• Korean Journal of Radiology
• /
• 제25권2호
• /
• pp.126-133
• /
• 2024

Large language models (LLMs) have revolutionized the global landscape of technology beyond natural language processing. Owing to their extensive pre-training on vast datasets, contemporary LLMs can handle tasks ranging from general functionalities to domain-specific areas, such as radiology, without additional fine-tuning. General-purpose chatbots based on LLMs can optimize the efficiency of radiologists in terms of their professional work and research endeavors. Importantly, these LLMs are on a trajectory of rapid evolution, wherein challenges such as "hallucination," high training cost, and efficiency issues are addressed, along with the inclusion of multimodal inputs. In this review, we aim to offer conceptual knowledge and actionable guidance to radiologists interested in utilizing LLMs through a succinct overview of the topic and a summary of radiology-specific aspects, from the beginning to potential future directions.

• 대한영상의학회지
• /
• 제84권4호
• /
• pp.784-791
• /
• 2023

국내의 각종 통계에 따르면 외상센터는 외상 환자 치료에 중심적이며 확고한 역할을 담당하고 있는 것으로 나타났다. 외상센터에서 인터벤션 영상의학자의 역할은 출혈이 멈추도록 하는 것이다. 기본적인 색전술이 치료의 근간을 이루지만 스텐트 그래프트 설치술 등이 사용되기도 한다. 전통적인 응급인터벤션시술이 사용되어 왔으나 외상 환자에게는 짧은 시간 내에 효율적으로 출혈을 막는 것이 필수적이다. 따라서, 최근 부각되고 있는 손상통제인터벤션영상의학의 개념을 정확히 인지하고 실행하는 것이 예방 가능 외상 사망률을 낮추는데 매우 중요하다.

• 대한방사선기술학회지:방사선기술과학
• /
• 제31권3호
• /
• pp.217-222
• /
• 2008

본 논문은 2006. 1. 1${\sim}$12. 31(1년)까지 방사선 종사자 근무분야별 피폭에 관하여 서울시내 3차 의료기관인 A, B, C병원의 방사선 분야 종사자 방사선 피폭선량에 대한 분석 결과, 다음과 같은 결론을 얻었다. 1. 방사선 종사자 근무분야별 피폭은 심혈관조영실이 1.41mSv로서 제일 많았고, 방사선종양학과는 0.64mSv로서 제일 낮았다. 2. 방사선 종사자 근무분야별 피폭선량은 시술건수에 비례하였다. 3. 방사선 종사자 근무분야별 시술건수 당 피폭선량은 심혈관조영실 근무자가 많았고, 영상의학과 근무자는 적은 것으로 나타났다. 4. 방사선 종사자 근무분야별 피폭선량 순위는 심혈관조영실, 핵의학과, 영상의학과, 방사선종양학과의 순이었다. 이상과 같은 결과로 볼 때, 국제방사선방어위원회(ICRP) 권고안 범위이내이므로 병원 방사선 종사자들의 피폭에 따른 유해는 없는 것으로 판단되었다.

• Korean Journal of Radiology
• /
• 제23권7호
• /
• pp.732-741
• /
• 2022

Objective: To determine the impact of dedicated subspecialized radiologists in multidisciplinary team (MDT) discussions on the management of lower gastrointestinal (GI) tract malignancies. Materials and Methods: We retrospectively analyzed the data of 244 patients (mean age ± standard deviation, 61.7 ± 11.9 years) referred to MDT discussions 249 times (i.e., 249 cases, as five patients were discussed twice for different issues) for lower GI tract malignancy including colorectal cancer, small bowel cancer, GI stromal tumor, and GI neuroendocrine tumor between April 2018 and June 2021 in a prospective database. Before the MDT discussions, dedicated GI radiologists reviewed all imaging studies again besides routine clinical reading. The referring clinician's initial diagnosis, initial treatment plan, change in radiologic interpretation compared with the initial radiology report, and the MDT's consensus recommendations for treatment were collected and compared. Factors associated with changes in treatment plans and the implementation of MDT decisions were analyzed. Results: Of the 249 cases, radiologic interpretation was changed in 73 cases (29.3%) after a review by dedicated GI radiologists, with 78.1% (57/73) resulting in changes in the treatment plan. The treatment plan was changed in 92 cases (36.9%), and the rate of change in the treatment plan was significantly higher in cases with changes in radiologic interpretation than in those without (78.1% [57/73] vs. 19.9% [35/176], p < 0.001). Follow-up records of patients showed that 91.2% (227/249) of MDT recommendations for treatment were implemented. Multiple logistic regression analysis revealed that the nonsurgical approach (vs. surgical approach) decided through MDT discussion was a significant factor for patients being managed differently than the MDT recommendations (odds ratio, 4.48; p = 0.017). Conclusion: MDT discussion involving additional review of radiology examinations by dedicated GI radiologists resulted in a change in the treatment plan in 36.9% of cases. Changes in treatment plans were significantly associated with changes in radiologic interpretation.

