• Korean Journal of Clinical Laboratory Science
• /
• v.56 no.2
• /
• pp.147-155
• /
• 2024

Gallium-68-prostate-specific membrane antigen-11 (⁶⁸Ga-PSMA-11) is a positron emission tomography radiopharmaceutical that labels a Glu-urea-Lys-based ligand with ⁶⁸Ga, binding specifically to the PSMA. It is used widely for imaging recurrent prostate cancer and metastases. On the other hand, the preparation and quality control testing of ⁶⁸Ga-PSMA-11 in medical institutions takes over 60 minutes, limiting the daily capacity of ⁶⁸Ge/⁶⁸Ga generators. While the generator provides 1,110 MBq (30 mCi) nominally, its activity decreases over time, and the labeling yield declines irregularly. Consequently, additional preparations are needed, increasing radiation exposure for medical technicians, prolonging patient wait times, and necessitating production schedule adjustments. This study aimed to reduce the ⁶⁸Ga-PSMA-11 preparation time and optimize the automated synthesis system. By shortening the reaction time between ⁶⁸Ga and the PSMA-11 precursor and adjusting the number of purification steps, a faster and more cost-effective method was tested while maintaining quality. The final synthesis time was reduced from 30 to 20 minutes, meeting the standards for the HEPES content, residual solvent EtOH content, and radiochemical purity. This optimized procedure minimizes radiation exposure for medical technicians, reduces patient wait times, and maintains consistent production schedules, making it suitable for clinical application.

• Journal of Wetlands Research
• /
• v.26 no.2
• /
• pp.147-159
• /
• 2024

Lack of streamflow observations makes model calibration difficult and limits model performance improvement. Satellite-based remote sensing products offer a new alternative as they can be actively utilized to obtain hydrological data. Recently, several studies have shown that artificial intelligence-based solutions are more appropriate than traditional conceptual and physical models. In this study, a data-driven approach combining various recurrent neural networks and decision tree-based algorithms is proposed, and the utilization of satellite remote sensing information for AI training is investigated. The satellite imagery used in this study is from MODIS and SMAP. The proposed approach is validated using publicly available data from 25 watersheds. Inspired by the traditional regionalization approach, a strategy is adopted to learn one data-driven model by integrating data from all basins, and the potential of the proposed approach is evaluated by using a leave-one-out cross-validation regionalization setting to predict streamflow from different basins with one model. The GRU + Light GBM model was found to be a suitable model combination for target basins and showed good streamflow prediction performance in ungauged basins (The average model efficiency coefficient for predicting daily streamflow in 25 ungauged basins is 0.7187) except for the period when streamflow is very small. The influence of satellite remote sensing information was found to be up to 10%, with the additional application of satellite information having a greater impact on streamflow prediction during low or dry seasons than during wet or normal seasons.

• Journal of The Korean Society of Inherited Metabolic disease
• /
• v.24 no.1
• /
• pp.26-36
• /
• 2024

Lesch-Nyhan syndrome (LNS) is an Clinical symptoms can range from mild to severe depending on residual enzyme activity and genetic mutations. In Korea, 27 cases of LNS have been reported. We report the results of an 11-year comparative follow-up of two cases of children who visited because of pink diapers, one who died from LNS with no residual enzymes and one case with partial residual enzymes. Case 1: During follow-up, seizures, developmental delay, and regression were observed. The boy experienced insomnia and severe constipation. He exhibited self-mutilating behavior, a grand mal seizure, scoliosis with severe spasticity, truncal hypotonia, choreoathetoid movement, and ataxia. After prolonged emaciation, staghorn calculi, and recurrent pneumonia, the patient died suddenly at the age of 11 years. Genetic testing revealed a hemizygous HPRT1 variant (c.151C>T (p.Arg51Ter)). Uric acid level was 10.5 mg/dL (normal range: ~3.5-7.9) and HPRT activity 0.02 nmol/hr/spot (10-23.8 nmol/hr/spot). Case 2: During follow-up, the patient remained underweight. He has normal intelligence attending primary school. Self-mutilation symptoms were not observed. Regular renal ultrasonography did not reveal urolithiasis. The patient had a hemizygous HPRT1 variant (c.35A>C (p.Asp12Ala)). Uric acid level and HPRT activity were 11 mg/dL and 0.56 nmol/hr/spot. Pink diapers after the neonatal period and severe protein aversion, neurological problems, and kidney stones, differentiation for LNS is necessary. When suspected, serum uric acid levels, HPRT enzyme activity, and molecular biological tests may be helpful in predicting the prognosis of LNS.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.95-108
• /
• 2017

