• 경영정보학연구
• /
• 제25권1호
• /
• pp.111-128
• /
• 2023

인공지능(AI) 기술이 발전함에 따라 빅데이터 기반의 상품 선호도 추정 개인화 추천시스템에 관심이 증가하고 있는 추세이다. 하지만 개인화 추천이 적합하지 않은 경우 고객의 구매 의사를 감소시키고 심지어 금융상품의 특성상 막대한 재무적 손실로 확대될 수 있는 위험을 가지고 있다. 따라서 고객의 특성과 상품 선호도를 포괄적으로 반영한 추천시스템을 개발하는 것이 비즈니스 성과 창출과 컴플라이언스 이슈 대응에 매우 중요하다. 특히 금융상품의 경우 개인의 투자성향과 리스크 회피도에 따라 고객의 상품 선호도가 구분되므로 축적된 고객 행동 데이터를 활용하여 맞춤형 추천서비스를 제안하는 것이 필요하다. 이러한 고객의 행동 특성과 거래 내역 데이터를 사용하는 것뿐만 아니라, 고객의 인구통계정보, 자산정보, 종목 보유 정보를 포함하여 추천 시스템의 콜드 스타트 문제를 해결하고자 한다. 따라서, 본 연구는 고객의 거래 로그 기록을 바탕으로 고객의 투자성향과 같은 특성 정보와 거래 내역 및 금융상품 정보를 통해 고객별 금융상품 잠재 선호도를 도출하여 딥러닝 기반의 협업 필터링을 제안한 모형이 가장 성능 우수한 것을 확인하였다. 본 연구는 고객의 금융 투자 메커니즘을 기반으로 금융상품 거래 데이터를 통해 미거래 금융상품에 대한 예상 선호를 도출하는 추천 모델을 구축하여, 선호가 높을 것으로 예상되는 상위 상품군을 추천하는 서비스를 개발하는 것에 의의가 있다.

• 대한영상의학회지
• /
• 제83권3호
• /
• pp.620-631
• /
• 2022

목적 유방암 환자의 수술 전 자기공명영상에서 림프절 전이를 시사하는 소견들에 따른 진단 성적을 알아보고자 한다. 대상과 방법 수술 전 유방 자기공명영상을 촬영하고 유방암 수술을 시행한 192명의 환자를 후향적으로 분석하였다. 영상 소견에서 림프절의 크기와 장경/단경의 비율, 피질의 두께와 모양, 변연, 수질의 소실, 비대칭성, T2 강조영상에서의 신호강도, 이른 조영증강의 정도, 조영증강의 역학을 조사하였다. 수신자판단특성곡선 분석, 카이 분석과 t-검정, 맥니마 검정을 이용하여 통계분석을 시행하였다. 결과 단경의 증가, 피질의 불규칙한 모양과 피질 두께의 증가, 수질의 소실, 비대칭성, 피질의 불규칙한 변연 그리고 T2 강조영상에서의 낮은 신호강도는 전이를 시사하는 의미 있는 소견이었다. 이중 단경과 피질의 두께에 대해 수신자판단특성곡선 분석으로 각각 8.05 mm와 2.75 mm로 절단값을 얻었다. 2.75 mm 이상의 피질 두께, 피질의 불규칙한 모양은 맥니마 검정으로 다른 소견들과 비교할 때 민감도의 유의한 차이를 보였다. 피질의 불규칙한 변연(100%)은 가장 높은 특이도를 보였다. 결론 유방 자기공명영상의 전이 림프절 분석에서 2.75 mm 이상의 피질 두께와 피질의 불규칙한 모양은 다른 소견들보다 높은 민감도를 보이고 피질의 불규칙한 변연은 가장 높은 특이도를 보이는 소견이다.

