• Korean Journal of Radiology
• /
• v.23 no.3
• /
• 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.

• Journal of the Korean Society of Radiology
• /
• v.5 no.5
• /
• pp.303-308
• /
• 2011

Background/Aims : The increasing use of diagnostic and therapeutic interventional radiology calls for greater consideration of radiation exposure risk to radiologist and radiological technician, and emphasizes the proper system of radiation protection. This study was designed to assess the effect of a protective grass shield. Methods : A protective grass was following data depth, 0.8 cm; width, 100 cm; length, 100 cm, lead equivalent, 1.6 mmPb. The protective shield was located between the patient and the radiologist. Thirty patients (13 male and 17 female) undergoing interventional radiology between September 2010 and December 2010 were selected for this study. The dose of radiation exposure was recorded with or without the protective grass shield at the level of the head, chest, and pelvis. The measurement was made at 50 cm and 150 cm from the radiation source. Results : The mean patient age was 69 years. The mean patient height and weight was $159.7{\pm}6.7$ cm and $60.3{\pm}5.9$ kg, respectively. The mean body mass index (BMI) was $20.5{\pm}3.0$ kg/m2. radiologists received $1530.2{\pm}550.0$ mR/hr without the protective lead shield. At the same distance, radiation exposure was significantly reduced to $50.3{\pm}85.2$ mR/hr with the protective lead shield (p-value<0.0001). The radiation exposure to radiologist and radiological technician was significantly reduced by the use of a protective lead shield (p value <0.0001). The amount of radiation exposure during interventional radiology was related to the patient' BMI (r=0.749, p=0.001). Conclusions : This protective shield grass is effective in protecting radiologist and radiological technician from radiation exposure.

• Imaging Science in Dentistry
• /
• v.54 no.1
• /
• pp.105-107
• /
• 2024

The author herein presents an unusual case of eustachian tube calcification masquerading as loose radiopacities in the temporomandibular joints on a panoramic image, creating a diagnostic challenge. The patient, a 72-year-old woman, presented to the dental service for implant treatment to improve her masticatory function. A cone-beam computed tomography scan was performed and reviewed by a board-certified oral and maxillofacial radiologist. The scan showed no evidence of calcifications in the temporomandibular joints; however, it revealed nodular calcifications within the cartilaginous portion of the eustachian tube bilaterally. Additionally, this report briefly reviews the differential diagnosis of calcified loose bodies in the temporomandibular joint and provides information that needs to be reinforced periodically.

• Journal of the Korean Society of Radiology
• /
• v.84 no.2
• /
• pp.361-371
• /
• 2023

The success of image-guided breast biopsy depends on the biopsy method, needle selection, and appropriate technique based on the accurate judgment by the radiologist at biopsy. However, insufficient or inappropriate sampling of specimens may result in false-negative results or pathologic underestimation. Therefore, image-pathology concordance assessments after biopsy are essential for appropriate patient management. Particularly, the assessment of image-pathology concordance can avoid false-negative reports of breast cancer as a benign pathology. Therefore, this study aimed to discuss factors that impact the accurate interpretation of image-guided breast biopsy along with the appropriate assessments.

• Journal of International Society for Simulation Surgery
• /
• v.2 no.1
• /
• pp.17-25
• /
• 2015

Purpose In this paper, we propose a robust 3D vessel tracking algorithm by utilizing an active contour model and unscented Kalman filter which are the two representative algorithms on segmentation and tracking. Materials and Methods The proposed algorithm firstly accepts user input to produce an initial estimate of vessel boundary segmentation. On each Computed Tomography Angiography (CTA) slice, the active contour is applied to segment the vessel boundary. After that, the estimation process of the unscented Kalman filter is applied to track the vessel boundary of the current slice to estimate the inter-slice vessel position translation and shape deformation. Finally both active contour and unscented Kalman filter are inter-operated for vessel segmentation of the next slice. Results The arbitrarily shaped blood vessel boundary on each slice is segmented by using the active contour model, and the Kalman filter is employed to track the translation and shape deformation between CTA slices. The proposed algorithm is applied to the 3D visualization of chest CTA images using graphics hardware. Conclusion Through this algorithm, more opportunities, giving quick and brief diagnosis, could be provided for the radiologist before detailed diagnosis using 2D CTA slices, Also, for the surgeon, the algorithm could be used for surgical planning, simulation, navigation and rehearsal, and is expected to be applied to highly valuable applications for more accurate 3D vessel tracking and rendering.