Recently, AlphaGo which is Bakuk (Go) artificial intelligence program by Google DeepMind, had a huge victory against Lee Sedol. Many people thought that machines would not be able to win a man in Go games because the number of paths to make a one move is more than the number of atoms in the universe unlike chess, but the result was the opposite to what people predicted. After the match, artificial intelligence technology was focused as a core technology of the fourth industrial revolution and attracted attentions from various application domains. Especially, deep learning technique have been attracted as a core artificial intelligence technology used in the AlphaGo algorithm. The deep learning technique is already being applied to many problems. Especially, it shows good performance in image recognition field. In addition, it shows good performance in high dimensional data area such as voice, image and natural language, which was difficult to get good performance using existing machine learning techniques. However, in contrast, it is difficult to find deep leaning researches on traditional business data and structured data analysis. In this study, we tried to find out whether the deep learning techniques have been studied so far can be used not only for the recognition of high dimensional data but also for the binary classification problem of traditional business data analysis such as customer churn analysis, marketing response prediction, and default prediction. And we compare the performance of the deep learning techniques with that of traditional artificial neural network models. The experimental data in the paper is the telemarketing response data of a bank in Portugal. It has input variables such as age, occupation, loan status, and the number of previous telemarketing and has a binary target variable that records whether the customer intends to open an account or not. In this study, to evaluate the possibility of utilization of deep learning algorithms and techniques in binary classification problem, we compared the performance of various models using CNN, LSTM algorithm and dropout, which are widely used algorithms and techniques in deep learning, with that of MLP models which is a traditional artificial neural network model. However, since all the network design alternatives can not be tested due to the nature of the artificial neural network, the experiment was conducted based on restricted settings on the number of hidden layers, the number of neurons in the hidden layer, the number of output data (filters), and the application conditions of the dropout technique. The F1 Score was used to evaluate the performance of models to show how well the models work to classify the interesting class instead of the overall accuracy. The detail methods for applying each deep learning technique in the experiment is as follows. The CNN algorithm is a method that reads adjacent values from a specific value and recognizes the features, but it does not matter how close the distance of each business data field is because each field is usually independent. In this experiment, we set the filter size of the CNN algorithm as the number of fields to learn the whole characteristics of the data at once, and added a hidden layer to make decision based on the additional features. For the model having two LSTM layers, the input direction of the second layer is put in reversed position with first layer in order to reduce the influence from the position of each field. In the case of the dropout technique, we set the neurons to disappear with a probability of 0.5 for each hidden layer. The experimental results show that the predicted model with the highest F1 score was the CNN model using the dropout technique, and the next best model was the MLP model with two hidden layers using the dropout technique. In this study, we were able to get some findings as the experiment had proceeded. First, models using dropout techniques have a slightly more conservative prediction than those without dropout techniques, and it generally shows better performance in classification. Second, CNN models show better classification performance than MLP models. This is interesting because it has shown good performance in binary classification problems which it rarely have been applied to, as well as in the fields where it's effectiveness has been proven. Third, the LSTM algorithm seems to be unsuitable for binary classification problems because the training time is too long compared to the performance improvement. From these results, we can confirm that some of the deep learning algorithms can be applied to solve business binary classification problems.

