Search

Various diseases can affect the esophagus. Endoscopic ultrasound (EUS), which provides precise information about the layers of the esophageal wall, is the primary approach used to investigate esophageal diseases. However, CT is one of the most important imaging modalities for diagnosing esophageal diseases as it can elucidate mediastinal involvement, adjacent lymphadenopathy, and distant disease spread. These two modalities complement each other in the diagnosis of esophageal diseases. Although radiologists may be unfamiliar with EUS procedures and their interpretation, understanding them aids in the differential diagnosis of esophageal conditions. This pictorial essay illustrates the EUS and CT findings of various esophageal diseases originating in the esophageal wall.

Immunoglobulin G4-related disease (IgG4-RD) is an immune-mediated condition characterized by mass-forming inflammation with a sclerosing pattern that can affect nearly any organ. However, involvement of the diaphragm in IgG4-RD is exceptionally rare. We present the case of a 62-year-old male patient with chest radiographic abnormalities. Further investigation with CT revealed an infiltrative mass in the right hemidiaphragm. This mass, composed of engorged feeding vessels, an atypical manifestation of IgG4-RD, was also associated with lymphadenopathy. Surgical excision confirmed the presence of IgG4-positive cell infiltration, solidifying the diagnosis of IgG4-RD. Notably, the patient remained asymptomatic and did not require any treatment postoperatively. This case highlights the uncommon presentation of IgG4-RD as an infiltrative diaphragmatic mass.

A pulmonary artery periadventitial hematoma is a rare complication of a Stanford type A intramural hematoma. As the proximal ascending aorta and pulmonary artery share a common adventitial layer, extravasated blood from the intramural hematoma in the ascending thoracic aorta may extend to beneath the adventitia of the pulmonary artery. The authors describe a case involving a 66-year-old male with acute chest pain who presented with a pulmonary artery periadventitial hematoma associated with a Stanford type A intramural hematoma.

Background and Objectives: This study’s objective was to investigate the influence of increased scan speed and pitch on image quality and nodule volumetry in patients who underwent ultra-low-dose chest computed tomography (CT). Material and Methods: One hundred and two patients who had lung nodules were included in this study. Standard-speed, standard-pitch (SSSP) ultra-low-dose CT and high-speed, high-pitch (HSHP) ultra-low-dose CT were obtained for all patients. Image noise was measured as the standard deviation of attenuation. One hundred and sixty-three nodules were identified and classified according to location, volume, and nodule type. Volume measurement of detected pulmonary nodules was compared according to nodule location, volume, and nodule type. Motion artifacts at the right middle lobe, the lingular segment, and both lower lobes near the lung bases were evaluated. Subjective image quality analysis was also performed. Results: The HSHP CT scan demonstrated decreased motion artifacts at the left upper lobe lingular segment and left lower lobe compared to the SSSP CT scan (p < 0.001). The image noise was higher and the radiation dose was lower in the HSHP scan (p < 0.001). According to the nodule type, the absolute relative volume difference was significantly higher in ground glass opacity nodules compared with those of part-solid and solid nodules (p < 0.001). Conclusion: Our study results suggest that HSHP ultra-low-dose chest CT scans provide decreased motion artifacts and lower radiation doses compared to SSSP ultra-low-dose chest CT. However, lung nodule volumetry should be performed with caution for ground glass opacity nodules.

