Low-iodine-dose computed tomography coupled with an artificial intelligence-based contrast-boosting technique in children: a retrospective study on comparison with conventional-iodine-dose computed tomography.

BACKGROUND: Low-iodine-dose computed tomography (CT) protocols have emerged to mitigate the risks associated with contrast injection, often resulting in decreased image quality. OBJECTIVE: To evaluate the image quality of low-iodine-dose CT combined with an artificial intelligence (AI)-based contrast-boosting technique in abdominal CT, compared to a standard-iodine-dose protocol in children. MATERIALS AND METHODS: This single-center retrospective study included 35 pediatric patients (mean age 9.2 years, range 1-17 years) who underwent sequential abdominal CT scans-one with a standard-iodine-dose protocol (standard-dose group, Iobitridol 350 mgI/mL) and another with a low-iodine-dose protocol (low-dose group, Iohexol 240 mgI/mL)-within a 4-month interval from January 2022 to July 2022. The low-iodine CT protocol was reconstructed using an AI-based contrast-boosting technique (contrast-boosted group). Quantitative and qualitative parameters were measured in the three groups. For qualitative parameters, interobserver agreement was assessed using the intraclass correlation coefficient, and mean values were employed for subsequent analyses. For quantitative analysis of the three groups, repeated measures one-way analysis of variance with post hoc pairwise analysis was used. For qualitative analysis, the Friedman test followed by post hoc pairwise analysis was used. Paired t-tests were employed to compare radiation dose and iodine uptake between the standard- and low-dose groups. RESULTS: The standard-dose group exhibited higher attenuation, contrast-to-noise ratio (CNR), and signal-to-noise ratio (SNR) of organs and vessels compared to the low-dose group (all P-values < 0.05 except for liver SNR, P = 0.12). However, noise levels did not differ between the standard- and low-dose groups (P = 0.86). The contrast-boosted group had increased attenuation, CNR, and SNR of organs and vessels, and reduced noise compared with the low-dose group (all P < 0.05). The contrast-boosted group showed no differences in attenuation, CNR, and SNR of organs and vessels (all P > 0.05), and lower noise (P = 0.002), than the standard-dose group. In qualitative analysis, the contrast-boosted group did not differ regarding vessel enhancement and lesion conspicuity (P > 0.05) but had lower noise (P < 0.05) and higher organ enhancement and artifacts (all P < 0.05) than the standard-dose group. While iodine uptake was significantly reduced in low-iodine-dose CT (P < 0.001), there was no difference in radiation dose between standard- and low-iodine-dose CT (all P > 0.05). CONCLUSION: Low-iodine-dose abdominal CT, combined with an AI-based contrast-boosting technique exhibited comparable organ and vessel enhancement, as well as lesion conspicuity compared to standard-iodine-dose CT in children. Moreover, image noise decreased in the contrast-boosted group, albeit with an increase in artifacts.

Shear wave elastography and dispersion imaging for hepatic veno-occlusive disease prediction after pediatric hematopoietic stem cell transplantation: a feasibility study.

BACKGROUND: Non-invasive imaging modalities are warranted for diagnosing and monitoring veno-occlusive disease because early diagnosis and treatment improve the prognosis. OBJECTIVE: To evaluate the usefulness of liver shear wave elastography (SWE) and shear wave dispersion (SWD) imaging in diagnosing and monitoring veno-occlusive disease in pediatric patients. MATERIALS AND METHODS: We conducted a prospective cohort study at a single tertiary hospital from March 2021 to April 2022. The study protocol included four ultrasound (US) sessions: a baseline US and three follow-up US after hematopoietic stem cell transplantation. Clinical criteria, including the European Society for Blood and Marrow Transplantation criteria, were used to diagnose veno-occlusive disease. We compared clinical factors and US parameters between the veno-occlusive disease and non-veno-occlusive disease groups. The diagnostic performance of US parameters for veno-occlusive disease was assessed by plotting receiver operating characteristic (ROC) curves. We describe temporal changes in US parameters before and after veno-occlusive disease diagnosis. RESULTS: Among the 38 participants (mean age 10.7 years), eight developed veno-occlusive disease occurring 17.0 ± 5.2 days after hematopoietic stem cell transplantation. Liver stiffness, as measured by SWE (15.0 ± 6.2 kPa vs. 5.8 ± 1.8 kPa; P<0.001), and viscosity, as assessed with SWD (17.7 ± 3.1 m/s/kHz vs. 14.3 ± 2.8 m/s/kHz; P=0.015), were significantly higher in the veno-occlusive disease group compared to the non-veno-occlusive disease group at the time of diagnosis. Liver stiffness demonstrated the highest area under the ROC (AUROC) curves at 0.960, with an optimal predictive value of >6.5 kPa, resulting in sensitivity and specificity of 100% and 83.3%, respectively. Viscosity demonstrated an AUROC of 0.783, with an optimal cutoff value of 13.9 m/s/kHz for predicting veno-occlusive disease, with a sensitivity of 100% and specificity of 53.3%, respectively. Liver stiffness increased with disease severity and decreased during post-treatment follow-up. CONCLUSION: SWE may be a promising technique for early diagnosis and severity prediction of veno-occlusive disease. Furthermore, liver viscosity assessed by SWD may serve as an additional marker of veno-occlusive disease.

