• Korean Journal of Radiology
• /
• 제23권3호
• /
• pp.343-354
• /
• 2022

Objective: To develop and evaluate a deep learning-based artificial intelligence (AI) model for detecting skull fractures on plain radiographs in children. Materials and Methods: This retrospective multi-center study consisted of a development dataset acquired from two hospitals (n = 149 and 264) and an external test set (n = 95) from a third hospital. Datasets included children with head trauma who underwent both skull radiography and cranial computed tomography (CT). The development dataset was split into training, tuning, and internal test sets in a ratio of 7:1:2. The reference standard for skull fracture was cranial CT. Two radiology residents, a pediatric radiologist, and two emergency physicians participated in a two-session observer study on an external test set with and without AI assistance. We obtained the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity along with their 95% confidence intervals (CIs). Results: The AI model showed an AUROC of 0.922 (95% CI, 0.842-0.969) in the internal test set and 0.870 (95% CI, 0.785-0.930) in the external test set. The model had a sensitivity of 81.1% (95% CI, 64.8%-92.0%) and specificity of 91.3% (95% CI, 79.2%-97.6%) for the internal test set and 78.9% (95% CI, 54.4%-93.9%) and 88.2% (95% CI, 78.7%-94.4%), respectively, for the external test set. With the model's assistance, significant AUROC improvement was observed in radiology residents (pooled results) and emergency physicians (pooled results) with the difference from reading without AI assistance of 0.094 (95% CI, 0.020-0.168; p = 0.012) and 0.069 (95% CI, 0.002-0.136; p = 0.043), respectively, but not in the pediatric radiologist with the difference of 0.008 (95% CI, -0.074-0.090; p = 0.850). Conclusion: A deep learning-based AI model improved the performance of inexperienced radiologists and emergency physicians in diagnosing pediatric skull fractures on plain radiographs.

• Archives of Plastic Surgery
• /
• 제51권2호
• /
• pp.251-257
• /
• 2024

Background Plastic surgery has developed to benefit in a variety of challenging areas formerly handled by other disciplines. Medical students do not have a clear picture of plastic surgery as a career due to lacking scope, clinical practice, and understanding of plastic surgery as a clinical area of expertise, including general practitioners, nursing staff, medical trainees, and the general public, and misconceptions about the extent of reconstructive and plastic surgery. Methods A cross-sectional observational study was conducted on Kuwait University Medical students (2nd-7th Years) over a period of 1 month. A questionnaire and a consent form were provided to eligible students. The inclusion criteria were Kuwait University Medical students from 2nd to 7th Years with signed consent form. The response was collected via email sent in coordination with the Vice Dean of Student Affairs in the Faculty of Medicine. Using statistical package for the social sciences, responses were statistically analyzed. Pearson's chi-square test was used to calculate p-values, where p < 0.05 was considered statistically significant. Results A total of 244 eligible medical students, 121 males and 123 females, were included in the study, with a mean age of 21 (±2) years. Similarly, 126 (51.6%) were preclinical students (2nd-4th-year students), while 118 (48.4%) were clinical students (5th-7th-year students). About 79.8% of medical students believed that plastic surgery plays an essential role in trauma management, whereas 9.2% did not consider plastic surgery significant for trauma management. This study found that only 15.5% of medical students were interested in enrolling in plastic surgery residency after graduation, while 47.1% of students did not consider plastic surgery residency after graduation. However, 37.4% were uncertain. The two most driving factors in deciding on plastic surgery residency were expected income (61.8%) and lifestyle (14.3%). Conclusion Improving medical students' education quality can enhance their perception and awareness of plastic surgery. Students should be taught the broader scope of plastic surgery. The inclusion of formal training during undergraduation is the essence of time and should be added to or improved during plastic surgery rotations with more emphasis on reconstructive and hand/peripheral nerve surgery. Student-led interest groups can be a useful tool for educating students about their specialty.

