• 대한영상의학회지
• /
• 제82권5호
• /
• pp.1218-1230
• /
• 2021

목적 고위험 환자에서 초기 간암 선별 검사로써 단축 자기공명영상 검사의 환자별 진단능을 기존의 고식적 간 자기공명영상검사와 비교하고자 한다. 대상과 방법 간암 고위험군에서 간 자기공명영상 검사를 시행 받은 총 201명의 환자에 대해 연구를 시행하였다. 단축 자기공명영상 검사 군의 프로토콜은 T2 강조영상, 담도기 T1 강조영상, 확산강조영상 등으로 구성되며, 두 명의 영상의학과 의사가 각각의 환자에 대해 후향적으로 단축 자기공명영상검사 군 및 고식적 자기공명영상검사 군, 두 군의 영상을 독립적으로 평가하였다. 두 연구자 간 일관성은 Cohen's kappa 값을 이용하여 비교하였다. 복합적인 참조표준을 이용하여 두 군에서 각각 진단능을 평가하여 비교하였다. 결과 79 명의 환자에서 총 93개의 간암이 발견되었다. 두 연구자 간 일관성은 두 군에서 모두 매우 양호하였다(κ = 0.839, 0.948). 단축 자기공명영상검사 군에서 민감도 및 음성예측도는 각각 94.9% 및 96.4%였으며, 이는 고식적 자기공명영상검사 군과 큰 차이를 보이지 않았다(96.2%, 97.5%). 결론 단축 자기공명영상검사는 고식적 자기공명영상검사에 비교하여 임상적으로 허용 가능한 민감도와 음성예측도를 갖는다. 따라서 간암 고위험군 환자에서 간암 선별검사로써 새로운 대안이 될 수 있을 것이다.

• Korean Journal of Radiology
• /
• 제24권6호
• /
• pp.498-511
• /
• 2023

Objective: To evaluate the diagnostic performance of chest computed tomography (CT)-based qualitative and radiomics models for predicting residual axillary nodal metastasis after neoadjuvant chemotherapy (NAC) for patients with clinically node-positive breast cancer. Materials and Methods: This retrospective study included 226 women (mean age, 51.4 years) with clinically node-positive breast cancer treated with NAC followed by surgery between January 2015 and July 2021. Patients were randomly divided into the training and test sets (4:1 ratio). The following predictive models were built: a qualitative CT feature model using logistic regression based on qualitative imaging features of axillary nodes from the pooled data obtained using the visual interpretations of three radiologists; three radiomics models using radiomics features from three (intranodal, perinodal, and combined) different regions of interest (ROIs) delineated on pre-NAC CT and post-NAC CT using a gradient-boosting classifier; and fusion models integrating clinicopathologic factors with the qualitative CT feature model (referred to as clinical-qualitative CT feature models) or with the combined ROI radiomics model (referred to as clinical-radiomics models). The area under the curve (AUC) was used to assess and compare the model performance. Results: Clinical N stage, biological subtype, and primary tumor response indicated by imaging were associated with residual nodal metastasis during the multivariable analysis (all P < 0.05). The AUCs of the qualitative CT feature model and radiomics models (intranodal, perinodal, and combined ROI models) according to post-NAC CT were 0.642, 0.812, 0.762, and 0.832, respectively. The AUCs of the clinical-qualitative CT feature model and clinical-radiomics model according to post-NAC CT were 0.740 and 0.866, respectively. Conclusion: CT-based predictive models showed good diagnostic performance for predicting residual nodal metastasis after NAC. Quantitative radiomics analysis may provide a higher level of performance than qualitative CT features models. Larger multicenter studies should be conducted to confirm their performance.