Prediction of High-Risk Neuroblastoma Among Neuroblastic Tumors Using Radiomics Features Derived from Magnetic Resonance Imaging: A Pilot Study.

PURPOSE: This study aimed to predict high-risk neuroblastoma among neuroblastic tumors using radiomics features extracted from MRI. MATERIALS AND METHODS: Pediatric patients (age≤18 years) diagnosed with neuroblastic tumors who had pre-treatment MR images available were enrolled from institution A from January 2010 to November 2019 (training set) and institution B from January 2016 to January 2022 (test set). Segmentation was performed with regions of interest manually drawn along tumor margins on the slice with the widest tumor area by two radiologists. First-order and texture features were extracted and intraclass correlation coefficients (ICCs) were calculated. Multivariate logistic regression (MLR) and random forest (RF) models from 10-fold cross-validation were built using these features. The trained MLR and RF models were tested in an external test set. RESULTS: Thirty-two patients (M:F=23:9, 26.0±26.7 months) were in the training set and 14 patients (M:F=10:4, 33.4±20.4 months) were in the test set with radiomics features (n=930) being extracted. For 10 of the most relevant features selected, intra- and inter-observer variability was moderate to excellent (ICCs 0.633-0.911, 0.695-0.985, respectively). The area under the receiver operating characteristic curve (AUC) was 0.94 (sensitivity 67%, specificity 91%, and accuracy 84%) for the MLR model and the average AUC was 0.83 (sensitivity 44%, specificity 87%, and accuracy 75%) for the RF model from 10-fold cross-validation. In the test set, AUCs of the MLR and RF models were 0.94 and 0.91, respectively. CONCLUSION: An MRI-based radiomics model can help predict high-risk neuroblastoma among neuroblastic tumors.

Feasibility of a deep learning artificial intelligence model for the diagnosis of pediatric ileocolic intussusception with grayscale ultrasonography.

PURPOSE: This study explored the feasibility of utilizing a deep learning artificial intelligence (AI) model to detect ileocolic intussusception on grayscale ultrasound images. METHODS: This retrospective observational study incorporated ultrasound images of children who underwent emergency ultrasonography for suspected ileocolic intussusception. After excluding video clips, Doppler images, and annotated images, 40,765 images from two tertiary hospitals were included (positive-to-negative ratio: hospital A, 2,775:35,373; hospital B, 140:2,477). Images from hospital A were split into a training set, a tuning set, and an internal test set (ITS) at a ratio of 7:1.5:1.5. Images from hospital B comprised an external test set (ETS). For each image indicating intussusception, two radiologists provided a bounding box as the ground-truth label. If intussusception was suspected in the input image, the model generated a bounding box with a confidence score (0-1) at the estimated lesion location. Average precision (AP) was used to evaluate overall model performance. The performance of practical thresholds for the modelgenerated confidence score, as determined from the ITS, was verified using the ETS. RESULTS: The AP values for the ITS and ETS were 0.952 and 0.936, respectively. Two confidence thresholds, CTopt and CTprecision, were set at 0.557 and 0.790, respectively. For the ETS, the perimage precision and recall were 95.7% and 80.0% with CTopt, and 98.4% and 44.3% with CTprecision. For per-patient diagnosis, the sensitivity and specificity were 100.0% and 97.1% with CTopt, and 100.0% and 99.0% with CTprecision. The average number of false positives per patient was 0.04 with CTopt and 0.01 for CTprecision. CONCLUSION: The feasibility of using an AI model to diagnose ileocolic intussusception on ultrasonography was demonstrated. However, further study involving bias-free data is warranted for robust clinical validation.