• 대한영상의학회지
• /
• 제82권1호
• /
• pp.116-127
• /
• 2021

목적 간 섬유화 단계 평가를 위한 회색조 초음파 영상 기반 텍스처 분석 측정 변수들의 진단적 유용성에 대해 평가한다. 대상과 방법 간 회색조 초음파 검사를 시행한 총 167명의 환자를 대상으로 하였다. 텍스처 분석은 한 명의 의사가 전용 소프트웨어를 이용하여 시행하였으며 3, 5, 6, 7, 8번 간 분절에 20픽셀에 해당하는 원형 관심 영역을 지정하여 측정하였다. 간 섬유화 정도에 대한 표준 품으로는 fibrosis-4 (이하 FIB-4 index)를 사용하였다. 산출된 텍스처 변수들과 간의 섬유화 정도의 비교는 t-검정과 Mann-Whitney U 검정을 사용하였으며, 진단적으로 유의한 변수들에 대하여 수신자 운영 특성 곡선의 곡선 하 면적(area under the receiver operating characteristic curve)으로 진단능을 평가하였다. 결과 연구에 포함된 환자는 정상군(FIB-4 < 1.45, n = 50), 경도(1.45 ≤ FIB-4 ≤ 2.35, n = 37), 중등도(2.35 < FIB-4 ≤ 3.25, n = 27)와 중증 간 섬유화군(FIB-4 > 3.25, n = 53)으로 구분되었다. 간의 5번 분절에서 왜도는 정상군과 경도군 사이에서 통계적으로 유의한 차이를 보였다(각각 0.2392 ± 0.3361, 0.4134 ± 0.3004, p = 0.0109). 정상군과 경도군을 구별하기 위한 왜도의 곡선 하 면적은 0.660 (95% confidence interval, 0.551-0.758) 이었으며, 추정 정확도, 민감도, 특이도는 각각 64%, 87%, 48%로 산출되었다. 결론 왜도는 5번 간 분절에서 정상군과 경도 섬유화군을 구분하는 데 유의한 차이를 보였다.

• Korean Journal of Radiology
• /
• 제24권6호
• /
• pp.541-552
• /
• 2023

Objective: Detection of pneumoperitoneum using abdominal radiography, particularly in the supine position, is often challenging. This study aimed to develop and externally validate a deep learning model for the detection of pneumoperitoneum using supine and erect abdominal radiography. Materials and Methods: A model that can utilize "pneumoperitoneum" and "non-pneumoperitoneum" classes was developed through knowledge distillation. To train the proposed model with limited training data and weak labels, it was trained using a recently proposed semi-supervised learning method called distillation for self-supervised and self-train learning (DISTL), which leverages the Vision Transformer. The proposed model was first pre-trained with chest radiographs to utilize common knowledge between modalities, fine-tuned, and self-trained on labeled and unlabeled abdominal radiographs. The proposed model was trained using data from supine and erect abdominal radiographs. In total, 191212 chest radiographs (CheXpert data) were used for pre-training, and 5518 labeled and 16671 unlabeled abdominal radiographs were used for fine-tuning and self-supervised learning, respectively. The proposed model was internally validated on 389 abdominal radiographs and externally validated on 475 and 798 abdominal radiographs from the two institutions. We evaluated the performance in diagnosing pneumoperitoneum using the area under the receiver operating characteristic curve (AUC) and compared it with that of radiologists. Results: In the internal validation, the proposed model had an AUC, sensitivity, and specificity of 0.881, 85.4%, and 73.3% and 0.968, 91.1, and 95.0 for supine and erect positions, respectively. In the external validation at the two institutions, the AUCs were 0.835 and 0.852 for the supine position and 0.909 and 0.944 for the erect position. In the reader study, the readers' performances improved with the assistance of the proposed model. Conclusion: The proposed model trained with the DISTL method can accurately detect pneumoperitoneum on abdominal radiography in both the supine and erect positions.

• Korean Journal of Radiology
• /
• 제24권5호
• /
• pp.465-475
• /
• 2023

Objective: To evaluate the feasibility of ultrasound shear wave elastography (SWE) for predicting hepatic fibrosis and native liver outcomes in patients with biliary atresia. Materials and Methods: This prospective study included 33 consecutive patients with biliary atresia (median age, 8 weeks [interquartile range, 6-10 weeks]; male:female ratio, 15:18) from Severance Children's Hospital between May 2019 and February 2022. Preoperative (within 1 week from surgery) and immediate postoperative (on postoperative days [PODs] 3, 5, and 7) ultrasonographic findings were obtained and analyzed, including the SWE of the liver and spleen. Hepatic fibrosis, according to the METAVIR score at the time of Kasai portoenterostomy and native liver outcomes during postsurgical follow-up, were compared and correlated with imaging and laboratory findings. Poor outcomes were defined as intractable cholangitis or liver transplantation. The diagnostic performance of SWE in predicting METAVIR F3-F4 and poor hepatic outcomes was analyzed using receiver operating characteristic (ROC) analyses. Results: All patients were analyzed without exclusion. Perioperative advanced hepatic fibrosis (F3-F4) was associated with older age and higher preoperative direct bilirubin and SWE values in the liver and spleen. Preoperative liver SWE showed a ROC area of 0.806 and 63.6% (7/11) sensitivity and 86.4% (19/22) specificity at a cutoff of 17.5 kPa for diagnosing F3-F4. The poor outcome group included five patients with intractable cholangitis and three undergoing liver transplantation who showed high postoperative liver SWE values. Liver SWE on PODs 3-7 showed ROC areas of 0.783-0.891 for predicting poor outcomes, and a cutoff value of 10.3 kPa for SWE on POD 3 had 100% (8/8) sensitivity and 73.9% (17/23) specificity. Conclusion: Preoperative liver SWE can predict advanced hepatic fibrosis, and immediate postoperative liver SWE can predict poor native liver outcomes in patients with biliary atresia.

