• Korean Journal of Head & Neck Oncology
• /
• v.28 no.2
• /
• pp.132-134
• /
• 2012

Ectopic thyroid is an uncommon embryologic aberration characterized by the presence of thyroid tissue in a site other than its usual pre-tracheal location. Dual ectopic thyroid is extremely rare, only few cases have been reported in the literature. Physical examination, laboratory test and radiologic examinations are usually performed for the diagnosis and therapeutic plan of dual ectopic thyroid. We report a 36-year old female with dual ectopic thyroid in lingual and hyoid regions but without thyroid tissue in its normal area. The diagnosis was made through pathologic examination after surgical resection.

• Journal of Korean Neurosurgical Society
• /
• v.43 no.3
• /
• pp.155-158
• /
• 2008

A 64-year-old woman was referred to our hospital with a one-month history of progressive headache. Magnetic resonance imaging (MRI) showed a hemorrhagic mass adjacent to the left inferior cerebellar hemisphere associated with a peripheral rim of signal void. Angiography demonstrated an avascular mass and the provisional diagnosis was a large cavernous angioma in the cerebellum. Intraoperative findings revealed a thrombosed giant aneurysm of the left distal posterior inferior cerebellar artery (PICA). We report an unusual case of a completely thrombosed giant aneurysm simulating a large cavernous angioma in the cerebellum. The cerebellar cisternal location of the mass may be a clue for the pre-operative diagnosis of an aneurysm.

• Clinics in Shoulder and Elbow
• /
• v.6 no.2
• /
• pp.173-177
• /
• 2003

Superficial lipoma was easy to diagnose, but deep lipoma, especially intraosseus lipoma, was difficult to detect pre-operatively. Intraosseous lipoma is very rare and had been difficult to differentiate from other tumors before image diagnosis was developed. Recently, the detecting ratio has increased due to advanced diagnostic tools. Preoperative diagnosis is crucial for the treatment plan and influences the approach method for excision. We experienced one case of misdiagnosis which was diagnosed as intraosseous lipoma according to the preoperative MRI but turned out to be a parosteal lipoma after the surgery.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.3230-3232
• /
• 2000

DR (Digital Radiography) system will be the best candidate for next generation x-ray diagnosis system. DR system will replace x-ray film by computer monitor and provide various merits like reduced processing time, easy recording, remote diagnosis and etc. In this paper, we propose the pre-processing algorithm which is designed to compensate dead and defected pixel for x-ray detector panel. We also designed DSP(Digital Signal Processor) based DR image processing board for real-time processing of suggested algorithm.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.15 no.3
• /
• pp.166-171
• /
• 2015

In this paper, we measure the current and vibration signals of one-dimensional time series that occur in a motor and pump, respectively. These machines are representative rotary and pumping machines. We also eliminate unnecessary components such as noise by pre-processing the current and vibration signals. Then, in order to diagnose fault signals for the pump and motor, we transform from one-dimensional time series to a two-dimensional phase portrait using Takens’ embedding method. After this transformation, we review the variation in the pattern according to the fault signals.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2904-2926
• /
• 2022

Currently, diabetes is the most common chronic disease in the world, affecting 23.7% of the population in the Kingdom of Saudi Arabia. Diabetes may be the cause of lower-limb amputations, kidney failure and blindness among adults. Therefore, diagnosing the disease in its early stages is essential in order to save human lives. With the revolution in technology, Artificial Intelligence (AI) could play a central role in the early prediction of diabetes by employing Machine Learning (ML) technology. In this paper, we developed a diagnosis system using machine learning models for the detection of type 2 diabetes among adults, through the adoption of two different diabetes datasets: one for training and the other for the testing, to analyze and enhance the prediction accuracy. This work offers an enhanced classification accuracy as a result of employing several pre-processing methods before applying the ML models. According to the obtained results, the implemented Random Forest (RF) classifier offers the best classification accuracy with a classification score of 98.95%.

• Korean Journal of Radiology
• /
• v.22 no.11
• /
• pp.1858-1874
• /
• 2021

Recent advances in the molecular and genetic characterization of central nervous system (CNS) tumors have ushered in a new era of tumor classification, diagnosis, and prognostic assessment. In this emerging and rapidly evolving molecular genetic era, imaging plays a critical role in the preoperative diagnosis and surgical planning, molecular marker prediction, targeted treatment planning, and post-therapy assessment of CNS tumors. This review provides an overview of the current imaging methods relevant to the molecular genetic classification of CNS tumors. Specifically, we focused on 1) the correlates between imaging features and specific molecular genetic markers and 2) the post-therapy imaging used for therapeutic assessment.