Effects of iodine status on thyroid volume and goiter in children living in an iodine-replete area.

Objective: Adequate iodine intake is essential for growing children, and thyroid volume (Tvol) is considered as an indicator of iodine status. We investigated Tvol and goiter using ultrasonography (US) and their association with iodine status in 228 6-year-old children living in Korea. Methods: Iodine status was assessed using urine iodine concentration (UIC) and categorized as deficient (<100 µg/L), adequate (100-299 µg/L), mild excess (300-499 µg/L), moderate excess (500-999 µg/L), and severe excess (≥1000 µg/L). Tvol was measured using US, and a goiter on the US (goiter-US) was defined as Tvol greater than 97th percentile value by age- and body surface area (BSA)-specific international references. Results: The median Tvol was 2.4 mL, larger than the international reference value (1.6 mL). The age- and BSA-specific goiter-US rates were 25.9% (n = 59) and 34.6% (n = 79), respectively. The prevalence of excess iodine was 73.7% (n = 168). As iodine status increased from adequate to severe excess, the goiter-US rate significantly increased (P for trend <0.05). The moderate and severe iodine excess groups showed higher risk of goiter-US (adjusted odds ratio (aOR) = 3.1 (95% CI: 1.1-9.2) and aOR = 3.1 (95% CI: 1.2-8.3), respectively; age-specific criteria) than the iodine-adequate group. Conclusions: Excess iodine was prevalent in Korean children, and their Tvol was higher than the international reference values. Goiter rate was associated with iodine excess, which significantly increased in the moderate and severe iodine excess groups. Further studies are warranted to define optimal iodine intake in children.

Clinical outcomes of nephrocalcinosis in preschool-age children: association between nephrocalcinosis improvement and long-term kidney function.

Background: We evaluated the long-term clinical outcomes of nephrocalcinosis (NC) according to etiology and grade in preschool-age children with NC. Methods: We retrospectively analyzed the clinical outcomes and disease grade of children with NC classified into three groups according to etiology: prematurity, tubular disorders, and others. Results: Overall, 67 children were diagnosed with NC [median age, 0.76 years; interquartile range (IQR) 0.46-2.14 years]. The etiologies of NC included prematurity (28.4%), tubular disorders (25.4%), and others (46.3%). Moreover, 56 (83.6%) children were asymptomatic and diagnosed accidentally through kidney ultrasonography. Newly diagnosed underlying diseases were greater in the tubular disorders group than in the other two groups (P = 0.001). Significantly more newly diagnosed NCs were grade 3 than grade 1 (P = 0.003). The median estimated glomerular filtration rate (eGFR) changed from 96.1 (IQR 68.8-119.2) ml/min/1.72 m2 at diagnosis to 90.9 (IQR 76.4-106.4) ml/min/1.72 m2 at the last follow-up, without a significant difference (P = 0.096). Changes in the kidney function did not differ according to etiology. However, patients without improvement in NC grade showed a decrease in eGFR from 98.1 (IQR 71.1-132.9) to 87.4 (IQR 74.0-104.1) ml/min/1.73 m2 (P = 0.023), while patients with improved NC grade did not show any change in the kidney function. Conclusions: Early recognition, especially in NC grade 3, can help uncover further diagnoses, such as tubular disorders. Long-term kidney function depends on whether the NC grade improves.

Factors contributing to uncertainty in paediatric abdominal ultrasound reports in the paediatric emergency department.

