• 대한원격탐사학회지
• /
• 제39권6_1호
• /
• pp.1371-1388
• /
• 2023

지구온난화로 인해 촉발된 기후변화가 홍수와 같은 수재해의 빈도와 규모를 증가시키며 국내 또한 장마와 집중호우로 인한 수재해가 증가하는 추세를 보인다. 이에 광범위한 수재해에 대해 효과적인 대응 및 기후 변화에 따른 선제적 대처가 필수적이며 이는 위성레이더 영상을 통해 가능하다. 본 연구에서는 Sentinel-1 위성 레이더 영상으로부터 국내 수체의 특성을 반영하기 위해 한강권역과 낙동강 권역의 일부 수체 영역에 대해 수체 학습 데이터셋 1,423장을 구축하였다. 정밀한 데이터 어노테이션(Annotation)을 위해 다양한 상황에 따른 구축 기준 문서를 작성한 뒤 진행하였다. 구축이 완료된 데이터셋을 딥러닝 모델 중 U-Net에 적용하여 수체 탐지 결과를 분석하였다. 최종적으로 학습된 모델을 학습과에 활용되지 않은 수체 영역에 적용하여 결과를 분석함으로써 전 국토 수체 모니터링의 가능성을 확인하였다. 분석 결과 구축된 수체 영역의 대해서는 F1-Score 0.987, Intersection over Union (IoU) 0.955의 높은 정확도로 수체를 탐지할 수 있었으며, 학습 및 평가에 활용되지 않은 다른 국내 수체 영역에 대해서도 동일하게 F1-Score 0.941, IoU 0.89의 높은 수체 탐지 결과를 나타냈다. 두 결과 모두 전반적으로 일부 그림자 영역과 폭이 좁은 하천에서 오류가 관찰되었으나, 그 외에는 정밀하게 수체를 탐지하였다. 이러한 연구 결과는 수재해 피해 규모 및 수자원 변화 모니터링에 중요한 기여를 할 것으로 기대된다. 추후 연구에서는 보다 다양한 수체 특성을 가진 데이터셋을 추가 구축한다면 오분류한 영역을 개선할 수 있을 것으로 기대되며, 전 국토의 수체를 효율적으로 관리 및 모니터링하는데 활용될 것으로 사료된다.

• Journal of Chest Surgery
• /
• 제57권2호
• /
• pp.128-135
• /
• 2024

Background: This retrospective study aimed to determine the treatment patterns and the surgical and oncologic outcomes after completion lobectomy (CL) in patients with locoregionally recurrent stage I non-small cell lung cancer (NSCLC) who previously underwent sublobar resection. Methods: Data from 36 patients who initially underwent sublobar resection for clinical, pathological stage IA NSCLC and experienced locoregional recurrence between 2008 and 2016 were analyzed. Results: Thirty-six (3.6%) of 1,003 patients who underwent sublobar resection for NSCLC experienced locoregional recurrence. The patients' median age was 66.5 (range, 44-77) years at the initial operation, and 28 (77.8%) patients were men. Six (16.7%) patients underwent segmentectomy and 30 (83.3%) underwent wedge resection as the initial operation. The median follow-up from the initial operation was 56 (range, 9-150) months. Ten (27.8%) patients underwent CL, 22 (61.1%) underwent non-surgical treatments (chemotherapy, radiation, concurrent chemoradiation therapy), and 4 (11.1%) did not receive treatment or were lost to follow-up after recurrence. Patients who underwent CL experienced no significant complications or deaths. The median follow-up time after CL was 64.5 (range, 19-93) months. The 5-year overall survival (OS) and post-recurrence survival (PRS) were higher in the surgical group than in the non-surgical (p<0.001) and no-treatment groups (p<0.001). Conclusion: CL is a technically demanding but safe procedure for locoregionally recurrent stage I NSCLC after sublobar resection. Patients who underwent CL had better OS and PRS than patients who underwent non-surgical treatments or no treatments; however, a larger cohort study and long-term surveillance are necessary.