• Clinical and Experimental Pediatrics
• /
• v.49 no.1
• /
• pp.76-81
• /
• 2006

Purpose : This study evaluated the clinical characteristics of brain tumors in children according to their location, the parental delay and the doctor's delay between the onset of symptoms and the diagnosis of a pediatric brain tumor. In addition, this study compared the relationship between the pre-diagnostic symptomatic interval and the tumor location. Methods : A retrospective study was undertaken of 45 children with primary brain tumors admitted to Inha Hospital from July, 1986 to June, 2004. A diagnosis of the tumor location was made using brain MRI. Results : The male to female ratio was 1 : 0.67. The median age at diagnosis was 6.0 years in supratentorial tumors, 7.0 years in infratentorial tumors. Twenty four cases(53.3 percent) were located in the supratentorial area, 21 cases(46.6 percent) were located in the infratentorial area. The distribution of supratentorial tumors were 14(58.3 percent) in the cerebral hemisphere and temporal lobe, seven (29.1 percent) in the suprasellar area, and three(12.5 percent) in the pineal gland and posterial lateral ventricle. The distributions of the infratentorial tumors were 12(57.1 percent) in the cerebellar vermis and fourth ventricle, four(19.1 percent) in the brain stem, and five(23.8 percent) in the cerebellar hemisphere. The most common initial symptom was seizure(37.5 percent) in the supratentorial tumor and headache(38.0 percent) in infratentorial tumors. The median pre-diagnostic symptomatic interval (PSI) was 21 days(range 0-240 days). The median PSI with a parental delay in supratentorial tumor was six days(range 1-240 days), and 30 days(range 1-40 days) in the infratentorial tumor. We immediately diagnosed most cases after visiting the hospital. There was no significant relationship between the tumor location and the pre-diagnostic symptomatic interval. Conclusion : The most common symptom of supratentorial tumors and infratentorial tumors was seizure and headache, respectively. Although, the median pre-diagnostic symptomatic interval was shorter than in previous studies, a detailed medical history and a correctly interpreted neurological examination should lead to an earlier diagnosis of pediatric brain tumors.

• Journal of Korean Academy of Oral and Maxillofacial Radiology
• /
• v.29 no.2
• /
• pp.407-410
• /
• 1999

Purpose; To find out the best imaging parameters for the diagnosis of disc in MRI imaging. Materials and methods; The diagnostic quality of the disc among the Tl, PD and T2 images of same patients02 joints, 223 images) was compared by visual(I-IV grades) and gray level measurement (pre- and infra-discal area) method. Results; PD images showed best results with 43.7％ of the images belonging to grade III (good) and with statistically significant higher difference of the gray levels at pre- and infra-discal areas. But there were no grade N (excellent) images. Conclusions; PD images are best method among Tl. PD and T2 images in diagnosing the disc but since there were no excellent images further imaging parameters should be studied for better images.

• Journal of Chest Surgery
• /
• v.20 no.2
• /
• pp.384-392
• /
• 1987

The occlusive coronary artery disease presents a potential threat to a significant population in the United State. According to many case reports, the increasing incidence of coronary artery disease due to atherosclerosis is noted in Korean, recently. We experienced one case of coronary artery disease. He was a 68 year old male who had been suffered from hypertension since 1 5 years ago, and had intermittent conservative treatment at local clinic. He had been afflicted with severe chest pain on exertion, but this symptom was relieved on rest. Pre-operative EKG finding revealed no any other ischemic sign. Significant S-T segment depression was noted at lead II, aVF, V3, V4, and V5, and inverted T wave in V5 and V6 after Master`s test. Simple chest X-ray finding showed emphysematous field, bilaterally. Final pre-operative diagnosis was made by coronary angiogram, which showed almost 90% degree of occlusive lesion in the proximal part of left main coronary artery above the origin LAD artery. He was treated successfully by aorta-coronary saphenous vein graft under extra-corporeal circulation in May, 1987. He has been followed up with uneventful course.