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.

PURPOSE: ⁶⁸Ga-labeled 1,4,7,10-tetraazacyclododecane-N,N′,N″,N‴-tetraacetic acid-D-Phe1-Tyr3-octreotide (⁶⁸Ga-DOTATOC) is taken up by activated macrophages, which accumulate in active inflammatory lesions. The purpose of this study was to investigate the feasibility of ⁶⁸Ga-DOTATOC PET/CT for assessment of vulnerable plaque, by evaluating correlation between aortic uptake of ⁶⁸Ga-DOTATOC and cardiovascular risk factors. METHODS: Fifty patients with neuroendocrine tumors who underwent ⁶⁸Ga-DOTATOC PET/CT were retrospectively enrolled. The uptakes in the thoracic aorta were measured by two methods: multi-sample region-of-interest (ROI) method and single volume-of-interest (VOI) method. TBRmax-avg, TBRmean-avg, TBRmax-VOI, and TBRmean-VOI were defined by maximum and mean target-to-background ratio (TBR) from the multi-sample ROI method and the single VOI method, respectively. RESULTS: Framinghamrisk score (FRS) exhibited significant correlations with TBRmax-avg and TBRmean-avg, aswell as TBRmax-VOI (r = 0.3389–0.4593, P < 0.05 for all). TBRmax-avg and TBRmax-VOI were significantly higher in high FRS group than in low FRS group (1.48 ± 0.21 vs. 1.70 ± 0.17, P < 0.001 for TBRmax-avg and 1.90 ± 0.33 vs. 2.25 ± 0.36, P = 0.002 for TBRmax-VOI). TBR exhibited high correlations between the two measuring methods (r = 0.9684, P < 0.001 for TBRmean-avg and TBRmean-VOI and r = 0.8681, P < 0.001 for TBRmax-avg and TBRmax-VOI). CONCLUSIONS ⁶⁸Ga-DOTATOC uptake in the thoracic aorta exhibited a significant correlation with cardiovascular risk factors, which suggests the feasibility of ⁶⁸Ga-DOTATOC PET for vulnerable plaque imaging, with a simple measurement of the single VOI method that is comparable to the multi-sample ROI-based approach.

PURPOSE: Herein, we report characteristics of ¹⁸F–fluorodeoxyglucose (FDG) uptake in abdominal aortic aneurysms (AAAs) during a long-term follow-up. In addition, we investigated the association between FDG uptake and the physician decision to perform an intervention. METHODS: We performed a retrospective review of 42 patients with AAAs who underwent FDG positron emission tomography (PET)/computed tomography (CT). The size of the AAA was measured in serial CT or PET/CT images. The long-term growth rate of AAAs was calculated by linear regression of the size change. Maximal SUV of the AAA (SUV(AAA)) and mean SUV of the blood pool (SUV(Blood)) were measured in PET/CT fusion images. To assess the FDG uptake of AAAs, the target-to-background ratio (TBR) was defined as the ratio of SUV(AAA) to SUV(Blood). We compared FDG uptake of AAAs with the long-term growth rate of AAAs and clinical data. RESULTS: TBR was not significantly different between patients with and without significant growth (1.55 ± 0.20 vs. 1.57 ± 0.14; P = 0.5599).However, in patients with significant growth, TBR exhibited a significant positive correlation with the growth rate (r² = 0.2601, P = 0.0306). TBR also exhibited a significant difference between patients with and without intervention (P = 0.0228). CONCLUSION FDG uptake of AAA is associated with long-term growth of AAAs in a specified group that exhibits growth. FDG PET/CT may only be effective in predicting the long-term growth of AAAs in specific subgroups of patients. It is also suggested that FDG PET is potentially related to the clinical conditions of AAA patients who need surgical or interventional treatment.