• Korean Journal of Radiology
• /
• 제24권6호
• /
• pp.529-540
• /
• 2023

Objective: To compare the diagnostic performance and clinical outcomes of 2-mSv computed tomography (CT) and conventional-dose CT (CDCT), following radiology residents' interpretation of CT examinations for suspected appendicitis. Materials and Methods: Altogether, 3074 patients with suspected appendicitis aged 15-44 years (28 ± 9 years, 1672 females) from 20 hospitals were randomly assigned to the 2-mSv CT (n = 1535) or CDCT (n = 1539) groups in a pragmatic trial from December 2013 and August 2016. Overall, 107 radiology residents participated in the trial as readers in the form of daily practice after online training for 2-mSv CT. They made preliminary CT reports, which were later finalized by attending radiologists via addendum reports, for 640 and 657 patients in the 2-mSv CT and CDCT groups, respectively. We compared the diagnostic performance of the residents, discrepancies between preliminary and addendum reports, and clinical outcomes between the two groups. Results: Patient characteristics were similar between the 640 and 657 patients. Residents' diagnostic performance was not significantly different between the 2-mSv CT and CDCT groups, with a sensitivity of 96.0% and 97.1%, respectively (difference [95% confidence interval {CI}], -1.1% [-4.9%, 2.6%]; P = 0.69) and specificity of 93.2% and 93.1%, respectively (0.1% [-3.6%, 3.7%]; P > 0.99). The 2-mSv CT and CDCT groups did not significantly differ in discrepancies between the preliminary and addendum reports regarding the presence of appendicitis (3.3% vs. 5.2%; -1.9% [-4.2%, 0.4%]; P = 0.12) and alternative diagnosis (5.5% vs. 6.4%; -0.9% [-3.6%, 1.8%]; P = 0.56). The rates of perforated appendicitis (12.0% vs. 12.6%; -0.6% [-4.3%, 3.1%]; P = 0.81) and negative appendectomies (1.9% vs. 1.1%; 0.8% [-0.7%, 2.3%]; P = 0.33) were not significantly different between the two groups. Conclusion: Diagnostic performance and clinical outcomes were not significantly different between the 2-mSv CT and CDCT groups following radiology residents' CT readings for suspected appendicitis.

• 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.

• 대한영상의학회지
• /
• 제81권6호
• /
• pp.1397-1411
• /
• 2020

목적 이 연구는 인공지능(artificial intelligence; 이하 AI)에 대한 영상의학과 전공의들의 인식 및 의견을 알아보고자 하였다. 대상과 방법 2019년 6월 4일부터 7일까지 AI와 관련한 18개의 객관식 문항과 1개의 주관식 문항이 포함된 설문의 응답을 받았다. 모집된 결과를 로지스틱 회귀분석을 이용하여 전공의 연차, 소속 병원의 위치 및 규모 등의 요인에 따라 분석하였다. 결과 총 101명(89.4%)의 전공의가 응답하였다. AI의 지식적 측면에서 응답자의 50명(49.5%)이 AI에 대해 평균 이상으로 공부하고 있으며, 68명(67.3%)이 AI 관련 용어에 대한 이해도가 평균 이상이라고 응답하였다. 또한 서울 및 경기 지역 응답자가 기타 지역 응답자에 비하여 AI에 대한 자가 평가 및 지식수준이 의미 있게 높았으며, 4년차 전공의에 비해 1~2년차 전공의가 AI에 대한 자가 평가 및 지식수준이 의미 있게 낮았다. AI 관련 연구에 참여해본 적 있는 전공의는 15.8%이었지만, 추후 연구 참여 의향이 있는 전공의는 90%에 달하였다. 전공의 들은 또한 학회 주도의 AI 교육 및 적극적 홍보를 원하고 있었다. 결론 영상의학과 전공의의 AI 교육 수요를 충족시키고, 의료 AI 시대의 영상의학과 의사의 역할을 제대로 알리기 위해 보다 많은 학회 차원의 노력이 요청된다.

• 대한영상의학회지
• /
• 제81권5호
• /
• pp.1260-1265
• /
• 2020

카포시 육종은 후천성 면역 결핍 증후군(acquired immunodeficiency syndrome; 이하 AIDS)와 연관되어, 피부, 점막과 여러 장기를 침범하는 다발성의 혈관성 결절로 나타나는 신생물을 일컫는다. AIDS와 연관되어 생기는 위장관 카포시 육종은 내장에 파종성 질환으로 가장 흔하게 발생한다. 우리는 다양한 장기를 침범하여 복통과 함께 장관 내 출혈을 유발한 드문 카포시 육종의 영상 소견에 대해 보고한다. 회장 대장내시경을 통해 말단 회장, S자 결장, 직장 내 다양한 병변이 발견되었으며 소장 투시검사로 공장과 회장의 병변을 확인할 수 있었다. 복부 골반 전산화단층촬영에서 회장 내 조영증강된 다양한 납작한 병변과 복강 내 크기가 커진 림프절을 발견하였다. 조직병리학 검사에서 카포시 육종으로 최종 진단이 된 환자는 항레트로바이러스제로 치료를 시행 받았다. 최근 AIDS 환자의 수가 늘고 있는 상황에서, AIDS와 연관된 Kaposi's sarcoma의 영상학적 소견을 숙지하는 것은 영상의학과 의사를 비롯한 임상의사들에게 빠른 진단과 치료뿐만이 아니라 예상치 못한 AIDS의 감염 위험에 노출될 수 있는 의료진의 안전을 위해서도 필수적이다.