• 터널과지하공간
• /
• 제34권3호
• /
• pp.208-217
• /
• 2024

AI영상 기반 건설현장 안전관리 모니터링 시스템 개발 및 적용하는 추세에 다양한 환경변화에 따른 위험 객체 탐지 딥러닝 모델 개발에 많은 연구적 관심이 쏟아지고 있다. 여러 환경 변화요인 중 저조도 조건에서 객체 검출 모델의 정확도는 현저히 감소하며, 저조도 환경을 고려한 학습을 수행하더라도 일관적인 객체 탐지 정확도를 확보할 수 없다. 이에 따라 저조도 영상을 강화하는 영상 전처리 기술의 필요성이 대두된다. 따라서, 본 논문은 취득된 건설 현장 영상 데이터를 활용하여 다양한 딥러닝 기반 저조도 영상 강화 모델(GLADNet, KinD, LLFlow, Zero-DCE)을 학습하고, 모델별 저조도 영상 강화 성능을 비교 검증실험을 진행하였다. 저조도 강화된 영상을 시각적으로 검증하였고, 영상품질 평가 지수(PSNR, SSIM, Delta-E)를 도입하여 정량적으로 분석하였다. 실험 결과, GLADNet의 저조도 영상 강화 성능이 정량·정성적 평가에서 우수한 결과를 보여줬으며, 저조도 영상 강화 모델로 적합한 것으로 분석되었다. 향후 딥러닝 기반 객체 검출 모델에 저조도 영상 강화 기법이 전처리 단계로 적용한다면, 저조도 환경에서 일관된 객체 검출 성능을 확보할 것으로 예상된다.

• Korean Journal of Radiology
• /
• 제23권10호
• /
• pp.949-958
• /
• 2022

Objective: To investigate the feasibility of using a deep learning-based analysis of auscultation data to predict significant stenosis of arteriovenous fistulas (AVF) in patients undergoing hemodialysis requiring percutaneous transluminal angioplasty (PTA). Materials and Methods: Forty patients (24 male and 16 female; median age, 62.5 years) with dysfunctional native AVF were prospectively recruited. Digital sounds from the AVF shunt were recorded using a wireless electronic stethoscope before (pre-PTA) and after PTA (post-PTA), and the audio files were subsequently converted to mel spectrograms, which were used to construct various deep convolutional neural network (DCNN) models (DenseNet201, EfficientNetB5, and ResNet50). The performance of these models for diagnosing ≥ 50% AVF stenosis was assessed and compared. The ground truth for the presence of ≥ 50% AVF stenosis was obtained using digital subtraction angiography. Gradient-weighted class activation mapping (Grad-CAM) was used to produce visual explanations for DCNN model decisions. Results: Eighty audio files were obtained from the 40 recruited patients and pooled for the study. Mel spectrograms of "pre-PTA" shunt sounds showed patterns corresponding to abnormal high-pitched bruits with systolic accentuation observed in patients with stenotic AVF. The ResNet50 and EfficientNetB5 models yielded an area under the receiver operating characteristic curve of 0.99 and 0.98, respectively, at optimized epochs for predicting ≥ 50% AVF stenosis. However, Grad-CAM heatmaps revealed that only ResNet50 highlighted areas relevant to AVF stenosis in the mel spectrogram. Conclusion: Mel spectrogram-based DCNN models, particularly ResNet50, successfully predicted the presence of significant AVF stenosis requiring PTA in this feasibility study and may potentially be used in AVF surveillance.

• Korean Journal of Radiology
• /
• 제23권2호
• /
• pp.159-171
• /
• 2022

Objective: This study aimed to investigate the impact of baseline values and temporal changes in body composition parameters, including skeletal muscle index (SMI) and visceral adipose tissue area (VAT), measured using serial computed tomography (CT) imaging on the prognosis of operable breast cancers in Asian patients. Materials and Methods: This study retrospectively included 627 Asian female (mean age ± standard deviation [SD], 53.6 ± 8.3 years) who underwent surgery for stage I-III breast cancer between January 2011 and September 2012. Body composition parameters, including SMI and VAT, were semi-automatically calculated on baseline abdominal CT at the time of diagnosis and follow-up CT for post-treatment surveillance. Serial changes in SMI and VAT were calculated as the delta values. Multivariable Cox regression analysis was used to evaluate the association of baseline and delta SMI and VAT values with disease-free survival. Results: Among 627 patients, 56 patients (9.2%) had breast cancer recurrence after a median of 40.5 months. The mean value ± SD of the baseline SMI and baseline VAT were 43.7 ± 5.8 cm²/m² and 72.0 ± 46.0 cm², respectively. The mean value of the delta SMI was -0.9 cm²/m² and the delta VAT was 0.5 cm². The baseline SMI and VAT were not significantly associated with disease-free survival (adjusted hazard ratio [HR], 0.983; 95% confidence interval [CI], 0.937-1.031; p = 0.475 and adjusted HR, 1.001; 95% CI, 0.995-1.006; p = 0.751, respectively). The delta SMI and VAT were also not significantly associated with disease-free survival (adjusted HR, 0.894; 95% CI, 0.766-1.043; p = 0.155 and adjusted HR, 1.001; 95% CI, 0.989-1.014; p = 0.848, respectively). Conclusion: Our study revealed that baseline and early temporal changes in SMI and VAT were not independent prognostic factors regarding disease-free survival in Asian patients undergoing surgery for breast cancer.