PURPOSE: Although ¹⁸F-fluorodeoxyglucose (FDG) positron emission tomography (PET) is a standard imaging modality for response evaluation in FDG-avid lymphoma, there is a controversy using FDG PET in indolent lymphoma. The purpose of this study was to investigate the effectiveness of quantitative indexes on FDG PET in response evaluation of the indolent lymphoma. METHODS: Fifty-seven indolent lymphoma patients who completed chemotherapy were retrospectively enrolled. FDG PET/computed tomography (CT) scans were performed at baseline, interim, and end of treatment (EOT). Response was determined by Lugano classification, and progression-free survival (PFS) by follow-up data. Maximumstandardized uptake value (SUV(max)), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) were measured in the single hottest lesion (target A) or five hottest lesions (target B). Their efficacies regarding response evaluation and PFS prediction were evaluated. RESULTS: On EOT PET, SUV(max), and MTVof both targets were well associated with visual analysis. Changes between initial and EOT PET were not significantly different between CR and non-CR groups. On interim PET, SUV(max), and %ΔSUV(max) in both targets were significantly different between CR and non-CR groups. For prediction of PFS, most tested indexes were significant on EOT and interim PET, with SUVmax being the most significant prognostic factor. CONCLUSION Quantitative indexes of FDG PET are well associated with Lugano classification in indolent lymphoma. SUV(max) measured in the single hottest lesion can be effective in response evaluation and prognosis prediction on interim and EOT PET.

PURPOSE: In malignant melanoma, recurrence is often observed in distant areas from the primary site. While FDG PET is a sensitive imaging for detecting malignant lesions, the role of FDG PET in posttreatment surveillance period has not been investigated sufficiently. The aim of this study was to evaluate the value of PET during posttreatment surveillance in melanoma. METHODS: A total of 76 melanoma patients who underwent FDG PET during surveillance period after completion of the first treatment were retrospectively enrolled. PET scans were grouped according to the purpose and clinical situations, routine surveillance, or evaluating clinical suspicion. Final diagnosis of recurrence was determined by complete clinical evaluation or long-term follow-up. In each situation, the diagnostic role of FDG PET was assessed. RESULTS: A total of 143 scans of 76 patients were analyzed: 51 for clinical suspicion and 92 for routine surveillance. In the clinical suspicion group, PET correctly diagnosed non-recurrence in 10 cases (20%). In routine surveillance group, 16 cases (17%) presented recurrence, all of which was correctly diagnosed on PET. NPVand PPV were 100% and 76%, respectively. In subgroup analysis, sensitivity and NPV were higher in the low-risk group (stages I–II(A)) than in the high-risk group (stages II(B)–IV), while specificity and PPV were higher in the high-risk group. CONCLUSION In conclusion, FDG PET is an effective diagnostic tool in posttreatment surveillance of melanoma. Even in cases without clinical suspicion, melanoma recurs in a considerable proportion of patients, which can be sensitively diagnosed on PET.

PURPOSE: Herein, we report characteristics of ¹⁸F–fluorodeoxyglucose (FDG) uptake in abdominal aortic aneurysms (AAAs) during a long-term follow-up. In addition, we investigated the association between FDG uptake and the physician decision to perform an intervention.METHODS: We performed a retrospective review of 42 patients with AAAs who underwent FDG positron emission tomography (PET)/computed tomography (CT). The size of the AAA was measured in serial CT or PET/CT images. The long-term growth rate of AAAs was calculated by linear regression of the size change. Maximal SUV of the AAA (SUV(AAA)) and mean SUV of the blood pool (SUV(Blood)) were measured in PET/CT fusion images. To assess the FDG uptake of AAAs, the target-to-background ratio (TBR) was defined as the ratio of SUV(AAA) to SUV(Blood). We compared FDG uptake of AAAs with the long-term growth rate of AAAs and clinical data.RESULTS: TBR was not significantly different between patients with and without significant growth (1.55 ± 0.20 vs. 1.57 ± 0.14; P = 0.5599).However, in patients with significant growth, TBR exhibited a significant positive correlation with the growth rate (r² = 0.2601, P = 0.0306). TBR also exhibited a significant difference between patients with and without intervention (P = 0.0228).CONCLUSION: FDG uptake of AAA is associated with long-term growth of AAAs in a specified group that exhibits growth. FDG PET/CT may only be effective in predicting the long-term growth of AAAs in specific subgroups of patients. It is also suggested that FDG PET is potentially related to the clinical conditions of AAA patients who need surgical or interventional treatment.
Aortic Aneurysm, Abdominal ; Follow-Up Studies ; Humans ; Linear Models ; Positron-Emission Tomography ; Positron-Emission Tomography and Computed Tomography ; Retrospective Studies