BACKGROUND: Abdominal pain, which is a common cause of children presenting to the paediatric emergency department (PED), is often evaluated by ultrasonography (US). However, uncertainty in US reports may necessitate additional imaging. OBJECTIVE: In this study, we evaluated factors contributing to uncertainty in paediatric abdominal US reports in the PED. MATERIALS AND METHODS: This retrospective cohort study included children younger than 18 years of age who underwent abdominal US in the PED of the study hospital between January 2017 and December 2019. After exclusion, the researchers manually reviewed and classified all US reports as 'certain' or 'uncertain'. Univariate and multivariate logistic regression analyses were performed to identify the factors contributing to uncertain reports. RESULTS: In total, 1006 patients were included in the final analysis., 796 patients were tagged as having certain reports, and 210 as having uncertain reports. Children with uncertain reports had a significantly higher rate of undergoing an additional computed tomography (CT) scan (31.0% vs. 2.5%, p < 0.001) and a longer PED median length of stay (321.0 (Interquartile range (IQR); 211.3-441.5) minutes vs. 284.5 (IQR; 191.8-439.5) minutes, p = 0.042). After logistic regression, US performed by a radiology resident (odds ratio, 5.01; 95% confidence interval, 3.63-7.15) was the most significant factor contributing to uncertainty in paediatric abdominal US reports followed by obesity and age. CONCLUSION: Several factors contribute to uncertainty in paediatric abdominal US reports. Uncertain radiological reports increase the likelihood of additional CT scans. Measures to improve the clarity of radiological reports must be considered to improve the quality of care for children visiting the PED.

Spontaneous recovery of underlying bony erosion following surgical removal of craniofacial dermoid cysts in periatric patients: A prospective study.

This study aimed to evaluate the spontaneous recovery of bone deformity after surgical excision of craniofacial dermoid cysts in pediatrics. Pediatric patients who underwent excision of a dermoid cyst were included in the study. A prospective analysis was conducted to evaluate the amount of bone recovery by comparing the depth of bony concavity in the preoperative and postoperative (6 months) ultrasonography. In 145 of 187 patients with preoperative imaging available, the mean size of dermoid cysts was 1.4 cm3 (range, 0.1 to 9.5), and 41.4% (60/145 cases) showed cranial bone depression. In the comparison of preoperative and postoperative ultrasonography of 30 patients, the mean depth of bony cavity decreased significantly from 4.0 to 0.9 mm (p<0.001) after a mean of 6.7 months postoperatively. There was 13.3% (4/30) of mild (≤2.0 mm), 40.0% (12/30) of moderate (>2.0 to ≤4.0 mm), and 46.7% (14/30) of severe (>4.0 mm) depression, and the concavity depth significantly decreased in all groups (p = 0.028, mild; p<0.001, moderate; p<0.001 severe). Within the limitations of the study it seems that significant recovery of cranial bone depression does take place within 6 months after excision of craniofacial dermoid cysts in pediatric patients, saving the need for immediate reconstruction.

Ultra-low-dose computed tomography with deep learning reconstruction for craniosynostosis at radiation doses comparable to skull radiographs: a pilot study.

BACKGROUND: Craniofacial computed tomography (CT) is the diagnostic investigation of choice for craniosynostosis, but high radiation dose remains a concern. OBJECTIVE: To evaluate the image quality and diagnostic performance of an ultra-low-dose craniofacial CT protocol with deep learning reconstruction for diagnosis of craniosynostosis. MATERIALS AND METHODS: All children who underwent initial craniofacial CT for suspected craniosynostosis between September 2021 and September 2022 were included in the study. The ultra-low-dose craniofacial CT protocol using 70 kVp, model-based iterative reconstruction and deep learning reconstruction techniques was compared with a routine-dose craniofacial CT protocol. Quantitative analysis of the signal-to-noise ratio and noise was performed. The 3-dimensional (D) volume-rendered images were independently evaluated by two radiologists with regard to surface coarseness, step-off artifacts and overall image quality on a 5-point scale. Sutural patency was assessed for each of six sutures. Radiation dose was compared between the two protocols. RESULTS: Among 29 patients (15 routine-dose CT and 14 ultra-low-dose CT), 23 patients had craniosynostosis. The 3-D volume-rendered images of ultra-low-dose CT without deep learning showed decreased image quality compared to routine-dose CT. The 3-D volume-rendered images of ultra-low-dose CT with deep learning reconstruction showed higher noise level, higher surface coarseness but decreased step-off artifacts, comparable signal-to-noise ratio and overall similar image quality compared to the routine-dose CT images. Diagnostic performance for detecting craniosynostosis at the suture level showed no significant difference between ultra-low-dose CT without deep learning reconstruction, ultra-low-dose CT with deep learning reconstruction and routine-dose CT. The estimated effective radiation dose for the ultra-low-dose CT was 0.05 mSv (range, 0.03-0.06 mSv), a 95% reduction in dose over the routine-dose CT at 1.15 mSv (range, 0.54-1.74 mSv). This radiation dose is comparable to 4-view skull radiography (0.05-0.1 mSv) and lower than previously reported effective dose for craniosynostosis protocols (0.08-3.36 mSv). CONCLUSION: In this pilot study, an ultra-low-dose CT protocol using radiation doses at a level similar to skull radiographs showed preserved diagnostic performance for craniosynostosis, but decreased image quality compared to the routine-dose CT protocol. However, by combining the ultra-low-dose CT protocol with deep learning reconstruction, image quality was improved to a level comparable to the routine-dose CT protocol, without sacrificing diagnostic performance for craniosynostosis.