• Korean Journal of Radiology
• /
• 제23권12호
• /
• pp.1269-1280
• /
• 2022

Objective: This study aimed to evaluate the usefulness of quantitative indices obtained from deep learning analysis of gadoxetic acid-enhanced hepatobiliary phase (HBP) MRI and their longitudinal changes in predicting decompensation and death in patients with advanced chronic liver disease (ACLD). Materials and Methods: We included patients who underwent baseline and 1-year follow-up MRI from a prospective cohort that underwent gadoxetic acid-enhanced MRI for hepatocellular carcinoma surveillance between November 2011 and August 2012 at a tertiary medical center. Baseline liver condition was categorized as non-ACLD, compensated ACLD, and decompensated ACLD. The liver-to-spleen signal intensity ratio (LS-SIR) and liver-to-spleen volume ratio (LS-VR) were automatically measured on the HBP images using a deep learning algorithm, and their percentage changes at the 1-year follow-up (ΔLS-SIR and ΔLS-VR) were calculated. The associations of the MRI indices with hepatic decompensation and a composite endpoint of liver-related death or transplantation were evaluated using a competing risk analysis with multivariable Fine and Gray regression models, including baseline parameters alone and both baseline and follow-up parameters. Results: Our study included 280 patients (153 male; mean age ± standard deviation, 57 ± 7.95 years) with non-ACLD, compensated ACLD, and decompensated ACLD in 32, 186, and 62 patients, respectively. Patients were followed for 11-117 months (median, 104 months). In patients with compensated ACLD, baseline LS-SIR (sub-distribution hazard ratio [sHR], 0.81; p = 0.034) and LS-VR (sHR, 0.71; p = 0.01) were independently associated with hepatic decompensation. The ΔLS-VR (sHR, 0.54; p = 0.002) was predictive of hepatic decompensation after adjusting for baseline variables. ΔLS-VR was an independent predictor of liver-related death or transplantation in patients with compensated ACLD (sHR, 0.46; p = 0.026) and decompensated ACLD (sHR, 0.61; p = 0.023). Conclusion: MRI indices automatically derived from the deep learning analysis of gadoxetic acid-enhanced HBP MRI can be used as prognostic markers in patients with ACLD.

• 대한임상독성학회지
• /
• 제21권2호
• /
• pp.69-80
• /
• 2023

Purpose: Suicide ranks among the top causes of death among youth in South Korea. This study aimed to identify the characteristics of suicidal individuals treated at emergency departments between 2011 and 2020. Methods: A retrospective analysis was conducted using data from January 2011 to December 2020 in the Injury Surveillance Cohort, a prospective registry. Patients' sex, age, mortality, methods of self-harm, and previous suicide attempts were analyzed. The methods of self-harm were categorized into falls, asphyxiation, blunt injuries, penetrating injuries, poisoning, and others. Sub-groups with and without poisoning were compared. Results: The proportion of self-harm/suicide attempts increased from 2.3% (2011) to 5.0% (2020). The mortality rate decreased from 10.8% (2011) to 6.3% (2020). Poisoning was the most common method (61.7%). Mortality rates ranged from 42.0% for asphyxiation to 0.2% for blunt injuries. Individuals in their 20s showed a marked increase in suicide/self-harm attempts, especially in the last three years. A large proportion of decedents in their 70s or older (52.6%) used poisoning as a method of suicide. The percentage of individuals with two or more previous attempts rose from 7.1% (2011) to 19.7% (2020). The death rates by poisoning decreased from 7.7% (2011) to 2.5% (2020). Conclusion: Our findings underscore the urgent need for targeted interventions and suicide prevention policies. Managing and reducing suicide and self-harm in emergency settings will require a focus on poisoning, the 10-29 age group, and the elderly. This paper will be valuable for future policies aiming to reduce the societal burden of suicide and self-harm.