• Radiation Oncology Journal
• /
• v.19 no.2
• /
• pp.87-94
• /
• 2001

Purpose : To evaluate the role of LINAC-based stereotactic radiosurgery (SRS) in the management of meningiomas, we reviewed clinical response, image response, neurological deficits for patients treated at our institution. Methods and materials : Between February 1995 and December 1999, twenty-six patients were treated with SRS. Seven patients had undergone prior resection. Nineteen patients received SRS as the initial treatment. There were 7 male and 19 female patients. The median age was 51 years (range, $14\~67\;years$). At least one clinical symptom presented at the time of SRS in 17 patients and cranial neuropathy was seen in 7 patients. The median tumor volume was $4.7\;cm^3\;(range,\;0.7\~16.5\;m^3)$. The mean marginal dose was 15 Gy (range, $10\~20\;Gy$), delivered to the $80\%$ isodose surface (range, $46\~90\%$). The median clinical and imaging follow-up periods were 27 months (range, 1-71 months) and 25 months (range, $1\~52\;months$), respectively. Results : Of 14 patients who had clinical follow-up of one year or longer, thirteen patients $(93\%)$ were improved clinically at follow-up examination. Clinical symptom worsened in one patient at 4 months after SRS as a result of intratumoral edema, who underwent surgical resection at 7 months. OF 14 patients who had radiologic follow-up of one year or longer, tumor volume decreased in 7 patients $(50\%)$ at a median of 11 months (range, $6\~25\;months$), remained stable in 6 patients $(43\%)$, and increased in one patient $(7\%)$, who underwent surgical resection at 44 months. New radiation-induced neurological deficits developed in six patients $(23\%)$. Five patients $(19\%)$ had transient neurological deficits, completely resolved by conservative treatment including steroid therapy. Radiation-induced brain necrosis developed in one patient $(3.8\%)$ at 9 months after SRS who followed by surgical resection of tumor and necrotic tissue. Conclusions : LINAC-based SRS proves to be an effective and safe management strategy for small to moderate sized meningiomas, inoperable, residual, and recurrent, but long-term follow-up will be necessary to fully evaluate its efficacy. To reduce the radiation-induced neurological deficit for large size meningioma and/or in the proximity of critical and neural structure, more delicate treatment planning and optimal decision of radiation dose will be necessary.

• Journal of Chest Surgery
• /
• v.36 no.12
• /
• pp.929-936
• /
• 2003

We analysed the surgical outcomes of immediate reoperations after mitral valve repair. Material and Method: Eighteen patients who underwent immediate reoperation for failed mitral valve repair from April 1995 through July 2001 were reviewed retrospectively. There were 13 female patients. The mitral valve disease was regurgitation (MR) in 12 patients, stenosis (MS) in 3, and mixed lesion in 3. The etiologies of the valve disease were rheumatic in 9 patients, degenerative in 8, and endocarditis in 1. The causes of reoperation was residual MR in 13 patients, residual MS in 4, and rupture of left ventricle in 1. Fourteen patients had rerepair for residual mitral lesions (77.8%) and four underwent replacement. Result: There was no early death. After mean follow-vp of 33 months, there was one late death. Echocardiography revealed no or grade 1 of MR (64.3%) in 9 patients and no or mild MS in 11 patients (78,6%). Reoperation was done in one patient. The cumulative survival and freedom from valve-related reoperation at 6 years were 94% and 90%, respectively. The cumulative freedom from recurrent MR and MS at 4 years were 56% and 44%, respectively. Conclusion: This study suggests that immediate reoperation for failed mitral valve repair offers good early and intermediate survival, and mitral valve rerepair can be successfully performed in most of patients. However, because mitral rerepair have high failure rate, especially in rheumatic valve disease, adequate selections of valvuloplasty technique and indication are important to reduce the failure rate of mitral rerepair.