Monitoring Posterior Cerebral Perfusion Changes With Dynamic Susceptibility Contrast-Enhanced Perfusion MRI After Anterior Revascularization Surgery in Pediatric Moyamoya Disease.

OBJECTIVE: To determine whether dynamic susceptibility contrast-enhanced (DSC) perfusion magnetic resonance imaging (MRI) can be used to evaluate posterior cerebral circulation in pediatric patients with moyamoya disease (MMD) who underwent anterior revascularization. MATERIALS AND METHODS: This study retrospectively included 73 patients with MMD who underwent DSC perfusion MRI (age, 12.2 ± 6.1 years) between January 2016 and December 2020, owing to recent-onset clinical symptoms during the follow-up period after completion of anterior revascularization. DSC perfusion images were analyzed using a dedicated software package (NordicICE; Nordic NeuroLab) for the middle cerebral artery (MCA), posterior cerebral artery (PCA), and posterior border zone between the two regions (PCA-MCA). Patients were divided into two groups; the PCA stenosis group included 30 patients with newly confirmed PCA involvement, while the no PCA stenosis group included 43 patients without PCA involvement. The relationship between DSC perfusion parameters and PCA stenosis, as well as the performance of the parameters in discriminating between groups, were analyzed. RESULTS: In the PCA stenosis group, the mean follow-up duration was 5.3 years after anterior revascularization, and visual disturbances were a common symptom. Normalized cerebral blood volume was increased, and both the normalized time-to-peak (nTTP) and mean transit time values were significantly delayed in the PCA stenosis group compared with those in the no PCA stenosis group in the PCA and PCA-MCA border zones. TTPPCA (odds ratio [OR] = 6.745; 95% confidence interval [CI] = 2.665-17.074; P < 0.001) and CBVPCA-MCA (OR = 1.567; 95% CI = 1.021-2.406; P = 0.040) were independently associated with PCA stenosis. TTPPCA showed the highest receiver operating characteristic curve area in discriminating for PCA stenosis (0.895; 95% CI = 0.803-0.986). CONCLUSION: nTTP can be used to effectively diagnose PCA stenosis. Therefore, DSC perfusion MRI may be a valuable tool for monitoring PCA stenosis in patients with MMD.

Contrast-enhanced ultrasound for the diagnosis of acute pyelonephritis in pediatric patients with urinary tract infection: A feasibility study.