PURPOSE: ⁶⁸Ga-labeled 1,4,7,10-tetraazacyclododecane-N,N′,N″,N‴-tetraacetic acid-D-Phe1-Tyr3-octreotide (⁶⁸Ga-DOTATOC) is taken up by activated macrophages, which accumulate in active inflammatory lesions. The purpose of this study was to investigate the feasibility of ⁶⁸Ga-DOTATOC PET/CT for assessment of vulnerable plaque, by evaluating correlation between aortic uptake of ⁶⁸Ga-DOTATOC and cardiovascular risk factors.METHODS: Fifty patients with neuroendocrine tumors who underwent ⁶⁸Ga-DOTATOC PET/CT were retrospectively enrolled. The uptakes in the thoracic aorta were measured by two methods: multi-sample region-of-interest (ROI) method and single volume-of-interest (VOI) method. TBRmax-avg, TBRmean-avg, TBRmax-VOI, and TBRmean-VOI were defined by maximum and mean target-to-background ratio (TBR) from the multi-sample ROI method and the single VOI method, respectively.RESULTS: Framinghamrisk score (FRS) exhibited significant correlations with TBRmax-avg and TBRmean-avg, aswell as TBRmax-VOI (r = 0.3389–0.4593, P < 0.05 for all). TBRmax-avg and TBRmax-VOI were significantly higher in high FRS group than in low FRS group (1.48 ± 0.21 vs. 1.70 ± 0.17, P < 0.001 for TBRmax-avg and 1.90 ± 0.33 vs. 2.25 ± 0.36, P = 0.002 for TBRmax-VOI). TBR exhibited high correlations between the two measuring methods (r = 0.9684, P < 0.001 for TBRmean-avg and TBRmean-VOI and r = 0.8681, P < 0.001 for TBRmax-avg and TBRmax-VOI).CONCLUSIONS: ⁶⁸Ga-DOTATOC uptake in the thoracic aorta exhibited a significant correlation with cardiovascular risk factors, which suggests the feasibility of ⁶⁸Ga-DOTATOC PET for vulnerable plaque imaging, with a simple measurement of the single VOI method that is comparable to the multi-sample ROI-based approach.
Aorta, Thoracic ; Atherosclerosis ; Humans ; Macrophages ; Methods ; Neuroendocrine Tumors ; Positron-Emission Tomography and Computed Tomography ; Retrospective Studies ; Risk Factors

PURPOSE: Although ¹⁸F-fluorodeoxyglucose (FDG) positron emission tomography (PET) is a standard imaging modality for response evaluation in FDG-avid lymphoma, there is a controversy using FDG PET in indolent lymphoma. The purpose of this study was to investigate the effectiveness of quantitative indexes on FDG PET in response evaluation of the indolent lymphoma.METHODS: Fifty-seven indolent lymphoma patients who completed chemotherapy were retrospectively enrolled. FDG PET/computed tomography (CT) scans were performed at baseline, interim, and end of treatment (EOT). Response was determined by Lugano classification, and progression-free survival (PFS) by follow-up data. Maximumstandardized uptake value (SUV(max)), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) were measured in the single hottest lesion (target A) or five hottest lesions (target B). Their efficacies regarding response evaluation and PFS prediction were evaluated.RESULTS: On EOT PET, SUV(max), and MTVof both targets were well associated with visual analysis. Changes between initial and EOT PET were not significantly different between CR and non-CR groups. On interim PET, SUV(max), and %ΔSUV(max) in both targets were significantly different between CR and non-CR groups. For prediction of PFS, most tested indexes were significant on EOT and interim PET, with SUVmax being the most significant prognostic factor.CONCLUSION: Quantitative indexes of FDG PET are well associated with Lugano classification in indolent lymphoma. SUV(max) measured in the single hottest lesion can be effective in response evaluation and prognosis prediction on interim and EOT PET.
Classification ; Disease-Free Survival ; Drug Therapy ; Follow-Up Studies ; Glycolysis ; Humans ; Lymphoma ; Positron-Emission Tomography ; Prognosis ; Retrospective Studies ; Tumor Burden

