopped by the time the family presented to the emergency room.