PURPOSE: This study aimed to assess the feasibility of contrast-enhanced ultrasound (CEUS) for the diagnosis of acute pyelonephritis (APN) in pediatric patients with febrile urinary tract infection (UTI). MATERIALS AND METHODS: Between March 2019 and January 2021, study participants with suspected UTI were assessed for APN using ultrasound. Parenchymal echogenicity changes, renal pelvis dilatation, and the presence of a focal suspected lesion were assessed using conventional grayscale ultrasound. The presence and location of a decreased perfusion area were evaluated using color Doppler ultrasound (CDUS) and CEUS. Agreement between each ultrasound examination and a 99mTc‒dimercaptosuccinic acid (DMSA) scan was assessed using the κ value, and the most visible period of the lesion was evaluated using CEUS. RESULTS: This study enrolled 21 participants (median age, 8.0 months; range, 2.0-61.0 months) with isolated urinary tract pathogens. Five increased parenchymal echotextures (11.9%) and 14 renal pelvic dilatations (33.3%) were confirmed, but no focal lesions were detected on the grayscale images. CDUS and CEUS showed decreased local perfusion suggestive of APN in two and five kidneys, respectively. DMSA scan showed substantial agreement with CEUS findings (κ = 0.80, P = 0.010), but other grayscale and CDUS findings did not agree with DMSA scan results (P > 0.05). All lesions were best observed in the late parenchymal phase on CEUS. CONCLUSION: CEUS can reveal renal perfusion defects in pediatric patients with suspected APN without radiation exposure or sedation; therefore, CEUS may be a feasible and valuable diagnostic technique.

The spectrum of imaging manifestations of Gorham-Stout disease: a novel dynamic contrast-enhanced MR lymphangiography.

BACKGROUND: To describe the radiological features of Gorham-Stout disease (GSD) as evaluated using plain radiography and dynamic contrast-enhanced magnetic resonance lymphangiography (DCMRL) imaging techniques. METHODS: Clinical and conventional imaging data were retrospectively reviewed for 15 patients with GSD between January 2001 and December 2020. After December 2018, DCMRL examinations were performed for lymphatic vessel evaluation in patients with GSD and reviewed in four patients. RESULTS: The median age at diagnosis was 9 years (range: 2 months-53 years). The clinical manifestations were dyspnea in seven patients (46.7%), sepsis in 12 (80.0%), orthopedic problems in seven (46.7%), and bloody chylothorax in seven (46.7%). The common sites of osseous involvement were the spine (73.3%) and pelvic bone (60.0%). Among the non-osseous involvements, peri-osseous infiltrative soft-tissue abnormalities adjacent to the area of bone involvement were the most common (86.7%), followed by splenic cysts (26.7%) and interstitial thickening (26.7%). DCMRL demonstrated weak central conducting lymphatic flow in two patients with abnormal giant tortuous thoracic ducts and no flow in one patient. All patients who underwent DCMRL in this study presented with altered anatomical lymphatics and functional flow with collateralization. CONCLUSION: DCMRL imaging and plain radiography are very useful for determining the extent of GSD. DCMRL is a novel imaging tool for the visualization of abnormal lymphatics in patients with GSD, which helps in further treatment. Therefore, in patients with GSD, it might be necessary to obtain not only plain radiographs but also MR and DCMRL images.

Usefulness of two-dimensional shear wave elastography in diagnosing hepatic veno-occlusive disease in pediatric patients undergoing hematopoietic stem cell transplantation.

PURPOSE: This study aimed to evaluate the usefulness of two-dimensional shear wave elastography (2D-SWE) in diagnosing hepatic veno-occlusive disease (VOD) in pediatric patients. METHODS: This study retrospectively included pediatric patients who underwent hematopoietic stem cell transplantation (HSCT) between November 2019 and January 2021. All 34 patients (8.7±5.0 years) were examined using 2D-SWE for an initial diagnosis. A subgroup analysis was performed using the data from follow-up examinations of patients diagnosed with VOD. The characteristics of the initial VOD diagnosis were compared with the longitudinal changes observed in VOD patients who underwent multiple ultrasound examinations. RESULTS: In total, 19 patients were diagnosed with VOD at 17.6±9.4 days after HSCT. All VOD patients showed hepatomegaly, ascites, and gallbladder wall thickening. Liver stiffness was higher in VOD patients than in non-VOD patients (12.4±1.1 vs. 6.3±0.8 kPa, P<0.001). Liver stiffness values above 7.2 kPa showed 84.2% sensitivity and 93.3% specificity in distinguishing VOD from non-VOD (area under the curve, 0.925; 95% confidence interval, 0.780 to 0.987; P<0.001). A subgroup analysis of 11 patients showed a linear decrease in liver stiffness values after VOD diagnosis with treatment (first, second, and third follow-ups; 13.5±1.7, 11.3±1.4, and 9.5±0.8 kPa, respectively), but without statistical significance in the pairwise analysis. CONCLUSION: Liver stiffness measured using 2D-SWE increased in pediatric patients who develop VOD after HSCT. Therefore, liver stiffness can be a predictive and quantitative parameter for diagnosing VOD.