• Korean Journal of Radiology
• /
• 제24권5호
• /
• pp.395-405
• /
• 2023

Objective: This study aimed to develop and validate models using radiomics features on a native T1 map from cardiac magnetic resonance (CMR) to predict left ventricular reverse remodeling (LVRR) in patients with nonischemic dilated cardiomyopathy (NIDCM). Materials and Methods: Data from 274 patients with NIDCM who underwent CMR imaging with T1 mapping at Severance Hospital between April 2012 and December 2018 were retrospectively reviewed. Radiomic features were extracted from the native T1 maps. LVRR was determined using echocardiography performed ≥ 180 days after the CMR. The radiomics score was generated using the least absolute shrinkage and selection operator logistic regression models. Clinical, clinical + late gadolinium enhancement (LGE), clinical + radiomics, and clinical + LGE + radiomics models were built using a logistic regression method to predict LVRR. For internal validation of the result, bootstrap validation with 1000 resampling iterations was performed, and the optimism-corrected area under the receiver operating characteristic curve (AUC) with 95% confidence interval (CI) was computed. Model performance was compared using AUC with the DeLong test and bootstrap. Results: Among 274 patients, 123 (44.9%) were classified as LVRR-positive and 151 (55.1%) as LVRR-negative. The optimism-corrected AUC of the radiomics model in internal validation with bootstrapping was 0.753 (95% CI, 0.698-0.813). The clinical + radiomics model revealed a higher optimism-corrected AUC than that of the clinical + LGE model (0.794 vs. 0.716; difference, 0.078 [99% CI, 0.003-0.151]). The clinical + LGE + radiomics model significantly improved the prediction of LVRR compared with the clinical + LGE model (optimism-corrected AUC of 0.811 vs. 0.716; difference, 0.095 [99% CI, 0.022-0.139]). Conclusion: The radiomic characteristics extracted from a non-enhanced T1 map may improve the prediction of LVRR and offer added value over traditional LGE in patients with NIDCM. Additional external validation research is required.

• Korean Journal of Radiology
• /
• 제24권2호
• /
• pp.133-144
• /
• 2023

Objective: Cyclin-dependent kinase inhibitor (CDKN)2A/B homozygous deletion is a key molecular marker of isocitrate dehydrogenase (IDH)-mutant astrocytomas in the 2021 World Health Organization. We aimed to investigate whether qualitative and quantitative MRI parameters can predict CDKN2A/B homozygous deletion status in IDH-mutant astrocytomas. Materials and Methods: Preoperative MRI data of 88 patients (mean age ± standard deviation, 42.0 ± 11.9 years; 40 females and 48 males) with IDH-mutant astrocytomas (76 without and 12 with CDKN2A/B homozygous deletion) from two institutions were included. A qualitative imaging assessment was performed. Mean apparent diffusion coefficient (ADC), 5th percentile of ADC, mean normalized cerebral blood volume (nCBV), and 95th percentile of nCBV were assessed via automatic tumor segmentation. Logistic regression was performed to determine the factors associated with CDKN2A/B homozygous deletion in all 88 patients and a subgroup of 47 patients with histological grades 3 and 4. The discrimination performance of the logistic regression models was evaluated using the area under the receiver operating characteristic curve (AUC). Results: In multivariable analysis of all patients, infiltrative pattern (odds ratio [OR] = 4.25, p = 0.034), maximal diameter (OR = 1.07, p = 0.013), and 95th percentile of nCBV (OR = 1.34, p = 0.049) were independent predictors of CDKN2A/B homozygous deletion. The AUC, accuracy, sensitivity, and specificity of the corresponding model were 0.83 (95% confidence interval [CI], 0.72-0.91), 90.4%, 83.3%, and 75.0%, respectively. On multivariable analysis of the subgroup with histological grades 3 and 4, infiltrative pattern (OR = 10.39, p = 0.012) and 95th percentile of nCBV (OR = 1.24, p = 0.047) were independent predictors of CDKN2A/B homozygous deletion, with an AUC accuracy, sensitivity, and specificity of the corresponding model of 0.76 (95% CI, 0.60-0.88), 87.8%, 80.0%, and 58.1%, respectively. Conclusion: The presence of an infiltrative pattern, larger maximal diameter, and higher 95th percentile of the nCBV may be useful MRI biomarkers for CDKN2A/B homozygous deletion in IDH-mutant astrocytomas.