• Korean Journal of Radiology
• /
• 제20권4호
• /
• pp.631-640
• /
• 2019

Objective: To evaluate the value of airway computed tomography (CT) in patients with obstructive sleep apnea (OSA) as a predictor of cerebrocardiovascular disease (CCVD) clinically, by quantitatively analyzing carotid arterial calcification (CarAC). Materials and Methods: This study included 287 patients aged 40-80 years, who had undergone both polysomnography (PSG) and airway CT between March 2011 and October 2015. The carotid arterial calcium score (CarACS) was quantified using the modified Agatston method on each upper airway CT. The OSA severity was categorized as normal, mild, moderate, and severe using the PSG results. Clinical characteristics, comorbid diseases, and lipid profiles of all patients were analyzed, and the prevalence of CCVDs was investigated during the follow up period (52.2 ± 16.0 months). Results: CCVD occurred in 27 patients (9.3%) at the end of follow-up, and the CCVD-present groups showed a significantly older mean age (57.5 years vs. 54.2 years), higher prevalence of hypertension (59% vs. 34%) and CarAC (51.9% vs. 20.8%), whereas sex, other comorbid diseases, and severity of OSA were not significantly different from the CCVD-absent group. A univariate analysis showed that age, hypertension, incidence of CarAC, and CarACS were risk factors for the occurrence of CCVD events. In a multivariate analysis, the incidence of CarAC was the only independent risk factor for CCVD. Conclusion: CarAC is an independent risk factor for CCVD, whereas the severity of OSA is not a contributory risk factor in patients with OSA. Therefore, additional analysis of CarACS based on airway CT scans may be useful for predicting CCVD.

• Korean Journal of Radiology
• /
• 제2권2호
• /
• pp.63-67
• /
• 2001

Objective: Atrophy and a high T2 signal of the hippocampus are known to be the principal MR imaging findings of hippocampal sclerosis. The purpose of this study was to determine whether or not individual MRI findings correlate with surgical outcome in patients with this condition. Materials and Methods: Preoperative MR imaging findings in 57 consecutive patients with pathologically-proven hippocampal sclerosis who underwent anterior temporal lobectomy and were followed-up for 24 months or more were retrospectively reviewed, and the results were compared with the postsurgical outcome (Engel classification). The MR images included routine sagittal T1-weighted and axial T2-weighted spin-echo images, and oblique coronal T1-weighted 3D gradient-echo and T2-weighted 2D fast spin-echo images obtained on either a 1.5 T or 1.0 T unit. The images were visually evaluated by two neuroradiologists blinded to the outcome; their focus was the presence or absence of atrophy and a high T2 hippocampal signal. Results: Hippocampal atrophy was seen in 96% of cases (55/57) [100% (53/53) of the good outcome group (Engel class I and II), and 50% (2/4) of the poor outcome group (class III and IV)]. A high T2 hippocampal signal was seen in 61% of cases (35/57) [62% (33/53) of the good outcome group and 50% (2/4) of the poor outcome group]. All 35 patients with a high T2 signal had hippocampal atrophy. 'Normal' hippocampus, as revealed by MR imaging, occurred in 4% of patients (2/57), both of whom showed a poor outcome (Engel class III). The presence or absence of hippocampal atrophy correlated well with surgical outcome (p<0.01). High T2 signal intensity did not, however, significantly correlate with surgical outcome (p>0.05). Conclusion: Compared with a high T2 hippocampal signal, hippocampal atrophy is more common and correlates better with surgical outcome. For the prediction of this, it thus appears to be the more useful indicator.

• 말소리와 음성과학
• /
• 제16권1호
• /
• pp.57-65
• /
• 2024

정상압 수두증(normal pressure hydrocephalus, NPH)은 뇌의 뇌척수압은 정상 범위에 있지만 뇌척수액이 정상 수준보다 증가해 뇌실확장증을 유발하는 질환으로, 조음기관의 운동성과 범위가 감소해 조음교대운동(diadochokinesis, DDK)과 말명료도에 영향을 줄 수 있다. 본 연구에서는 NPH 환자 38명과 정상 노인 38명을 대상으로 /파/, /타/, /카/ 및 /파타카/에 대한 DDK 과제를 실시한 후, 정확한 산출만 측정한 DDK(accurate token-DDK)와 부정확한 산출 포함, 모든 산출시도를 측정한 DDK(all token-DDK)의 두 방법을 모두 사용해 그 결과를 비교하였다. 또한 DDK가 NPH와 정상 노인의 두 집단을 얼마나 정확하게 분류 가능한지, 그리고 DDK와 말명료도 간 상관관계는 어떠한지에 대해서도 알아보았다. 연구결과, NPH 집단과 정상 노인 집단 간에는 accurate token-DDK와 all token-DDK 모두에서 유의한 차이가 있었고, 집단 분류정확도는 accurate token-DDK의 경우 75.0%, all token-DDK의 경우 77.6%로 비교적 높았다. 그러나 NPH 집단에서 DDK 속도와 말명료도 측정값 간에는 유의한 상관관계가 없었다. 본 연구는 NPH 환자의 말운동능력을 민감하게 평가하는 데에 DDK가 유용한 방법임을 시사한다.