• Korean Journal of Radiology
• /
• 제24권5호
• /
• pp.454-464
• /
• 2023

Objective: We aimed to investigate current expectations and clinical adoption of artificial intelligence (AI) software among neuroradiologists in Korea. Materials and Methods: In April 2022, a 30-item online survey was conducted by neuroradiologists from the Korean Society of Neuroradiology (KSNR) to assess current user experiences, perceptions, attitudes, and future expectations regarding AI for neuro-applications. Respondents with experience in AI software were further investigated in terms of the number and type of software used, period of use, clinical usefulness, and future scope. Results were compared between respondents with and without experience with AI software through multivariable logistic regression and mediation analyses. Results: The survey was completed by 73 respondents, accounting for 21.9% (73/334) of the KSNR members; 72.6% (53/73) were familiar with AI and 58.9% (43/73) had used AI software, with approximately 86% (37/43) using 1-3 AI software programs and 51.2% (22/43) having up to one year of experience with AI software. Among AI software types, brain volumetry software was the most common (62.8% [27/43]). Although 52.1% (38/73) assumed that AI is currently useful in practice, 86.3% (63/73) expected it to be useful for clinical practice within 10 years. The main expected benefits were reducing the time spent on repetitive tasks (91.8% [67/73]) and improving reading accuracy and reducing errors (72.6% [53/73]). Those who experienced AI software were more familiar with AI (adjusted odds ratio, 7.1 [95% confidence interval, 1.81-27.81]; P = 0.005). More than half of the respondents with AI software experience (55.8% [24/43]) agreed that AI should be included in training curriculums, while almost all (95.3% [41/43]) believed that radiologists should coordinate to improve its performance. Conclusion: A majority of respondents experienced AI software and showed a proactive attitude toward adopting AI in clinical practice, suggesting that AI should be incorporated into training and active participation in AI development should be encouraged.

• Korean Journal of Radiology
• /
• 제24권4호
• /
• pp.284-293
• /
• 2023

Objective: To validate a simplified ordinal scoring method, referred to as modified length-based grading, for assessing coronary artery calcium (CAC) severity on non-electrocardiogram (ECG)-gated chest computed tomography (CT). Materials and Methods: This retrospective study enrolled 120 patients (mean age ± standard deviation [SD], 63.1 ± 14.5 years; male, 64) who underwent both non-ECG-gated chest CT and ECG-gated cardiac CT between January 2011 and December 2021. Six radiologists independently assessed CAC severity on chest CT using two scoring methods (visual assessment and modified length-based grading) and categorized the results as none, mild, moderate, or severe. The CAC category on cardiac CT assessed using the Agatston score was used as the reference standard. Agreement among the six observers for CAC category classification was assessed using Fleiss kappa statistics. Agreement between CAC categories on chest CT obtained using either method and the Agatston score categories on cardiac CT was assessed using Cohen's kappa. The time taken to evaluate CAC grading was compared between the observers and two grading methods. Results: For differentiation of the four CAC categories, interobserver agreement was moderate for visual assessment (Fleiss kappa, 0.553 [95% confidence interval {CI}: 0.496-0.610]) and good for modified length-based grading (Fleiss kappa, 0.695 [95% CI: 0.636-0.754]). The modified length-based grading demonstrated better agreement with the reference standard categorization with cardiac CT than visual assessment (Cohen's kappa, 0.565 [95% CI: 0.511-0.619 for visual assessment vs. 0.695 [95% CI: 0.638-0.752] for modified length-based grading). The overall time for evaluating CAC grading was slightly shorter in visual assessment (mean ± SD, 41.8 ± 38.9 s) than in modified length-based grading (43.5 ± 33.2 s) (P < 0.001). Conclusion: The modified length-based grading worked well for evaluating CAC on non-ECG-gated chest CT with better interobserver agreement and agreement with cardiac CT than visual assessment.