• Korean Journal of Radiology
• /
• v.21 no.6
• /
• pp.660-669
• /
• 2020

Objective: To evaluate the accuracy of a deep learning-based automated segmentation of the left ventricle (LV) myocardium using cardiac CT. Materials and Methods: To develop a fully automated algorithm, 100 subjects with coronary artery disease were randomly selected as a development set (50 training / 20 validation / 30 internal test). An experienced cardiac radiologist generated the manual segmentation of the development set. The trained model was evaluated using 1000 validation set generated by an experienced technician. Visual assessment was performed to compare the manual and automatic segmentations. In a quantitative analysis, sensitivity and specificity were calculated according to the number of pixels where two three-dimensional masks of the manual and deep learning segmentations overlapped. Similarity indices, such as the Dice similarity coefficient (DSC), were used to evaluate the margin of each segmented masks. Results: The sensitivity and specificity of automated segmentation for each segment (1-16 segments) were high (85.5-100.0%). The DSC was 88.3 ± 6.2%. Among randomly selected 100 cases, all manual segmentation and deep learning masks for visual analysis were classified as very accurate to mostly accurate and there were no inaccurate cases (manual vs. deep learning: very accurate, 31 vs. 53; accurate, 64 vs. 39; mostly accurate, 15 vs. 8). The number of very accurate cases for deep learning masks was greater than that for manually segmented masks. Conclusion: We present deep learning-based automatic segmentation of the LV myocardium and the results are comparable to manual segmentation data with high sensitivity, specificity, and high similarity scores.

• Journal of Biomedical Engineering Research
• /
• v.38 no.5
• /
• pp.237-241
• /
• 2017

Early detection of the pulmonary nodule is important for diagnosis and treatment of lung cancer. Recently, CT has been used as a screening tool for lung nodule detection. And, it has been reported that computer aided detection(CAD) systems can improve the accuracy of the radiologist in detection nodules on CT scan. The previous study has been proposed a method using Convolutional Neural Network(CNN) in Lung CAD system. But the proposed model has a limitation in accuracy due to its sparse layer structure. Therefore, we propose a Deep Convolutional Neural Network to overcome this limitation. The model proposed in this work is consist of 14 layers including 8 convolutional layers and 4 fully connected layers. The CNN model is trained and tested with 61,404 regions-of-interest (ROIs) patches of lung image including 39,760 nodules and 21,644 non-nodules extracted from the Lung Image Database Consortium(LIDC) dataset. We could obtain the classification accuracy of 91.79% with the CNN model presented in this work. To prevent overfitting, we trained the model with Augmented Dataset and regularization term in the cost function. With L1, L2 regularization at Training process, we obtained 92.39%, 92.52% of accuracy respectively. And we obtained 93.52% with data augmentation. In conclusion, we could obtain the accuracy of 93.75% with L2 Regularization and Data Augmentation.