• 대한영상의학회지
• /
• 제84권4호
• /
• pp.970-976
• /
• 2023

29세 남성에서의 미만성 연수막성 신경교종을 증례 보고한다. 이 질환은 드문 중추신경계 종양으로, 대부분 소아에서 발견되며 성인에서는 소수만 보고되어 있다. 본 환자는 만성 두통으로 내원하여 MRI를 시행하였다. 뇌 MRI에서 경도의 수두증과 다수의 테두리 조영증강을 보이는 병변이 안장위 수조에서 보였으며, FLAIR에서 신호가 억제되지 않는 다수의 비조영증강 낭종성 병변이 양측 기저핵, 시상 및 대뇌에서 관찰되었다. 척추 MRI에서는 요추 및 천추부위의 미만성 연수막 조영증강이 보였다. 생식세포종양의 연수막 파종을 의심하였고 경접형골 종양제거술을 시행 받았다. 병리학 검사에서 미만성 연수막성 신경교종으로 확진되었고, 차세대 염기서열 검사에서 FGFR1 유전자의 돌연변이가 발견되었다. 결론적으로 연수막 결절성 조영증강과 FLAIR에서 신호가 억제되지 않는 다수의 비조영증강 낭종성 뇌 병변이 함께 관찰될 경우 연수막 조영증강을 보이는 여러 다른 질환들과의 감별 진단에 도움이 된다.

• 대한영상의학회지
• /
• 제85권1호
• /
• pp.3-23
• /
• 2024

임상에서 자주 접하게 되는 추간판탈출증 중 분리추간판은 추간판의 성분이 원래의 수질핵과 완전히 분리되는 특별한 경우를 의미한다. 이러한 분리추간판은 척추관 내부뿐만 아니라 외부에도 위치할 수 있으며, 주변 구조물에 압력을 가하거나 신경 경로를 압박하게 되고 이로 인해 다양한 임상 증상을 유발할 수 있다. 특히 경막 내에 위치한 분리추간판의 경우, 경막절개술을 통해서만 병변을 식별할 수 있다. 따라서 수술 전에 분리추간판의 정확한 위치와 범위를 파악하는 것은 수술 계획을 세우는 데 중요하다. 자기공명영상에서 분리추간판은 초기에는 모체 추간판과 유사한 신호강도를 보이지만 이후 독립적인 퇴행 변화를 거치며 신호강도가 달라질 수 있다. 또한 대부분의 분리추간판 조각은 염증 반응의 결과로 인해 인접한 혈관발생과 육아조직의 형성 정도에 따라 다양한 정도의 주변 조영증강을 보일 수 있다. 이종설에서는 분리추간판의 다양한 영상 소견과 위치를 소개하여 환자에게 정확한 진단과 적절한 치료 방향을 제시하는 데 도움이 되고자 한다.

• Journal of Cerebrovascular and Endovascular Neurosurgery
• /
• 제26권2호
• /
• pp.152-162
• /
• 2024

Objective: Stroke is the second-leading cause of death globally. Intracranial atherosclerotic stenosis (ICAS) represents 10-15% of ischemic strokes in Western countries and up to 47% in Asian countries. Patients with ICAS have an especially high risk of stroke recurrence. The aim of this meta-analysis is to reassess recurrent stroke, transient ischemic attack (TIA), and other outcomes with stenting versus best medical management for symptomatic ICAS. Methods: The search protocol was developed a priori according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The OVID Medline, Embase, Web of Science, and Cochrane Library databases were searched from inception to August 14th, 2022. Results: This meta-analysis included four randomized controlled trials (RCTs), with a total number of 991 patients. The mean age of participants was 57 years. The total number of intracranial stenting patients was 495, and the number of medical treatment patients was 496. The included studies were published between 2011 and 2022. Two studies were conducted in the USA, and the other two in China. All included studies compared intracranial stenting to medical treatment for ICAS. Conclusions: In patients with ischemic stroke due to symptomatic severe intracranial atherosclerosis, the rate of 30-day ischemic stroke, 30-day intracerebral hemorrhage, one-year stroke in territory or mortality favored the medical treatment alone without intracranial stenting. The risk of same-territory stroke at last follow-up, disabling stroke at last follow-up, and mortality did not significantly favor either group. Intracranial stenting for atherosclerosis did not result in significant benefit over medical treatment.