Deep Learning-Based Computed Tomography Image Standardization to Improve Generalizability of Deep Learning-Based Hepatic Segmentation.

OBJECTIVE: We aimed to investigate whether image standardization using deep learning-based computed tomography (CT) image conversion would improve the performance of deep learning-based automated hepatic segmentation across various reconstruction methods. MATERIALS AND METHODS: We collected contrast-enhanced dual-energy CT of the abdomen that was obtained using various reconstruction methods, including filtered back projection, iterative reconstruction, optimum contrast, and monoenergetic images with 40, 60, and 80 keV. A deep learning based image conversion algorithm was developed to standardize the CT images using 142 CT examinations (128 for training and 14 for tuning). A separate set of 43 CT examinations from 42 patients (mean age, 10.1 years) was used as the test data. A commercial software program (MEDIP PRO v2.0.0.0, MEDICALIP Co. Ltd.) based on 2D U-NET was used to create liver segmentation masks with liver volume. The original 80 keV images were used as the ground truth. We used the paired t-test to compare the segmentation performance in the Dice similarity coefficient (DSC) and difference ratio of the liver volume relative to the ground truth volume before and after image standardization. The concordance correlation coefficient (CCC) was used to assess the agreement between the segmented liver volume and ground-truth volume. RESULTS: The original CT images showed variable and poor segmentation performances. The standardized images achieved significantly higher DSCs for liver segmentation than the original images (DSC [original, 5.40%-91.27%] vs. [standardized, 93.16%-96.74%], all P < 0.001). The difference ratio of liver volume also decreased significantly after image conversion (original, 9.84%-91.37% vs. standardized, 1.99%-4.41%). In all protocols, CCCs improved after image conversion (original, -0.006-0.964 vs. standardized, 0.990-0.998). CONCLUSION: Deep learning-based CT image standardization can improve the performance of automated hepatic segmentation using CT images reconstructed using various methods. Deep learning-based CT image conversion may have the potential to improve the generalizability of the segmentation network.

Efficacy and safety of mucous fistula refeeding in preterm infants: an exploratory randomized controlled trial.

BACKGROUND: This study aimed to evaluate whether mucous fistula refeeding (MFR) is safe and beneficial for the growth and intestinal adaptation of preterm infants with enterostomies. METHODS: This exploratory randomized controlled trial enrolled infants born before 35 weeks' gestation with enterostomy. If the stomal output was ≥ 40 mL/kg/day, infants were assigned to the high-output MFR group and received MFR. If the stoma output was < 40 mL/kg/day, infants were randomized to the normal-output MFR group or the control group. Growth, serum citrulline levels, and bowel diameter in loopograms were compared. The safety of MFR was evaluated. RESULTS: Twenty infants were included. The growth rate increased considerably, and the colon diameter was significantly larger after MFR. However, the citrulline levels did not significantly differ between the normal-output MFR and the control group. One case of bowel perforation occurred during the manual reduction for stoma prolapse. Although the association with MFR was unclear, two cases of culture-proven sepsis during MFR were noted. CONCLUSIONS: MFR benefits the growth and intestinal adaptation of preterm infants with enterostomy and can be safely implemented with a standardized protocol. However, infectious complications need to be investigated further. TRIAL REGISTRATION: clinicaltrials.gov NCT02812095, retrospectively registered on June 6, 2016.

A knowledge interaction learning for multi-echo MRI motion artifact correction towards better enhancement of SWI.