• Clinics in Shoulder and Elbow
• /
• v.9 no.1
• /
• pp.73-82
• /
• 2006

Purpose: The purpose of the present study was to evaluate the diagnostic efficacy of CT arthrography (CTA) in the assessment of various shoulder pathologies, compared with MR arthrography (MRA) and MRI with arthroscopic correlation. Materials and Methods: CTA in 84 patients, MRA in 70 patients, and MRI in 27 patients were obtained. A radiologist interpreted each image for 5 pathologies: Bankart, SLAP, Hill-Sachs lesion, full-thickness, and partial-thickness rotator cuff tear. Detailed arthroscopic reports were compared with CTA, MRA, and MRI. The sensitivity, specificity, predictive values, and accuracy were calculated. The agreement between each diagnostic modality and arthroscopy was calculated. Diagnostic efficacy was assessed by the areas under the receiver operating characteristic (ROC) curves. Results: The diagnostic values of all three imaging groups were comparable to each other for Bankart, SLAP, Hills-Sachs, and full-thickness cuff tear lesions, but those of CTA were lower than MRI and MRA for partial-thickness cuff tears. The areas under the ROC curves for CTA, MRA, and MRI were not significantly different for all pathologies, except for partial-thickness cuff tears. Conclusion: CTA was equally competent to MRA or MRI in demonstrating Bankart, Hill-Sachs lesions, SLAP, and full thickness rotator cuff tears but not as efficient in diagnosing partial thickness rotator cuff tears.

• Korean Journal of Head & Neck Oncology
• /
• v.15 no.2
• /
• pp.177-181
• /
• 1999

Objective: The clinical significance of mass screening for thyroid carcinoma remains unclear. This study was carried out to clarify the value of mass screening for thyroid carcinoma. Materials and Methods: From December 1997 through July 1998, a total of 1,401 subjects who were enrolled to receive breast screening or follow-up examination for breast cancer were included in this study. Thyroid glands were examined by 10 MHz ultrasonography by one experienced radiologist. The patients with thyroid nodules were classified into 2 groups according to their potential risk of malignancy by ultrasonographic findings(high-risk : hypoechogenicity, microcalcification, irregular margin, taller than wider shape). High-risk patients were advised to undergo fine-needle aspiration biopsy and thyroidectomy. The characteristics of the thyroid cancers detected by ultrasonographic mass screening were compared by those of clinical thyroid cancer excluding male patients during the same period. Results: Thyroid nodules were detected in 353(25.2%) of the subjects and 259(73.4%) were listed in the low-risk group and 94(26.6%) in high-risk group. Among 94 patients in the high-risk group, 43 underwent thyroidectomy and 37 turned out to have thyroid carcinomas. Thus, the detection rates for carcinoma were 2.6% of all subject, 10.5% of the detected nodules, 36.4% of the high risk women and 86.0% of the operated cases. The tumor size was significantly smaller in the mass-screening group than in the clinical cancer group(p<0.05). However, there was no statistical differences between two groups in the prevalences of neck node involvement and extracapsular invasion and the patients distributions by AMES score, MACIS score and TNM stage. Conclusion: Ultrasonogrpahic mass screening may be useful for the early detection of thyroid carcinoma in women who are scheduled to have breast examination.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• v.24 no.3
• /
• pp.279-287
• /
• 2021

Purpose: The clinical implications of bowel wall thickening (BWT) on abdominal computed tomography (CT) among children are unknown. We aimed to suggest a new method for measuring BWT and determining its clinical significance in children. Methods: We retrospectively analyzed 423 patients with acute abdomen who underwent abdominal CT; 262 were classified into the BWT group. For this group, the pediatric radiologist described the maximal bowel wall thickness (MT), normal bowel wall thickness (mm) (NT), and their ratios for each segment of the bowel wall. Results: In the thickened bowel walls, the thickness differed significantly between the small bowel (6.83±2.14 mm; mean±standard deviation) and the colon (8.56±3.46 mm; p<0.001). The ratios of MT to NT in the small bowel (6.09±3.17) and the colon (7.58±3.70) were also significantly different (p<0.001). In the BWT group, 35 of 53 patients had positive fecal polymerase chain reaction results; 6 patients infected with viruses predominantly had BWT in the small intestine, while the terminal ileum and the colon were predominantly affected in 29 patients with bacterial infections. In the initially undiagnosed 158 patients with BWT, the symptoms improved spontaneously without progression to chronic gastrointestinal disease. Conclusion: This study provides a clinical reference value for BWT in the small intestine and colon using a new method in children. The BWT on abdominal CT in children might indicate nonspecific findings that can be observed and followed up without additional evaluation, unlike in adults.