BackgroundRobust and accurate prediction of severity for patients with COVID-19 is crucial for patient triaging decisions. Many proposed models were prone to either high bias risk or low-to-moderate discrimination. Some also suffered from a lack of clinical interpretability and were developed based on early pandemic period data. Hence, there has been a compelling need for advancements in prediction models for better clinical applicability. ObjectiveThe primary objective of this study was to develop and validate a machine learning–based Robust and Interpretable Early Triaging Support (RIETS) system that predicts severity progression (involving any of the following events: intensive care unit admission, in-hospital death, mechanical ventilation required, or extracorporeal membrane oxygenation required) within 15 days upon hospitalization based on routinely available clinical and laboratory biomarkers. MethodsWe included data from 5945 hospitalized patients with COVID-19 from 19 hospitals in South Korea collected between January 2020 and August 2022. For model development and external validation, the whole data set was partitioned into 2 independent cohorts by stratified random cluster sampling according to hospital type (general and tertiary care) and geographical location (metropolitan and nonmetropolitan). Machine learning models were trained and internally validated through a cross-validation technique on the development cohort. They were externally validated using a bootstrapped sampling technique on the external validation cohort. The best-performing model was selected primarily based on the area under the receiver operating characteristic curve (AUROC), and its robustness was evaluated using bias risk assessment. For model interpretability, we used Shapley and patient clustering methods. ResultsOur final model, RIETS, was developed based on a deep neural network of 11 clinical and laboratory biomarkers that are readily available within the first day of hospitalization. The features predictive of severity included lactate dehydrogenase, age, absolute lymphocyte count, dyspnea, respiratory rate, diabetes mellitus, c-reactive protein, absolute neutrophil count, platelet count, white blood cell count, and saturation of peripheral oxygen. RIETS demonstrated excellent discrimination (AUROC=0.937; 95% CI 0.935-0.938) with high calibration (integrated calibration index=0.041), satisfied all the criteria of low bias risk in a risk assessment tool, and provided detailed interpretations of model parameters and patient clusters. In addition, RIETS showed potential for transportability across variant periods with its sustainable prediction on Omicron cases (AUROC=0.903, 95% CI 0.897-0.910). ConclusionsRIETS was developed and validated to assist early triaging by promptly predicting the severity of hospitalized patients with COVID-19. Its high performance with low bias risk ensures considerably reliable prediction. The use of a nationwide multicenter cohort in the model development and validation implicates generalizability. The use of routinely collected features may enable wide adaptability. Interpretations of model parameters and patients can promote clinical applicability. Together, we anticipate that RIETS will facilitate the patient triaging workflow and efficient resource allocation when incorporated into a routine clinical practice.

Abstract While many deep-learning-based computer-aided detection systems (CAD) have been developed and commercialized for abnormality detection in chest radiographs (CXR), their ability to localize a target abnormality is rarely reported. Localization accuracy is important in terms of model interpretability, which is crucial in clinical settings. Moreover, diagnostic performances are likely to vary depending on thresholds which define an accurate localization. In a multi-center, stand-alone clinical trial using temporal and external validation datasets of 1,050 CXRs, we evaluated localization accuracy, localization-adjusted discrimination, and calibration of a commercially available deep-learning-based CAD for detecting consolidation and pneumothorax. The CAD achieved image-level AUROC (95% CI) of 0.960 (0.945, 0.975), sensitivity of 0.933 (0.899, 0.959), specificity of 0.948 (0.930, 0.963), dice of 0.691 (0.664, 0.718), moderate calibration for consolidation, and image-level AUROC of 0.978 (0.965, 0.991), sensitivity of 0.956 (0.923, 0.978), specificity of 0.996 (0.989, 0.999), dice of 0.798 (0.770, 0.826), moderate calibration for pneumothorax. Diagnostic performances varied substantially when localization accuracy was accounted for but remained high at the minimum threshold of clinical relevance. In a separate trial for diagnostic impact using 461 CXRs, the causal effect of the CAD assistance on clinicians’ diagnostic performances was estimated. After adjusting for age, sex, dataset, and abnormality type, the CAD improved clinicians’ diagnostic performances on average (OR [95% CI] = 1.73 [1.30, 2.32]; p

