• Investigative Magnetic Resonance Imaging
• /
• v.26 no.1
• /
• pp.1-9
• /
• 2022

Artificial intelligence (AI) powered by deep learning (DL) has shown remarkable progress in image recognition tasks. Over the past decade, AI has proven its feasibility for applications in medical imaging. Various aspects of clinical practice in neuroimaging can be improved with the help of AI. For example, AI can aid in detecting brain metastases, predicting treatment response of brain tumors, generating a parametric map of dynamic contrast-enhanced MRI, and enhancing radiomics research by extracting salient features from input images. In addition, image quality can be improved via AI-based image reconstruction or motion artifact reduction. In this review, we summarize recent clinical applications of DL in various aspects of neuroimaging.

• Journal of the Korean Society of Radiology
• /
• v.81 no.3
• /
• pp.467-487
• /
• 2020

Anatomical imaging is the basis of the diagnosis and treatment response assessment of brain tumors. Among the existing imaging techniques currently available in clinical practice, diffusion-weighted imaging and perfusion imaging provide additional information. Recently, with the increasing importance of evaluation of the genomic variation and heterogeneity of tumors, clinical application of imaging techniques using radiomics and deep learning is expected. In this review, we will describe recommendations for magnetic resonance imaging protocols focusing on anatomical images that are still important in the clinical application of brain tumor imaging, and the basic principles of diffusion-weighted imaging and perfusion imaging among the advanced imaging techniques, as well as their pathophysiological background and clinical application. Finally, we will review the future perspectives of radiomics and deep learning applications in brain tumor imaging, which have been studied to a great extent due to the development of computer technology.

• International Journal of Advanced Culture Technology
• /
• v.7 no.4
• /
• pp.327-333
• /
• 2019

Wind speed data constitute important weather information for aircrafts flying at low altitudes, such as drones. Currently, the accuracy of low altitude wind predictions is much lower than that of high-altitude wind predictions. Deep neural networks are proposed in this study as a method to improve wind speed forecast information. Deep neural networks mimic the learning process of the interactions among neurons in the brain, and it is used in various fields, such as recognition of image, sound, and texts, image and natural language processing, and pattern recognition in time-series. In this study, the deep neural network model is constructed using the wind prediction values generated by the numerical model as an input to improve the wind speed forecasts. Using the ground wind speed forecast data collected at the Boseong Meteorological Observation Tower, wind speed forecast values obtained by the numerical model are compared with those obtained by the model proposed in this study for the verification of the validity and compatibility of the proposed model.

• Journal of Korean Society of Water and Wastewater
• /
• v.34 no.6
• /
• pp.481-493
• /
• 2020

Deep learning models, which imitate the function of human brain, have drawn attention from many engineering fields (mechanical, agricultural, and computer engineering etc). The major advantages of deep learning in engineering fields can be summarized by objects detection, classification, and time-series prediction. As well, it has been applied into environmental science and engineering fields. Here, we compiled our previous attempts to apply deep learning models in water-environment field and presented the future opportunities.

• Korean Journal of Radiology
• /
• v.21 no.10
• /
• pp.1126-1137
• /
• 2020

Imaging plays a key role in the management of brain tumors, including the diagnosis, prognosis, and treatment response assessment. Radiomics and deep learning approaches, along with various advanced physiologic imaging parameters, hold great potential for aiding radiological assessments in neuro-oncology. The ongoing development of new technology needs to be validated in clinical trials and incorporated into the clinical workflow. However, none of the potential neuro-oncological applications for radiomics and deep learning has yet been realized in clinical practice. In this review, we summarize the current applications of radiomics and deep learning in neuro-oncology and discuss challenges in relation to evidence-based medicine and reporting guidelines, as well as potential applications in clinical workflows and routine clinical practice.

• Journal of Biomedical Engineering Research
• /
• v.33 no.1
• /
• pp.47-52
• /
• 2012

The purpose of this study is to investigate whether medication and deep brain stimulation (DBS) have differential effects on the speed and amplitude of bradykinesia in patients with Parkinson's disease (PD). Five PD patients with implanted DBS electrodes (age: $60.6{\pm}7.4yrs$, H&Y stage: $3.1{\pm}0.2$) participated in this study. FT (finger tapping) movement was measured using a gyrosensor system in four treatment conditions: Med (Medication)-off/DBS-off, Med-off/DBS-on, Med-on/DBS-off and Med-on/DBS-on. Quantitative measures representing average speed and amplitude of FT movement included root-mean-squared (RMS) angular velocity and RMS angle. One-way repeated measures ANOVA showed that RMS angular velocity of Med-on/DBS-on was significantly greater than those of Med-off/DBS-off and Med-off/DBS-on (p < 0.01) whereas RMS angle was not different among conditions (p = 0.06). Two way repeated measures ANOVA showed that only medication improved RMS angular velocity (p < 0.01), whereas both medication and DBS had no significant effect on RMS angle (p > 0.02). Effect size of RMS angular velocity was greater than that of RMS angle in both medication and DBS. This suggests that medication and DBS have differential effects on FT bradykinesia and velocity and amplitude impairments may be associated with different functional aspects in PD.