PURPOSE: In malignant melanoma, recurrence is often observed in distant areas from the primary site. While FDG PET is a sensitive imaging for detecting malignant lesions, the role of FDG PET in posttreatment surveillance period has not been investigated sufficiently. The aim of this study was to evaluate the value of PET during posttreatment surveillance in melanoma.METHODS: A total of 76 melanoma patients who underwent FDG PET during surveillance period after completion of the first treatment were retrospectively enrolled. PET scans were grouped according to the purpose and clinical situations, routine surveillance, or evaluating clinical suspicion. Final diagnosis of recurrence was determined by complete clinical evaluation or long-term follow-up. In each situation, the diagnostic role of FDG PET was assessed.RESULTS: A total of 143 scans of 76 patients were analyzed: 51 for clinical suspicion and 92 for routine surveillance. In the clinical suspicion group, PET correctly diagnosed non-recurrence in 10 cases (20%). In routine surveillance group, 16 cases (17%) presented recurrence, all of which was correctly diagnosed on PET. NPVand PPV were 100% and 76%, respectively. In subgroup analysis, sensitivity and NPV were higher in the low-risk group (stages I–II(A)) than in the high-risk group (stages II(B)–IV), while specificity and PPV were higher in the high-risk group.CONCLUSION: In conclusion, FDG PET is an effective diagnostic tool in posttreatment surveillance of melanoma. Even in cases without clinical suspicion, melanoma recurs in a considerable proportion of patients, which can be sensitively diagnosed on PET.
Diagnosis ; Follow-Up Studies ; Humans ; Melanoma ; Positron-Emission Tomography ; Recurrence ; Retrospective Studies ; Sensitivity and Specificity

BACKGROUND: Iodine is an intrinsic element of thyroid hormone, which is essential for childhood growth and development. The Ideal Breast Milk (IBM) cohort study aims to evaluate the effects of maternal iodine status during pregnancy and lactation on maternal thyroid function, offspring growth and development, and offspring thyroid function. METHODS: The IBM cohort study recruited pregnant women from Seoul National University Hospital between June 2016 and August 2017, followed by enrollment of their offspring after delivery. For the maternal participants, iodine status is evaluated by urinary iodine concentration (UIC) and dietary records in the third trimester and at 3 to 4 weeks and 12 to 15 months postpartum. For the child participants, cord blood sampling and UIC measurements are performed at birth. At 3 to 4 weeks of age, UIC and breastmilk iodine concentrations are measured. At 12 to 15 months of age, growth and development are assessed and measurements of UIC, a thyroid function test, and ultrasonography are performed. RESULTS: A total of 198 pregnant women in their third trimester were recruited. Their mean age was 35.1±3.5 years, and 78 (39.4%) of them were pregnant with twins. Thirty-three (16.7%) of them had a previous history of thyroid disease. CONCLUSION: Korea is an iodine-replete area. In particular, lactating women in Korea are commonly exposed to excess iodine due to the traditional practice of consuming brown seaweed soup postpartum. The study of the IBM cohort is expected to contribute to developing guidelines for optimal iodine nutrition in pregnant or lactating women.
Breast* ; Child ; Cohort Studies* ; Cordocentesis ; Diet Records ; Female ; Growth and Development* ; Humans ; Infant ; Iodine* ; Korea ; Lactation* ; Milk, Human* ; Parturition ; Postpartum Period ; Pregnancy Trimester, Third ; Pregnancy* ; Pregnant Women ; Prospective Studies* ; Seaweed ; Seoul ; Thyroid Diseases ; Thyroid Function Tests ; Thyroid Gland* ; Twins ; Ultrasonography