BackgroundAn artificial intelligence (AI) model using chest radiography (CXR) may provide good performance in making prognoses for COVID-19. ObjectiveWe aimed to develop and validate a prediction model using CXR based on an AI model and clinical variables to predict clinical outcomes in patients with COVID-19. MethodsThis retrospective longitudinal study included patients hospitalized for COVID-19 at multiple COVID-19 medical centers between February 2020 and October 2020. Patients at Boramae Medical Center were randomly classified into training, validation, and internal testing sets (at a ratio of 8:1:1, respectively). An AI model using initial CXR images as input, a logistic regression model using clinical information, and a combined model using the output of the AI model (as CXR score) and clinical information were developed and trained to predict hospital length of stay (LOS) ≤2 weeks, need for oxygen supplementation, and acute respiratory distress syndrome (ARDS). The models were externally validated in the Korean Imaging Cohort of COVID-19 data set for discrimination and calibration. ResultsThe AI model using CXR and the logistic regression model using clinical variables were suboptimal to predict hospital LOS ≤2 weeks or the need for oxygen supplementation but performed acceptably in the prediction of ARDS (AI model area under the curve [AUC] 0.782, 95% CI 0.720-0.845; logistic regression model AUC 0.878, 95% CI 0.838-0.919). The combined model performed better in predicting the need for oxygen supplementation (AUC 0.704, 95% CI 0.646-0.762) and ARDS (AUC 0.890, 95% CI 0.853-0.928) compared to the CXR score alone. Both the AI and combined models showed good calibration for predicting ARDS (P=.079 and P=.859). ConclusionsThe combined prediction model, comprising the CXR score and clinical information, was externally validated as having acceptable performance in predicting severe illness and excellent performance in predicting ARDS in patients with COVID-19.

Background and Objectives: BRAF mutational status in resected non-small cell lung cancer (NSCLC) in the Korean population is poorly understood. We explored BRAF (particularly BRAF V600E) mutational status among Korean patients with NSCLC. Materials and Methods: This study included 378 patients with resected primary NSCLC who were enrolled from January 2015 to December 2017. The authors obtained formalin-fixed paraffin-embedded (FFPE) tissue blocks and performed peptide nucleic acid (PNA)-clamping polymerase chain reaction (PCR) for detecting BRAF V600, real-time PCR for detecting BRAF V600E, and immunohistochemical analyses using the mutation-specific Ventana VE1 monoclonal antibody. For positive cases in any methods mentioned above, direct Sanger sequencing was additionally performed. Results: The PNA-clamping method revealed the BRAF V600 mutation in 5 (1.3%) of the 378 patients. Among these five patients, real-time PCR, direct Sanger sequencing detected BRAF V600E mutations in three (0.8%) patients. Thus, two cases showed differences in their PNA-clamping and the others. Direct Sanger sequencing of PNA-clamping PCR product was performed for two cases showing negative results on direct Sanger sequencing; both contained BRAF mutations other than V600E. All patients harboring BRAF mutations had adenocarcinomas, and all patients with V600E mutation exhibited minor micropapillary components. Conclusions: Despite the low incidence of the BRAF mutation among Korean patients with NSCLC, lung adenocarcinoma patients with micropapillary components should be prioritized in terms of BRAF mutation testing. Immunohistochemical staining using Ventana VE1 antibody may serve as a screening examination for BRAF V600E.

MRI has the advantages of having excellent soft-tissue contrast and providing functional information without any harmful ionizing radiation. Although previous technical limitations restricted the use of chest MRI, recent technological advances and expansion of insurance coverage are increasing the demand for chest MRI. Recognizing the need for guidelines on appropriate use of chest MRI in Korean clinical settings, the Korean Society of Radiology has composed a development committee, working committee, and advisory committee to develop Korean chest MRI justification guidelines. Five key questions were selected and recommendations have been made with the evidence-based clinical imaging guideline adaptation methodology. Recommendations are as follows. Chest MRI can be considered in the following circumstances: for patients with incidentally found anterior mediastinal masses to exclude non-neoplastic conditions, for pneumoconiosis patients with lung masses to differentiate progressive massive fibrosis from lung cancer, and when invasion of the chest wall, vertebrae, diaphragm, or major vessels by malignant pleural mesothelioma or non-small cell lung cancer is suspected. Chest MRI without contrast enhancement or with minimal dose low-risk contrast media can be considered for pregnant women with suspected pulmonary embolism. Lastly, chest MRI is recommended for patients with pancoast tumors planned for radical surgery.