• Journal of Chest Surgery
• /
• v.32 no.7
• /
• pp.621-627
• /
• 1999

Background: Sixty five cases with congenitally corrected transposition of the great arteries (CCTGA) indicated for biventricular repair were operated on between 1984 and september 1998. Comparison between the results of the conventional(classic) connection(LV-PA) and the anatomic repair was done. Material and Method: Retrospective review was carried out based on the medical records of the patients. Operative procedures, complications and the long-term results accoding to the combining anomalies were analysed. Result: Mean age was 5.5$\pm$4.8 years(range, 2 months to 18years). Thirty nine were male and 26 were female. Situs solitus {S,L,L} was in 53 and situs inversus{I,D,D} in 12. There was no left ventricular outflow tract obstruction(LVOTO) in 13(20%) cases. The LVOTO was resulted from pulmonary stenosis(PS) in 26(40%)patients and from pulmonary atresia(PA) in 26(40%) patients. Twenty-five(38.5%) patients had tricuspid valve regurgitation(TR) greater than the mild degree that was present preoperatively. Twenty two patients previously underwent 24 systemic- pulmonary shunts previously. In the 13 patients without LVOTO, 7 simple closure of VSD or ASD, 3 tricuspid valve replacements(TVR), and 3 anatomic corrections(3 double switch operations: 1 Senning+ Rastelli, 1 Senning+REV-type, and 1 Senning+Arterial switch opera tion) were performed. As to the 26 patients with CCTGA+VSD or ASD+LVOTO(PS), 24 classic repairs and 2 double switch operations(1 Senning+Rastelli, 1 Mustard+REV-type) were done. In the 26 cases with CCTGA+VSD+LVOTO(PA), 19 classic repairs(18 Rastelli, 1 REV-type), and 7 double switch operations(7 Senning+Rastelli) were done. The degree of tricuspid regurgitation increased during the follow-up periods from 1.3$\pm$1.4 to 2.2$\pm$1.0 in the classic repair group(p<0.05), but not in the double switch group. Two patients had complete AV block preoperatively, and additional 7(10.8%) had newly developed complete AV block after the operation. Other complications were recurrent LVOTO(10), thromboembolism(4), persistent chest tube drainage over 2 weeks(4), chylothorax(3), bleeding(3), acute renal failure(2), and mediastinitis(2). Mean follow-up was 54$\pm$49 months(0-177 months). Thirteen patients died after the operation(operative mortality rate: 20.0%(13/65)), and there were 3 additional deaths during the follow up period(overall mortality: 24.6%(16/65)). The operative mortality in patients underwent anatomic repair was 33.3%(4/12). The actuarial survival rates at 1, 5, and 10 years were 75.0$\pm$5.6%, 75.0$\pm$5.6%, and 69.2$\pm$7.6%. Common causes of death were low cardiac output syndrome(8) and heart failure from TR(5). Conclusion: Although our study could not demonstrate the superiority of each classic or anatomic repair, we found that the anatomic repair has a merit of preventing the deterioration of tricuspid valve regurgitations. Meticulous selection of the patients and longer follow-up terms are mandatory to establish the selective advantages of both strategies.

• Clinical and Experimental Reproductive Medicine
• /
• v.33 no.3
• /
• pp.179-187
• /
• 2006

Objectives: The risk of aneuploidies of embryos increases in advanced maternal age or parental karyotype abnormality and it results in poor reproductive outcomes such as recurrent spontaneous abortion (RSA) or repeated implantation failure (RIF). Preimplantation genetic diagnosis for aneuploidy screening (PGD-AS) can be applied for better ART outcome by selecting chromosomally normal embryos. The aim of this study is to evaluate the clinical outcome of PGD-AS and which group can get much benefit from PGD-AS among the patients expected to have poor reproductive outcome. Methods: In 42 patients, 77 PGD cycles were performed for aneuploidy screening. Patients were allocated to 3 groups according to the indication of PGD-AS: group I-patients with old age (${\geq}37$) and RIF more than 3 times (n=11, mean age=42.2 yrs.), group II-patients with RSA (${\geq}3$ times) associated with aneuploid pregnancy (n=19, mean age=38.9 yrs.), group III-parental sex chromosome abnormality or mosaicism (n=18, mean age=29.6 yrs.) including Turner syndrome, Klinefelter syndrome and 47, XYY. PGD was performed by using FISH for chromosome 13, 16, 18, 21, X and Y in group I and II, and chromosome X, Y and 18 (or 17) in group III. Results: Blastomere biopsy was successful in 530 embryos and FISH efficiency was 92.3%. The proportions of transferable embryos in each group were $32.5{\pm}17.5%$, $23.0{\pm}21.7%$ and $52.6{\pm}29.2%$ (mean ${\pm}$ SD), respectively, showing higher normal rate in group III (group II vs. III, p<0.05). The numbers of transferred embryos in each group were $3.9{\pm}1.5$, $1.9{\pm}1.1$ and $3.1{\pm}1.4$ (mean ${\pm}$ SD), respectively. The clinical pregnancy rates per transfer was 0%, 30.0% and 20.0%, and it was significantly higher in group II (group I vs. group II, p<0.05). The overall pregnancy rate per transfer was 19.6% (10/51) and the spontaneous abortion rate was 20% (2/10) of which karyotypes were euploid. Nine healthy babies (one twin pregnancy) were born with normal karyotype confirmed on amniocentesis. Conclusion: Our data suggests that PGD-AS provides advantages in patients with RSA associated with aneuploidy or sex chromosome abnormality, decreasing abortion rate and increasing ongoing pregnancy rate. It is not likely to be beneficial in RIF group due to other detrimental factors involved in implantation.