• Korean Journal of Radiology
• /
• 제22권4호
• /
• pp.612-623
• /
• 2021

Objective: To evaluate the diagnostic performance of a deep learning algorithm for the automated detection of developmental dysplasia of the hip (DDH) on anteroposterior (AP) radiographs. Materials and Methods: Of 2601 hip AP radiographs, 5076 cropped unilateral hip joint images were used to construct a dataset that was further divided into training (80%), validation (10%), or test sets (10%). Three radiologists were asked to label the hip images as normal or DDH. To investigate the diagnostic performance of the deep learning algorithm, we calculated the receiver operating characteristics (ROC), precision-recall curve (PRC) plots, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) and compared them with the performance of radiologists with different levels of experience. Results: The area under the ROC plot generated by the deep learning algorithm and radiologists was 0.988 and 0.988-0.919, respectively. The area under the PRC plot generated by the deep learning algorithm and radiologists was 0.973 and 0.618-0.958, respectively. The sensitivity, specificity, PPV, and NPV of the proposed deep learning algorithm were 98.0, 98.1, 84.5, and 99.8%, respectively. There was no significant difference in the diagnosis of DDH by the algorithm and the radiologist with experience in pediatric radiology (p = 0.180). However, the proposed model showed higher sensitivity, specificity, and PPV, compared to the radiologist without experience in pediatric radiology (p < 0.001). Conclusion: The proposed deep learning algorithm provided an accurate diagnosis of DDH on hip radiographs, which was comparable to the diagnosis by an experienced radiologist.

• Korean Journal of Radiology
• /
• 제22권12호
• /
• pp.2017-2025
• /
• 2021

Objective: To evaluate the accuracy and clinical efficacy of a hybrid Greulich-Pyle (GP) and modified Tanner-Whitehouse (TW) artificial intelligence (AI) model for bone age assessment. Materials and Methods: A deep learning-based model was trained on an open dataset of multiple ethnicities. A total of 102 hand radiographs (51 male and 51 female; mean age ± standard deviation = 10.95 ± 2.37 years) from a single institution were selected for external validation. Three human experts performed bone age assessments based on the GP atlas to develop a reference standard. Two study radiologists performed bone age assessments with and without AI model assistance in two separate sessions, for which the reading time was recorded. The performance of the AI software was assessed by comparing the mean absolute difference between the AI-calculated bone age and the reference standard. The reading time was compared between reading with and without AI using a paired t test. Furthermore, the reliability between the two study radiologists' bone age assessments was assessed using intraclass correlation coefficients (ICCs), and the results were compared between reading with and without AI. Results: The bone ages assessed by the experts and the AI model were not significantly different (11.39 ± 2.74 years and 11.35 ± 2.76 years, respectively, p = 0.31). The mean absolute difference was 0.39 years (95% confidence interval, 0.33-0.45 years) between the automated AI assessment and the reference standard. The mean reading time of the two study radiologists was reduced from 54.29 to 35.37 seconds with AI model assistance (p < 0.001). The ICC of the two study radiologists slightly increased with AI model assistance (from 0.945 to 0.990). Conclusion: The proposed AI model was accurate for assessing bone age. Furthermore, this model appeared to enhance the clinical efficacy by reducing the reading time and improving the inter-observer reliability.

• 대한영상의학회지
• /
• 제82권1호
• /
• pp.49-65
• /
• 2021

미용적 성형 및 유방암 수술 후 재건의 목적으로 사용되는 실리콘 보형물의 사용이 국내외에서 크게 증가함에 따라 진료 영역에서 실리콘 보형물 삽입술을 받은 환자들을 어렵지 않게 접하게 되었다. 기존에 알려져 있던 보형물의 파열이나 구축과 같은 합병증 외에 최근에는 유방 보형물 연관 역형성 대세포 림프종과 같은 악성 종양과의 연관성도 보고되면서 보형물 관련한 영상 검사가 증가하고 있다. 이러한 상황에서 영상의학과 의사들은 보형물 삽입술을 받은 환자에 대해 어떤 검사가 필요하고 어떤 영상 소견이 보형물 관련 합병증을 시사하는지에 관한 충분한 지식을 갖추고 있어야 할 것이다. 본 종설에서는 영상의학과 의사들이 알아야 하는 실리콘 보형물의 다양한 합병증과 이들의 영상 소견에 대해 다루고자 한다.