Tracheal leiomyoma is a rare benign tumor, which is composed of transformed cells of mesenchymal origin. We describe a case in which digital tomosynthesis was useful to evaluate a tracheal tumor that was overlooked on initial chest radiographs.

Inflammatory myofibroblastic tumor is a rare benign lesion that accounts for 0.04–1% of all lung tumors and usually appears as a solitary pulmonary nodule or mass. Here, we report the case of an endobronchial inflammatory myofibroblastic tumor in a 21-year-old man with a focus on the imaging findings and a review of previous literature.

Backgroundand Objectives: To date, imaging characterization of non-rheumatic retro-odontoid pseudotumors (NRROPs) has been lacking; therefore, NRROPs have been confused with atlantoaxial joint involvement of rheumatoid arthritis (RA). It is important to differentiate these two disease because the treatment strategies may differ. The purpose of this study is to characterize imaging findings of NRROPs and compare them with those of RA. Material and Methods: From January 2015 to December 2019, 27 patients (14 women and 13 men) with NRROPs and 19 patients (15 women and 4 men) with RA were enrolled in this study. We evaluated various imaging findings, including atlantoaxial instability (AAI), and measured the maximum diameter of preodontoid and retro-odontoid spaces with magnetic resonance imaging (MRI) and computed tomography (CT). Results: Statistical significance was considered for p < 0.05. AAI was detected in eight patients with NRROPs and in all patients with RA (p < 0.0001). Seventeen patients with NRROPs and six patients with RA showed spinal cord compression (p = 0.047). Compressive myelopathy was observed in 14 patients with NRROPs and in 4 patients with RA (p = 0.048). Subaxial degeneration was observed in 25 patients with NRROPs and in 9 patients with RA (p = 0.001). Moreover, C2-3 disc abnormalities were observed in 11 patients with NRROPs and in 2 patients with RA (p = 0.02). Axial and longitudinal diameter of retro-odontoid soft tissue and preodontoid and retro-odontoid spaces showed significant differences between NRROP and RA patients (p < 0.0001). Furthermore, CT AAI measurements were differed significantly between NRROP and RA patients (p < 0.05). Conclusions: NRROPs showed prominent retro-odontoid soft tissue thickening, causing compressive myelopathy and a high frequency of subaxial and C2-3 degeneration without AAI.

Abstract Background Generally, structural destruction of lung parenchyma, such as pulmonary emphysema, is considered to be related to the low diagnostic yields and high complication rates of lung biopsies of peripheral lung lesions. Currently, little is known about the clinical outcomes of using endobronchial ultrasound with a guide sheath (EBUS-GS) to diagnose peripheral lesions in patients with emphysema. Methods This retrospective study was performed to identify the clinical outcomes of EBUS-GS in patients with pulmonary emphysema. This study included 393 consecutive patients who received EBUS-GS between February 2017 and April 2018. The patients were classified according to the severity of their emphysema, and factors possibly contributing to a successful EBUS-GS procedure were evaluated. Results The overall diagnostic yield of EBUS-GS in patients with no or mild emphysema was significantly higher than in those with moderate or severe pulmonary emphysema (78% vs. 61%, P = 0.007). There were no procedure-related complications. The presence of a bronchus sign on CT (P