• Journal of Korean Neurosurgical Society
• /
• v.48 no.2
• /
• pp.134-138
• /
• 2010

Objective : Meige syndrome is the combination of blepharospasm and oromandibular dystonia. We assessed the surgical results of bilateral globus pallidus internus (GPi) deep brain stimulation (DBS) in patients with medically refractory Meige syndrome. Methods : Eleven patients were retrospectively analyzed with follow-ups of more than 12 months. The mean follow-up period was $23.1{\pm}6.4$ months. The mean age at time of surgery was $58.0{\pm}7.8$ years. The mean duration of symptoms was $8.7 {\pm}7.6$ years. DBS electrodes were placed under local anesthesia using microelectrode recording and stimulation. After $2.4{\pm}1.3$ days of trial tests, the stimulation device was implanted under general anesthesia. Patients were evaluated using the Burke-Fahn-Marsden Dystonia Rating Scale (BFMDRS). Results : BFMDRS total movement scores improved by 59.8%, 63.5%, 74.1%, 74.5%, and 85.5% during the immediate postoperative period of test stimulation, 3, 6, 12, and 24 months (n = 5) after surgery, respectively. The BFMDRS total movement scores were reduced gradually and the results reached statistical significance in the postoperative period (test period, p < 0.001; 3 months, p < 0.001; 6 months, p = 0.003; 12 months, p < 0.001; 24 months, p = 0.042). There was no statistical difference between 12 months and 24 months. BFM subscores improved by 63.3% for the eyes, 80.9% for the mouth, 68.4% for speech/swallowing, and 87.9% for the neck at 12 months after surgery. The adverse effects were insignificant. Conclusion : The bilateral GPi-DBS can be effective for the treatment of intractable Meige syndrome without significant side effects.

• Journal of Korean Neurosurgical Society
• /
• v.46 no.4
• /
• pp.346-350
• /
• 2009

Objective : The purpose of this study was to analyze in detail the relationship between outcome and time course of effect in medically refractory primary cervical dystonia (CD) with phasic type that was treated by bilateral globus pallidus internus (Gpi) deep brain stimulation (DBS). Methods : Six patients underwent bilateral implantation of DBS into the Gpi under the guide of microelectrode recording and were followed for $18.7{\pm}11.1$ months. The mean duration of the CD was $5.8{\pm}3.4$ years. The mean age at time of surgery was $54.2{\pm}10.2$ years. Patients were evaluated with the Toronto Western Spasmodic Torticollis Rating Scale (TWSTRS) and relief scale using patient self-reporting. Results : The TWSTRS total scores improved by 64.5%, 65.5%, 75.8%, and 76.0% at 3, 6, 12 months, and at the last available follow-up after surgery, respectively. Statistically significant improvements in the TWSTRS scores were observed 3 months after surgery (p=0.028) with gradual improvement up to 12 months after surgery, thereafter, the improvement was sustained. However, there was no statistically significant difference between the scores at 3 and 12 months. Subjective improvement reported averaged $81.7{\pm}6.8%$ at last follow-up. Mild dysarthria, the most frequent adverse event, occurred in 3 patients. Conclusions : Our results show that the bilateral Gpi-DBS can offer a significant therapeutic effect from 3 months postoperatively in patients with primary CD with phasic type, without significant side effects.

• Journal of Korean Neurosurgical Society
• /
• v.37 no.5
• /
• pp.325-328
• /
• 2005

Objective: Stereotactic thalamic procedure is well known to be a effective treatment for disabling upper limb tremor of essential tremor. However, the effect of this procedure for head tremor, which is midline symptom of that disease entity, has not been sufficiently established. The authors discuss the result of stereotactic thalamic operations for head tremor of their patients who suffered from essential tremor. Methods: We evaluated 4 patients of essential tremor who had head tremor combined with both upper limb tremor. One patient underwent unilateral ventralis intermedius thalamotomy, two patients had unilateral Vim deep brain stimulation(DBS) and one patient had unilateral Vim thalamotomy and contralateral DBS. Postoperative results of tremor were evaluated using our proposed scale. Results: Contralateral upper limb tremors to surgical side were markedly resolved in all patients but there was no meaningful effect for head tremor in 3 patients who underwent unilateral thalamic surgery. In a patient having simultaneously unilateral thalamotomy and contralateral DBS, remarkable improvement of head tremor was observed. Conclusion: Although it is difficult to evaluate the efficacy of thalamic surgery for axial symptom of essential tremor with a few cases, simultaneous unilateral thalamotomy and contralateral DBS would be expected to induce favorable outcomes for head tremor with significant economical advantages.

• Journal of Korean Neurosurgical Society
• /
• v.62 no.2
• /
• pp.166-174
• /
• 2019

Objective : Globus pallidus interna (GPi) is acknowledged as an essential treatment for advanced Parkinson's disease (PD). Nonetheless, the neurotransmitter study about its results is undiscovered. The goal of this research was to examine influences of entopeduncular nucleus (EPN) stimulation, identical to human GPi, in no-lesioned (NL) rat and 6-hydroxydopamine (6-HD)-lesioned rat on glutamate change in the striatum. Methods : Extracellular glutamate level changes in striatum of NL category, NL with deep brain stimulation (DBS) category, 6-HD category, and 6-HD with DBS category were examined using microdialysis and high-pressure liquid chromatography. Tyrosine hydroxylase (TH) immunoreactivities in substantia nigra and striatum of the four categories were also analyzed. Results : Extracellular glutamate levels in the striatum of NL with DBS category and 6-HD with DBS category were significantly increased by EPN stimulation compared to those in the NL category and 6-HD category. EPN stimulation had no significant effect on the expression of TH in NL or 6-HD category. Conclusion : Clinical results of GPi DBS are not only limited to direct inhibitory outflow to thalamus. They also include extensive alteration within basal ganglia.