Patient movement during Magnetic Resonance Imaging (MRI) scan can cause severe degradation of image quality. In Susceptibility Weighted Imaging (SWI), several echoes are typically measured during a single repetition period, where the earliest echoes show less contrast between various tissues, while the later echoes are more susceptible to artifacts and signal dropout. In this paper, we propose a knowledge interaction paradigm that jointly learns feature details from multiple distorted echoes by sharing their knowledge with unified training parameters, thereby simultaneously reducing motion artifacts of all echoes. This is accomplished by developing a new scheme that boosts a Single Encoder with Multiple Decoders (SEMD), which assures that the generated features not only get fused but also learned together. We called the proposed method Knowledge Interaction Learning between Multi-Echo data (KIL-ME-based SEMD). The proposed KIL-ME-based SEMD allows to share information and gain an understanding of the correlations between the multiple echoes. The main purpose of this work is to correct the motion artifacts and maintain image quality and structure details of all motion-corrupted echoes towards generating high-resolution susceptibility enhanced contrast images, i.e., SWI, using a weighted average of multi-echo motion-corrected acquisitions. We also compare various potential strategies that might be used to address the problem of reducing artifacts in multi-echoes data. The experimental results demonstrate the feasibility and effectiveness of the proposed method, reducing the severity of motion artifacts and improving the overall clinical image quality of all echoes with their associated SWI maps. Significant improvement of image quality is observed using both motion-simulated test data and actual volunteer data with various motion severity strengths. Eventually, by enhancing the overall image quality, the proposed network can increase the effectiveness of the physicians' capability to evaluate and correctly diagnose brain MR images.

Application of 3D printing technology for pre-operative evaluation, education and informed consent in pediatric retroperitoneal tumors.

To investigate usefulness of 3D printing for preoperative evaluations, student and resident education, and communication with parents or guardians of patients with pediatric retroperitoneal tumors. Ten patients planning retroperitoneal tumor resection between March and November 2019 were included. Preoperative computed tomography (CT) images were used for 3D reconstruction and printing. Surveyed items were understanding of preoperative lesions with 3 different modules (CT, 3D reconstruction, and 3D printing) by students, residents, and specialists; satisfaction of specialists; and comprehension by guardians after preoperative explanations with each module. The median age at operation was 4.2 years (range, 1.8-18.1), and 8 patients were diagnosed with neuroblastoma. The 3D printing was the most understandable module for all groups (for students, residents, and specialists, P = 0.002, 0.027, 0.013, respectively). No significant intraoperative adverse events or immediate postoperative complications occurred. All specialists stated that 3D printing enhanced their understanding of cases. Guardians answered that 3D printing were the easiest to comprehend among the 3 modules (P = 0.007). Use of 3D printing in treatment of pediatric patients with retroperitoneal tumors was useful for preoperative planning, education, and parental explaining with obtaining informed consents.

Factors influencing outcomes of esophageal balloon dilatation for anastomosis site stenosis after esophageal atresia surgery.

BACKGROUND: Esophageal balloon dilatation is an effective treatment for anastomotic strictures, but the factors affecting the outcome of dilatation remain unclear. OBJECTIVE: To investigate the predictive factors of esophageal balloon dilatation outcome in children with anastomotic stricture after esophageal atresia repair. MATERIALS AND METHODS: We retrospectively reviewed children with esophageal atresia who underwent esophageal balloon dilatation for postoperative strictures between August 2007 and February 2021. We investigated each child's age, weight and height; type of esophageal atresia surgery; shape, length and level of stricture; esophageal balloon dilatation balloon size; application of mitomycin; number of inflation sessions; and number of esophageal balloon dilatation sessions. The outcome of each esophageal balloon dilatation session was determined as improvement in stricture diameter between pre- and post-esophageal balloon dilatation esophagography. We used uni- and multivariate analyses with generalized estimating equations to evaluate outcome predictors. RESULTS: Overall, 69 children (mean age, 2.3 years; 45 boys) underwent 227 esophageal balloon dilatations. In the univariate analysis, the positive effect of esophageal balloon dilatation decreased with increased age, weight, height, balloon size and number of esophageal balloon dilatation sessions. Additionally, the positive effect was decreased in cervical-level strictures and with the application of mitomycin during esophageal balloon dilatation. In the multivariate analysis, independent prognostic factors of the positive esophageal balloon dilatation effect were age (incidence rate ratio [IRR]: -0.01; 95% confidence interval [CI]: -0.01, -0.002), shape of stricture (IRR: -0.54; 95% CI: -0.91, -0.18) and number of esophageal balloon dilatation sessions (IRR, -0.10; 95% CI: -0.14, -0.18). CONCLUSION: Repeated esophageal balloon dilatation, older age and eccentric stricture shape are associated with poor response to esophageal balloon dilatation in children with anastomotic strictures after esophageal atresia repair.