Background and Objectives: Although reducing the radiation dose level is important during diagnostic computed tomography (CT) applications, effective image quality enhancement strategies are crucial to compensate for the degradation that is caused by a dose reduction. We performed this prospective study to quantify emphysema on ultra-low-dose CT images that were reconstructed using deep learning-based image reconstruction (DLIR) algorithms, and compared and evaluated the accuracies of DLIR algorithms versus standard-dose CT. Materials and Methods: A total of 32 patients were prospectively enrolled, and all underwent standard-dose and ultra-low-dose (120 kVp; CTDIvol < 0.7 mGy) chest CT scans at the same time in a single examination. A total of six image datasets (filtered back projection (FBP) for standard-dose CT, and FBP, adaptive statistical iterative reconstruction (ASIR-V) 50%, DLIR-low, DLIR-medium, DLIR-high for ultra-low-dose CT) were reconstructed for each patient. Image noise values, emphysema indices, total lung volumes, and mean lung attenuations were measured in the six image datasets and compared (one-way repeated measures ANOVA). Results: The mean effective doses for standard-dose and ultra-low-dose CT scans were 3.43 ± 0.57 mSv and 0.39 ± 0.03 mSv, respectively (p < 0.001). The total lung volume and mean lung attenuation of five image datasets of ultra-low-dose CT scans, emphysema indices of ultra-low-dose CT scans reconstructed using ASIR-V 50 or DLIR-low, and the image noise of ultra-low-dose CT scans that were reconstructed using DLIR-low were not different from those of standard-dose CT scans. Conclusions: Ultra-low-dose CT images that were reconstructed using DLIR-low were found to be useful for emphysema quantification at a radiation dose of only 11% of that required for standard-dose CT.

The ability to accurately predict the prognosis and intervention requirements for treating highly infectious diseases, such as COVID-19, can greatly support the effective management of patients, especially in resource-limited settings. The aim of the study is to develop and validate a multimodal artificial intelligence (AI) system using clinical findings, laboratory data and AI-interpreted features of chest X-rays (CXRs), and to predict the prognosis and the required interventions for patients diagnosed with COVID-19, using multi-center data. In total, 2282 real-time reverse transcriptase polymerase chain reaction-confirmed COVID-19 patients’ initial clinical findings, laboratory data and CXRs were retrospectively collected from 13 medical centers in South Korea, between January 2020 and June 2021. The prognostic outcomes collected included intensive care unit (ICU) admission and in-hospital mortality. Intervention outcomes included the use of oxygen (O2) supplementation, mechanical ventilation and extracorporeal membrane oxygenation (ECMO). A deep learning algorithm detecting 10 common CXR abnormalities (DLAD-10) was used to infer the initial CXR taken. A random forest model with a quantile classifier was used to predict the prognostic and intervention outcomes, using multimodal data. The area under the receiver operating curve (AUROC) values for the single-modal model, using clinical findings, laboratory data and the outputs from DLAD-10, were 0.742 (95% confidence interval [CI], 0.696–0.788), 0.794 (0.745–0.843) and 0.770 (0.724–0.815), respectively. The AUROC of the combined model, using clinical findings, laboratory data and DLAD-10 outputs, was significantly higher at 0.854 (0.820–0.889) than that of all other models (p < 0.001, using DeLong’s test). In the order of importance, age, dyspnea, consolidation and fever were significant clinical variables for prediction. The most predictive DLAD-10 output was consolidation. We have shown that a multimodal AI model can improve the performance of predicting both the prognosis and intervention in COVID-19 patients, and this could assist in effective treatment and subsequent resource management. Further, image feature extraction using an established AI engine with well-defined clinical outputs, and combining them with different modes of clinical data, could be a useful way of creating an understandable multimodal prediction model.

Acute phlegmonous esophagitis is a very rare, life-threatening form of esophagitis, characterized by diffuse bacterial infection and pus formation within the submucosal and muscularis layers of the esophagus. We describe a case in which contrast-enhanced chest CT was useful for evaluating the severity of phlegmonous esophagitis, which was overlooked and underestimated by endoscopy.