• Clinical and Experimental Pediatrics
• /
• v.48 no.7
• /
• pp.737-744
• /
• 2005

Purpose : Infants and children with cardiovascular diseases often present with respiratory symptoms. However, missed or delayed evaluation for potential airway problem may complicate overall prognosis. The aim of this study is to determine the clinical characteristics of these patients and explore the cause of airway problem. Methods : We reviewed the medical records of 64 patients(M : F=33:31, mean age : $6.3{\pm}7.5$ months) whose airway problems were proven by computed tomography or bronchoscopy in perioperative periods at the Asan Medical Center from January 1997 to June 2004. Patients were divided into two groups based on the duration of ventilator care : ${\leq}7$ days(group 1 : 23 cases, M : F=10 : 13) and >7 days(group 2 : 41 cases, M : F=23 : 18). Results : The patients in group 2 significantly developed more post-operative respiratory symptoms than group 1(P<0.001) and had more airway problems including extrinsic obstruction, intrinsic anomaly, and combined problem than group 1 although not significantly different(P=0.082). Among underlying diseases, the most common diseases were vascular anomaly(26.2 percent) and aortic arch anomaly(26.2 percent) in group 1 and pulmonary atresia with ventricular septal defect(22.4 percent) in group 2. The most frequent respiratory symptoms were recurrent wheezing pre-operatively and failure of ventilator weaning post-operatively. The major types of airway anomaly were tracheomalacia and tracheal stenosis(in each case 18.2 percent). Nineteen patients with persistent airway problems underwent aortopexy or other vascular correction. Of the 19 patients, 13(68.4 percent) were improved, but 2 failed in weaning ventilator and 4 died of non-airway problems. Conclusion : Early evaluation and treatment for potential airway problems may affect natural or surgical prognosis in patients with cardiovascular diseases presenting with respiratory symptoms.

• Tuberculosis and Respiratory Diseases
• /
• v.48 no.4
• /
• pp.428-437
• /
• 2000

Background : Five year survival rate of postoperative stage I non-small cell lung cancer(NSCLC) reaches to 66%. In the remaining one third of patients, however, cancer recurs and the overall survival of NSCLC remains dismal. To evaluate clinical and pathologic characteristics of recurred NSCLC, the patterns and factors for postoperative recurrence in patients with staged I and II NSCLC were studied. Method : A retrospective analysis was performed in 234 patients who underwent radical resection for pathologic stage I and II NSCLC. All patients who were followed up for at least one year were included in this study. Results : 1) There were 177 men and 57 women The median age was 63. The median duration of the follow up period was 732 days (range 365~1,695 days). The overall recurrence rate was 26.5%, and the recurrence occurred $358.8{\pm}239.8$ days after operation. 2) The ages of recurred NSCLC patients were higher ($63.2{\pm}8.8$ years) than those of non-recurred patients ($60.3{\pm}9.8$ years)(p=0.043). The recurrence rate was higher in stage II (46.9%) than in stage I (18.8%) NSCLC p<0.001. The size of primary lung mass was larger in recurred ($5.45{\pm}3.22\;cm$) than that of non-recurred NSCLC ($3.74{\pm}1.75\;cm$, p<0.001). Interestingly, there were no recurrent cases when the resected primary tumor was less than 2cm. 3) Distant recurrence was more frequent than locoregional recurrence (66.1% vs. 33.9%). Distant recurrence rate was higher in females and in cases of adenocarcinoma. Brain metastasis was more frequent in patients with adenocarcinoma than in those with squamous cell carcinoma (p=0.024). Conclusion: The tumor size and stage were two important factors for determining the possibility of a recurrence. Because distant brain metastasis was more frequent in patients with adenocarinoma, a prospective study should be conducted to evaluate the effectiveness of preoperative brain imaging.