• Korean Journal of Radiology
• /
• 제24권2호
• /
• pp.155-165
• /
• 2023

Objective: Little is known about the effects of using different expert-determined reference standards when evaluating the performance of deep learning-based automatic detection (DLAD) models and their added value to radiologists. We assessed the concordance of expert-determined standards with a clinical gold standard (herein, pathological confirmation) and the effects of different expert-determined reference standards on the estimates of radiologists' diagnostic performance to detect malignant pulmonary nodules on chest radiographs with and without the assistance of a DLAD model. Materials and Methods: This study included chest radiographs from 50 patients with pathologically proven lung cancer and 50 controls. Five expert-determined standards were constructed using the interpretations of 10 experts: individual judgment by the most experienced expert, majority vote, consensus judgments of two and three experts, and a latent class analysis (LCA) model. In separate reader tests, additional 10 radiologists independently interpreted the radiographs and then assisted with the DLAD model. Their diagnostic performance was estimated using the clinical gold standard and various expert-determined standards as the reference standard, and the results were compared using the t test with Bonferroni correction. Results: The LCA model (sensitivity, 72.6%; specificity, 100%) was most similar to the clinical gold standard. When expert-determined standards were used, the sensitivities of radiologists and DLAD model alone were overestimated, and their specificities were underestimated (all p-values < 0.05). DLAD assistance diminished the overestimation of sensitivity but exaggerated the underestimation of specificity (all p-values < 0.001). The DLAD model improved sensitivity and specificity to a greater extent when using the clinical gold standard than when using the expert-determined standards (all p-values < 0.001), except for sensitivity with the LCA model (p = 0.094). Conclusion: The LCA model was most similar to the clinical gold standard for malignant pulmonary nodule detection on chest radiographs. Expert-determined standards caused bias in measuring the diagnostic performance of the artificial intelligence model.

• Korean Journal of Radiology
• /
• 제21권10호
• /
• pp.1150-1160
• /
• 2020

Objective: To describe the experience of implementing a deep learning-based computer-aided detection (CAD) system for the interpretation of chest X-ray radiographs (CXR) of suspected coronavirus disease (COVID-19) patients and investigate the diagnostic performance of CXR interpretation with CAD assistance. Materials and Methods: In this single-center retrospective study, initial CXR of patients with suspected or confirmed COVID-19 were investigated. A commercialized deep learning-based CAD system that can identify various abnormalities on CXR was implemented for the interpretation of CXR in daily practice. The diagnostic performance of radiologists with CAD assistance were evaluated based on two different reference standards: 1) real-time reverse transcriptase-polymerase chain reaction (rRT-PCR) results for COVID-19 and 2) pulmonary abnormality suggesting pneumonia on chest CT. The turnaround times (TATs) of radiology reports for CXR and rRT-PCR results were also evaluated. Results: Among 332 patients (male:female, 173:159; mean age, 57 years) with available rRT-PCR results, 16 patients (4.8%) were diagnosed with COVID-19. Using CXR, radiologists with CAD assistance identified rRT-PCR positive COVID-19 patients with sensitivity and specificity of 68.8% and 66.7%, respectively. Among 119 patients (male:female, 75:44; mean age, 69 years) with available chest CTs, radiologists assisted by CAD reported pneumonia on CXR with a sensitivity of 81.5% and a specificity of 72.3%. The TATs of CXR reports were significantly shorter than those of rRT-PCR results (median 51 vs. 507 minutes; p < 0.001). Conclusion: Radiologists with CAD assistance could identify patients with rRT-PCR-positive COVID-19 or pneumonia on CXR with a reasonably acceptable performance. In patients suspected with COVID-19, CXR had much faster TATs than rRT-PCRs.

• Korean Journal of Radiology
• /
• 제24권5호
• /
• pp.406-423
• /
• 2023

Diagnosing bowel and mesenteric trauma poses a significant challenge to radiologists. Although these injuries are relatively rare, immediate laparotomy may be indicated when they occur. Delayed diagnosis and treatment are associated with increased morbidity and mortality; therefore, timely and accurate management is essential. Additionally, employing strategies to differentiate between major injuries requiring surgical intervention and minor injuries considered manageable via non-operative management is important. Bowel and mesenteric injuries are among the most frequently overlooked injuries on trauma abdominal computed tomography (CT), with up to 40% of confirmed surgical bowel and mesenteric injuries not reported prior to operative treatment. This high percentage of falsely negative preoperative diagnoses may be due to several factors, including the relative rarity of these injuries, subtle and non-specific appearances on CT, and limited awareness of the injuries among radiologists. To improve the awareness and diagnosis of bowel and mesenteric injuries, this article provides an overview of the injuries most often encountered, imaging evaluation, CT appearances, and diagnostic pearls and pitfalls. Enhanced diagnostic imaging awareness will improve the preoperative diagnostic yield, which will save time, money, and lives.