Background and Objectives: Glomus tumors are rare benign tumors. The majority of them affect the skin the most and are rarer in the trachea, where the glomus bodies may not be present. Only scarce reports of tracheal glomus tumors have been reported solely with case reports of relevant articles. Materials and Methods: A 53-year-old man, with a free previous medial history, presented to our hospital with tracheal mass which was incidentally found. He did not complain of any specific symptoms associated with the tracheal tumor. The contrast-enhanced chest computed tomography (CT) revealed an avid enhancing nodular lesion, which is similar to blood vessels, in the trachea, 3 cm above the carina level without definite airway obstruction. Results: Successful tracheal resection and end-to-end anastomosis were performed on the patients; therefore, the final post-operative pathologic findings revealed a benign tracheal glomus tumor. The follow-up CT scan four months after operation showed complete removal of the tumor. Conclusion: Tracheal glomus tumors, even rare entities, could be considered as a differential diagnosis if a highly enhancing mass appears on CT images.

Anterior mediastinal teratomas are congenital tumors containing derivatives of all three germ layers. They usually grow slowly and are often detected incidentally by imaging studies. We describe the case of a 38-year-old man with an anterior mediastinal teratoma extending to the anterior neck, which resulted in a cystic neck mass.

Purpose: We compared the outcomes of percutaneous transthoracic needle aspiration biopsy (PCNA) of lung masses in cases with and without prior positron emission tomography/computed tomography (PET/CT) information, and investigated the factors associated with false-negative pathological results. Materials and Methods: From a total of 291 patients, 161 underwent PCNA without prior PET/CT imaging, while 130 underwent PET/CT before PCNA. Clinical characteristics, procedural variables, pathological results, and diagnostic success rates were compared between the 2 groups. Among patients with initial negative (non-specific benign) PCNA results, the radiological findings of these groups were compared to evaluate the predictors of false-negative lesions. Results: No significant difference was found in the clinical characteristics, procedural characteristics, and pathological results of the 2 groups, nor was the diagnostic rate significantly different between them (p = 0.818). Among patients with initial negative PCNA results, radiological characteristics were similar in both the groups. In multivariate analysis, the presence of necrosis (p = 0.005) and ground-glass opacity (GGO) (p = 0.011) were the significant characteristics that indicated an increased probability of initial false-negative results in PCNA. Conclusion: Routine PET/CT did not have any additional benefit in patients undergoing PCNA of lung masses. The presence of necrosis or GGO could indicate an increased probability of false-negative pathological results.

Abstract Background The diagnostic yields and safety profiles of transbronchial lung biopsy have not been evaluated in inexperienced physicians using the combined modality of radial probe endobronchial ultrasound and a guide sheath (EBUS-GS). This study assessed the utility and safety of EBUS-GS during the learning phase by referring to a database of performed EBUS-GS procedures. Methods From December 2015 to January 2017, all of the consecutive patients who underwent EBUS-GS were registered. During the study period, two physicians with no previous experience performed the procedure. To assess the diagnostic yields, learning curve, and safety profile of EBUS-GS performed by these inexperienced physicians, the first 100 consecutive EBUS-GS procedures were included in the evaluation. Results The overall diagnostic yield of EBUS-GS performed by two physicans in 200 patients with a peripheral lung lesion was 73.0%. Learning curve analyses showed that the diagnostic yields were stable, even when the procedure was performed by beginners. Complications related to EBUS-GS occurred in three patients (1.5%): pneumothorax developed in two patients (1%) and resolved spontaneously without chest tube drainage; another patient (0.5%) developed a pulmonary infection after EBUS-GS. There were no cases of pneumothorax requiring chest tube drainage, severe hemorrhage, respiratory failure, premature termination of the procedure, or procedure-related mortality. Conclusions EBUS-GS is a safe and stable procedure with an acceptable diagnostic yield, even when performed by physicians with no previous experience.

Despite global efforts to eliminate tuberculosis, the disease remains of huge global public health problem. Prompt and accurate diagnosis of pulmonary tuberculosis is essential to ensure appropriate therapy. Chest radiography, sputum smear microscopy, mycobacterial culture, and nucleic acid amplification test are essential diagnostic elements, and appropriate use of recently introduced molecular tests and chest computed tomography could improve the accuracy of early diagnosis.