• Korean Journal of Radiology
• /
• 제23권8호
• /
• pp.811-820
• /
• 2022

Objective: To develop a model incorporating radiomic features and clinical factors to accurately predict acute ischemic stroke (AIS) outcomes. Materials and Methods: Data from 522 AIS patients (382 male [73.2%]; mean age ± standard deviation, 58.9 ± 11.5 years) were randomly divided into the training (n = 311) and validation cohorts (n = 211). According to the modified Rankin Scale (mRS) at 6 months after hospital discharge, prognosis was dichotomized into good (mRS ≤ 2) and poor (mRS > 2); 1310 radiomics features were extracted from diffusion-weighted imaging and apparent diffusion coefficient maps. The minimum redundancy maximum relevance algorithm and the least absolute shrinkage and selection operator logistic regression method were implemented to select the features and establish a radiomics model. Univariable and multivariable logistic regression analyses were performed to identify the clinical factors and construct a clinical model. Ultimately, a multivariable logistic regression analysis incorporating independent clinical factors and radiomics score was implemented to establish the final combined prediction model using a backward step-down selection procedure, and a clinical-radiomics nomogram was developed. The models were evaluated using calibration, receiver operating characteristic (ROC), and decision curve analyses. Results: Age, sex, stroke history, diabetes, baseline mRS, baseline National Institutes of Health Stroke Scale score, and radiomics score were independent predictors of AIS outcomes. The area under the ROC curve of the clinical-radiomics model was 0.868 (95% confidence interval, 0.825-0.910) in the training cohort and 0.890 (0.844-0.936) in the validation cohort, which was significantly larger than that of the clinical or radiomics models. The clinical radiomics nomogram was well calibrated (p > 0.05). The decision curve analysis indicated its clinical usefulness. Conclusion: The clinical-radiomics model outperformed individual clinical or radiomics models and achieved satisfactory performance in predicting AIS outcomes.

• 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
• /
• 제23권10호
• /
• pp.986-997
• /
• 2022

Objective: Whether metabolic redistribution occurs in patients with white matter hyperintensities (WMHs) on magnetic resonance imaging (MRI) is unknown. This study aimed 1) to propose a measure of the brain metabolic network for an individual patient and preliminarily apply it to identify impaired metabolic networks in patients with WMHs, and 2) to explore the clinical and imaging features of metabolic redistribution in patients with WMHs. Materials and Methods: This study included 50 patients with WMHs and 70 healthy controls (HCs) who underwent ¹⁸F-fluorodeoxyglucose-positron emission tomography/MRI. Various global property parameters according to graph theory and an individual parameter of brain metabolic network called "individual contribution index" were obtained. Parameter values were compared between the WMH and HC groups. The performance of the parameters in discriminating between the two groups was assessed using the area under the receiver operating characteristic curve (AUC). The correlation between the individual contribution index and Fazekas score was assessed, and the interaction between age and individual contribution index was determined. A generalized linear model was fitted with the individual contribution index as the dependent variable and the mean standardized uptake value (SUV_mean) of nodes in the whole-brain network or seven classic functional networks as independent variables to determine their association. Results: The means ± standard deviations of the individual contribution index were (0.697 ± 10.9) × 10^-3 and (0.0967 ± 0.0545) × 10^-3 in the WMH and HC groups, respectively (p < 0.001). The AUC of the individual contribution index was 0.864 (95% confidence interval, 0.785-0.943). A positive correlation was identified between the individual contribution index and the Fazekas scores in patients with WMHs (r = 0.57, p < 0.001). Age and individual contribution index demonstrated a significant interaction effect on the Fazekas score. A significant direct association was observed between the individual contribution index and the SUV_mean of the limbic network (p < 0.001). Conclusion: The individual contribution index may demonstrate the redistribution of the brain metabolic network in patients with WMHs.