• 한국인터넷방송통신학회논문지
• /
• 제24권3호
• /
• pp.27-34
• /
• 2024

지하 공동구 화재 발생에 따른 직·간접적 피해는 사회 전반에 매우 큰 영향을 미치므로 이를 사전에 예방 및 관리하기 위한 노력이 필요하며, 이를 위해 지하 공동구를 대상으로 디지털 트윈 기술을 적용하여 화재 침수 등의 재난을 예방하는 연구가 진행 중이다. 각 센서로부터 감지된 신호를 플랫폼까지 전송하기 위해서는 네트워크 망이 필요하다. 본질적으로 지하 공동구 터널이 외부 무선 통신 시스템의 수신 범위가 부족하여 지하 공동구 환경에서 무선망을 적용하기 위한 분석이 필요하며, 지하 공동구 내에는 송, 배전 케이블로 인해 발생하는 전자기파 간섭, 내부의 구조물, 장애물 및 수도관 등의 금속 재질 관에서 발생하는 신호의 난반사 등으로 인해 무선 신호가 왜곡되거나 크기 감소가 발생할 수 있으므로 센싱을 통한 원격 감시, 모니터링 작업을 위한 실시간 연결을 보장하려면 지하 공동구 내에 무선 범위를 측정하고 분석해야 한다. 따라서 본 연구에서는 지하 공동구 내 무선 네트워크 환경을 구축하기 위해서 음영지역을 최소화고, 공동구 내부에서 무선환경 연결에 문제가 없도록 실제 공동구 환경을 측정하였으며, 지하 공동구 지형별 각 구간에 따른 데이터 전송속도 및 신호의 세기, 신호 대 잡음비를 분석하였다. 얻은 결과는 지하 공동구에서 무선 네트워크 설치를 위한 적절한 무선 계획 접근 방식을 제공한다.

• 상하수도학회지
• /
• 제37권5호
• /
• pp.261-269
• /
• 2023

In light of recent social concerns related to issues such as water supply pipe deterioration leading to problems like leaks and degraded water quality, the significance of maintenance efforts to enhance water source quality and ensure a stable water supply has grown substantially. In this study, scan statistic was applied to analyze water quality complaints and water leakage accidents from 2015 to 2021 to present a reasonable method to identify areas requiring improvement in water management. SaTScan, a spatio-temporal statistical analysis program, and ArcGIS were used for spatial information analysis, and clusters with high relative risk (RR) were determined using the maximum log-likelihood ratio, relative risk, and Monte Carlo hypothesis test for I city, the target area. Specifically, in the case of water quality complaints, the analysis results were compared by distinguishing cases occurring before and after the onset of "red water." The period between 2015 and 2019 revealed that preceding the occurrence of red water, the leak cluster at location L2 posed a significantly higher risk (RR: 2.45) than other regions. As for water quality complaints, cluster C2 exhibited a notably elevated RR (RR: 2.21) and appeared concentrated in areas D and S, respectively. On the other hand, post-red water incidents of water quality complaints were predominantly concentrated in area S. The analysis found that the locations of complaint clusters were similar to those of red water incidents. Of these, cluster C7 exhibited a substantial RR of 4.58, signifying more than a twofold increase compared to pre-incident levels. A kernel density map analysis was performed using GIS to identify priority areas for waterworks management based on the central location of clusters and complaint cluster RR data.

• 한국간담췌외과학회지
• /
• 제28권2호
• /
• pp.144-154
• /
• 2024

Backgrounds/Aims: Socioeconomic determinants of health are incompletely characterized in cholangiocarcinoma (CCA). We assessed how socioeconomic status influences initial treatment decisions and survival outcomes in patients with CCA, additionally performing multiple sub-analyses based on anatomic location of the primary tumor. Methods: Observational study using the 2018 submission of the Surveillance, Epidemiology, and End Results (SEER)-18 Database. In total, 5,476 patients from 2004-2015 with a CCA were separated based on median household income (MHI) into low income (< 25th percentile of MHI) and high income (> 25th percentile of MHI) groups. Seventy-three percent of patients had complete follow up data, and were included in survival analyses. Survival and treatment outcomes were calculated using R-studio. Results: When all cases of CCA were included, the high-income group was more likely than the low-income to receive surgery, chemotherapy, and local tumor destruction modalities. Initial treatment modality based on income differed significantly between tumor locations. Patients of lower income had higher overall and cancer-specific mortality at 2 and 5 years. Non-cancer mortality was similar between the groups. Survival differences identified in the overall cohort were maintained in the intrahepatic CCA subgroup. No differences between income groups were noted in cancer-specific or overall mortality for perihilar tumors, with variable differences in the distal cohort. Conclusions: Lower income was associated with higher rates of cancer-specific mortality and lower rates of surgical resection in CCA. There were significant differences in treatment selection and outcomes between intrahepatic, perihilar, and distal tumors. Population-based strategies aimed at identifying possible etiologies for these disparities are paramount to improving patient outcomes.