The prognostic significance of tumor-infiltrating lymphocytes has been determined in cancers of the lung, colon and breast, though there is no standardized method for using this prognostic indicator for lung cancer. We applied a modified version of the method proposed by the International Immuno-Oncology Biomarkers Working Group to primary lung adenocarcinoma, which uses histologic findings of hematoxylin and eosin sections. The study included a total cohort of 146 lung adenocarcinoma patients who underwent lobectomy with lymph node dissection at two hospitals between 2008 and 2012. The full-face sections of hematoxylin and eosin-stained slides were reviewed, and we evaluated the level of tumor-infiltrating lymphocytes as a percentage of the area occupied out of the total intra-tumoral stromal area. Histopathologic factors include histologic grade, necrosis, extracellular mucin, lymphovascular invasion, lymph node metastasis, level of tumor infiltrating lymphocytes, tertiary lymphoid structures around the tumor, and the presence of a germinal center in tertiary lymphoid structures. The high level of tumor-infiltrating lymphocytes was found to be significantly correlated with the histologic grade (p = 0.023), necrosis (p = 0.042), abundance of tertiary lymphoid structures(p

Coronary artery variations are associated anomalies in 45% of congenitally corrected transposition of the great arteries (ccTGA) cases, and it is important to detect any coronary artery anomalies before cardiac surgery. We report a case of a 51-year-old woman with ccTGA and an unreported type of coronary artery anomaly.

We present the dynamic contrast-enhanced computed tomography (CT) findings of atypical pulmonary hamartoma with a rare histologic pattern in a 20-year-old male. CT showed a 3.4 cm lobulated mass with a 'tip of the iceberg' appearance in the medium bronchus of the right lower lobe. Dynamic contrast-enhanced CT demonstrated a heterogeneously and persistently enhancing mass. The CT Hounsfield unit (HU) measurements were: 17 HU pre-contrast, 32 HU at 1 minute, 44 HU at 2 minutes, 51 HU at 4 minutes, and 64 HU at 15 minutes. Pathologic examination after video-assisted thoracoscopic surgery disclosed a pulmonary hamartoma with a predominant fibroblastic component.

Background and objectives: Thin-section computed tomography (CT) is essential for identifying small bronchi during bronchoscopy using radial endobronchial ultrasound. Some patients should receive an additional CT for a thin-section image. We performed a retrospective study with a prospectively collected database to identify the optimal radiation dose for thin-section CT during peripheral bronchoscopy. Materials and Methods: In total, 91 patients with peripheral lung lesions underwent thin-section CT (both standard CT as a reference and ultra-low-dose CT (ultra-LDCT)). The patients were randomly assigned to one of four groups according to the ultra-LDCT parameters: group 1 = 120 kVp, 25 mAs; group 2 = 100 kVp, 15 mAs; group 3 = 120 kVp, 5 mAs; and group 4 = 100 kVp, 5 mAs. Two radiologists and two physicians analyzed both the standard CT and ultra-LDCT. Results: The effective doses (EDs) of ultra-LDCT significantly differed among the four groups (median EDs were 0.88, 0.34, 0.19, and 0.12 mSv for groups 1–4, respectively; p < 0.001). Median differences in peripheral airway wall thickness were higher in group 4 than in other groups (differences in median wall thickness measured by two radiologists were 0.4–0.5 mm and 0.8–0.9 mm for groups 1–3 and group 4, respectively). Bronchus signs on ultra-LDCT in groups 1 and 2 were well correlated with those of the standard-dose CT (accuracies of two radiologists and two pulmonary physicians were 95–100%). Conclusions: Our results indicate that ultra-LDCT with ED of >0.34 mSv (ED of group 2) is feasible for peripheral bronchoscopy.