• Journal of Trauma and Injury
• /
• 제37권3호
• /
• pp.201-208
• /
• 2024

Purpose: The number of elderly patients with trauma is increasing; therefore, precise models are necessary to estimate the mortality risk of elderly patients with trauma for informed clinical decision-making. This study aimed to develop machine learning based predictive models that predict 30-day mortality in severely injured elderly patients with trauma and to compare the predictive performance of various machine learning models. Methods: This study targeted patients aged ≥65 years with an Injury Severity Score of ≥15 who visited the regional trauma center at Chungbuk National University Hospital between 2016 and 2022. Four machine learning models-logistic regression, decision tree, random forest, and eXtreme Gradient Boosting (XGBoost)-were developed to predict 30-day mortality. The models' performance was compared using metrics such as area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, specificity, F1 score, as well as Shapley Additive Explanations (SHAP) values and learning curves. Results: The performance evaluation of the machine learning models for predicting mortality in severely injured elderly patients with trauma showed AUC values for logistic regression, decision tree, random forest, and XGBoost of 0.938, 0.863, 0.919, and 0.934, respectively. Among the four models, XGBoost demonstrated superior accuracy, precision, recall, specificity, and F1 score of 0.91, 0.72, 0.86, 0.92, and 0.78, respectively. Analysis of important features of XGBoost using SHAP revealed associations such as a high Glasgow Coma Scale negatively impacting mortality probability, while higher counts of transfused red blood cells were positively correlated with mortality probability. The learning curves indicated increased generalization and robustness as training examples increased. Conclusions: We showed that machine learning models, especially XGBoost, can be used to predict 30-day mortality in severely injured elderly patients with trauma. Prognostic tools utilizing these models are helpful for physicians to evaluate the risk of mortality in elderly patients with severe trauma.

• Nuclear Medicine and Molecular Imaging
• /
• 제42권1호
• /
• pp.8-16
• /
• 2008

목적: 내경동맥 또는 중대뇌동맥의 죽상 동맥 경화증 환자에서의 두개외강-내강 우회로술(이하 우회로술) 후의 연속적인 혈류 역학적 변화를 $^{99m}Tc$-ECD 아세타졸아마이드 부하 뇌혈류 단일 광자 방출 전산화 단층 촬영(이하 아세타졸아마이드 부하 SPECT)으로 평가하여 중대뇌 동맥의 각 분지별 영역에 대한 우회로술의 혈류역학적 개선효과를 알아보고자 하였다. 대상 및 방법: 전향적 방법으로 최근 3개월 내에 혈관 폐색성 징후가 발생하여 우회로술을 시행받은 환자를 대상으로 수술 전과 수술 1 주 후, 3-6 개월 후에 아세타졸아마이드 부하 SPECT를 시행하였다. 영상 분석을 위해 SPM의 SPECT 표준 뇌에 공간 정규화한 후 Anatomical Automated Labeling으로 중대뇌동맥의 지배를 받는 양측 전두, 측두, 두정 영역에 관심 구역을 설정하여 각 관심 영역별로 뇌혈류 지표(PI; $C_{region}/C_{ipsilateral\;cerebellum}$) 및 뇌혈관 예비능 지표$((PI_{acetazolamide}-PI_{basal})/PI_{basal})$로 정하여 이들 지표의 수술 전후 변화를 평가하였다. 결과한 측에 성공적인 우회로술을 시행한 환자 17 명(남:여=12:5, 나이 $53{\pm}2$세)을 분석하였다. 전체적으로 뇌혈류는 수술 1 주 후 유의하게 증가하나 3-6 개월 후 감소하여 수술 이전의 수준으로 유지되었으며 ($1.01{\pm}0.09{\rightarrow}1.06{\pm}0.09}{\rightarrow}1.02{\pm}0.10,\;p=0.005$) 뇌 혈관 예비능은 수술 1 주 후 유의하게 증가한 이후 유의하지는 않으나, 3-6개월 이후까지 계속 호전되었다($-0.14{\pm}0.05{\rightarrow}-0.07{\pm}0.04{\rightarrow}0.05{\pm}0.05,\;p=0.004$). 각 뇌 영역별로 뇌혈류는 두정 영역에서 수술 직후 증가하였다가($1.12{\pm}0.09{\rightarrow}1.18{\pm}0.09,\;p=0.003$) 수술 3-6개월 이후 감소하여($1.12{\pm}0.09,\;p=0.003$) 수술 이전의 수준으로 유지되었다. 뇌혈관 예비능은 수술 측의 전두 영역($-0.15{\pm}0.07{\rightarrow}0.08{\pm}0.05$), 두정 영역($-0.16{\pm}0.07{\rightarrow}-0.07{\pm}0.05$)에서 모두 수술 직후 유의하게 증가하였고(p<0.01) 이후 유의하지는 않으나 3-6개월까지 계속 호전되었다. 결론: 성공적인 우회로술 후 뇌혈류는 전체적으로 유의한 변화가 없었으나 뇌혈관 예비능은 중대뇌동맥 영역 전체에 걸쳐 수술 후 단기간에 유의한 호전을 보였으며 장기간 유지되었다. 따라서 뇌혈관 예비능의 호전여부는 우회로술에 의해 증가된 뇌관류압을 평가할 수 있는 중요한 지표로 생각되며 향후 우회로술에 의한 뇌졸중 재발방지 효과를 알아보기 위해 뇌혈관 예비능의 변화와 예후와의 상관관계에 대한 연구가 필요하리라 생각된다.