• Korean Journal of Radiology
• /
• 제24권4호
• /
• pp.305-312
• /
• 2023

Objective: Chronic enteropathy associated with SLCO2A1 gene (CEAS) is a recently recognized disease. We aimed to evaluate the enterographic findings of CEAS. Materials and Methods: Altogether, 14 patients with CEAS were confirmed based on known SLCO2A1 mutations. They were registered in a multicenter Korean registry between July 2018 and July 2021. Nine of the patients (37.2 ± 13 years; all female) who underwent surgery-naïve-state computed tomography enterography (CTE) or magnetic resonance enterography (MRE) were identified. Two experienced radiologists reviewed 25 and 2 sets of CTE and MRE examinations, respectively, regarding the small bowel findings. Results: In initial evaluation, eight patients showed a total of 37 areas with mural abnormalities in the ileum on CTE, including 1-4 segments in six and > 10 segments in two patients. One patient showed unremarkable CTE. The involved segments were 10-85 mm (median, 20 mm) in length, 3-14 mm (median, 7 mm) in mural thickness, circumferential in 86.5% (32/37), and showed stratified enhancement in the enteric and portal phases in 91.9% (34/37) and 81.8% (9/11), respectively. Perienteric infiltration and prominent vasa recta were noted in 2.7% (1/37) and 13.5% (5/37), respectively. Bowel strictures were identified in six patients (66.7%), with a maximum upstream diameter of 31-48 mm. Two patients underwent surgery for strictures immediately after the initial enterography. Follow-up CTE and MRE in the remaining patients showed minimal-to-mild changes in the extent and thickness of the mural involvement for 17-138 months (median, 47.5 months) after initial enterography. Two patients required surgery for bowel stricture at 19 and 38 months of follow-up, respectively. Conclusion: CEAS of the small bowel typically manifested on enterography in varying numbers and lengths of abnormal ileal segments that showed circumferential mural thickening with layered enhancement without perienteric abnormalities. The lesions caused bowel strictures that required surgery in some patients.

• Korean Journal of Radiology
• /
• 제23권6호
• /
• pp.615-624
• /
• 2022

Objective: To compare the therapeutic outcomes of laparoscopic hepatic resection (LHR) and laparoscopic radiofrequency ablation (LRFA) for single subcapsular hepatocellular carcinoma (HCC). Materials and Methods: We screened 244 consecutive patients who had received either LHR or LRFA between January 2014 and December 2016. The feasibility of LRFA in patients who underwent LHR was retrospectively assessed by two interventional radiologists. Finally, 60 LRFA-feasible patients who had received LHR and 29 patients who had received LRFA as the first treatment for a solitary subcapsular HCC between 1 cm and 3 cm were finally included. We compared the therapeutic outcomes, including local tumor progression (LTP), recurrence-free survival (RFS), and overall survival (OS) between the two groups before and after propensity score (PS) matching. Multivariable Cox proportional hazard regression was also used to evaluate the difference in OS and RFS between the two groups for all 89 patients. Results: PS matching yielded 23 patients in each group. The cumulative LTP and OS rates were not significantly different between the LHR and LRFA groups after PS matching (p = 0.900 and 0.003, respectively). The 5-year LTP rates were 4.6% and 4.4%, respectively, and OS rates were 100% and 90.7%, respectively. The RFS rate was higher in LHR group without statistical significance (p = 0.070), with 5-year rates of 78.3% and 45.3%, respectively. OS was not significantly different between the LHR (reference) and LRFA groups in multivariable analyses, with a hazard ratio (HR) of 1.33 (95% confidence interval, 0.12-1.54) (p = 0.818). RFS was higher in LHR (reference) than in LRFA without statistical significance in multivariable analysis, with an HR of 2.01 (0.87-4.66) (p = 0.102). Conclusion: There was no significant difference in therapeutic outcomes between LHR and LRFA for single subcapsular HCCs measuring 1-3 cm. The difference in RFS should be further evaluated in a larger study.