JUST-Net: Jointly unrolled cross-domain optimization based spatio-temporal reconstruction network for accelerated 3D myelin water imaging.

PURPOSE: We introduced a novel reconstruction network, jointly unrolled cross-domain optimization-based spatio-temporal reconstruction network (JUST-Net), aimed at accelerating 3D multi-echo gradient-echo (mGRE) data acquisition and improving the quality of resulting myelin water imaging (MWI) maps. METHOD: An unrolled cross-domain spatio-temporal reconstruction network was designed. The main idea is to combine frequency and spatio-temporal image feature representations and to sequentially implement convolution layers in both domains. The k-space subnetwork utilizes shared information from adjacent frames, whereas the image subnetwork applies separate convolutions in both spatial and temporal dimensions. The proposed reconstruction network was evaluated for both retrospectively and prospectively accelerated acquisition. Furthermore, it was assessed in simulation studies and real-world cases with k-space corruptions to evaluate its potential for motion artifact reduction. RESULTS: The proposed JUST-Net enabled highly reproducible and accelerated 3D mGRE acquisition for whole-brain MWI, reducing the acquisition time from fully sampled 15:23 to 2:22 min within a 3-min reconstruction time. The normalized root mean squared error of the reconstructed mGRE images increased by less than 4.0%, and the correlation coefficients for MWI showed a value of over 0.68 when compared to the fully sampled reference. Additionally, the proposed method demonstrated a mitigating effect on both simulated and clinical motion-corrupted cases. CONCLUSION: The proposed JUST-Net has demonstrated the capability to achieve high acceleration factors for 3D mGRE-based MWI, which is expected to facilitate widespread clinical applications of MWI.

Novel Cultivation of six-year-old Korean Ginseng (Panax ginseng) in pot: From Non-Agrochemical Management to Increased Ginsenoside.

Background: Ginseng (Panax ginseng Meyer) is a perennial plant belonging to the Araliaceae family that is known to have various beneficial effects including improving memory loss and spatial cognitive ability, and anti-cancer and anti-diabetes activity. Its functional benefits also include improving liver function, regulating blood pressure, stress, and providing antioxidant activity. Usually, various agrochemicals are used in cultivating ginseng preventing from many diseases. Methods: FCGP (field cultivated ginseng in pot) was implemented by imitating MCWG (mountain cultivated wild ginseng). Pesticide analysis of pot cultivation was carried out and the contents of bioactive components such as ginsenoside were also analyzed. Results: FCGP ginsenoside content was higher than that of FCG (field cultivated ginseng) and MCWG. FCGP has been shown to have a relatively high antioxidant effect compared with cultivated ginseng. Conclusion: It was confirmed that ginseng can be grown for 6 years without resorting to use of pesticides. In addition, it was confirmed that effective accumulation of physiologically active ingredients such as ginsenoside is possible. Our result represents FCGP is a novel method of pesticide-free ginseng cultivation.

3D MR fingerprinting-derived myelin water fraction characterizing brain development and leukodystrophy.

BACKGROUND: Magnetic resonance fingerprinting (MRF) enables fast myelin quantification via the myelin water fraction (MWF), offering a noninvasive method to assess brain development and disease. However, MRF-derived MWF lacks histological evaluation and remains unexamined in relation to leukodystrophy. This study aimed to access MRF-derived MWF through histology in mice and establish links between myelin, development, and leukodystrophy in mice and children, demonstrating its potential applicability in animal and human studies. METHODS: 3D MRF was performed on normal C57BL/6 mice with different ages, megalencephalic leukoencephalopathy with subcortical cyst 1 wild type (MLC1 WT, control) mice, and MLC 1 knock-out (MLC1 KO, leukodystrophy) mice using a 3 T MRI. MWF values were analyzed from 3D MRF data, and histological myelin quantification was carried out using immunohistochemistry to anti-proteolipid protein (PLP) in the corpus callosum and cortex. The associations between 'MWF and PLP' and 'MWF and age' were evaluated in C57BL/6 mice. MWF values were compared between MLC1 WT and MLC1 KO mice. MWF of normal developing children were retrospectively collected and the association between MWF and age was assessed. RESULTS: In 35 C57BL/6 mice (age range; 3 weeks-48 weeks), MWF showed positive relations with PLP immunoreactivity in the corpus callosum (ß = 0.0006, P = 0.04) and cortex (ß = 0.0005, P = 0.006). In 12-week-old C57BL/6 mice MWF showed positive relations with PLP immunoreactivity (ß = 0.0009, P = 0.003, R2 = 0.54). MWF in the corpus callosum (ß = 0.0022, P < 0.001) and cortex (ß = 0.0010, P < 0.001) showed positive relations with age. Seven MLC1 WT and 9 MLC1 KO mice showed different MWF values in the corpus callous (P < 0.001) and cortex (P < 0.001). A total of 81 children (median age, 126 months; range, 0-199 months) were evaluated and their MWF values according to age showed the best fit for the third-order regression model (adjusted R2 range, 0.44-0.94, P < 0.001). CONCLUSION: MWF demonstrated associations with histologic myelin quantity, age, and the presence of leukodystrophy, underscoring the potential of 3D MRF-derived MWF as a rapid and noninvasive quantitative indicator of brain myelin content in both mice and humans.

A regional brain volume-based age prediction model for neonates and the derived brain maturation index.

OBJECTIVE: To develop a postmenstrual age (PMA) prediction model based on segmentation volume and to evaluate the brain maturation index using the proposed model. METHODS: Neonatal brain MRIs without clinical illness or structural abnormalities were collected from four datasets from the Developing Human Connectome Project, the Catholic University of Korea, Hammersmith Hospital (HS), and Dankook University Hospital (DU). T1- and T2-weighted images were used to train a brain segmentation model. Another model to predict the PMA of neonates based on segmentation data was developed. Accuracy was assessed using mean absolute error (MAE), root mean square error (RMSE), and mean error (ME). The brain maturation index was calculated as the difference between the PMA predicted by the model and the true PMA, and its correlation with postnatal age was analyzed. RESULTS: A total of 247 neonates (mean gestation age 37 ± 4 weeks; range 24-42 weeks) were included. Thirty-one features were extracted from each neonate and the three most contributing features for PMA prediction were the right lateral ventricle, left caudate, and corpus callosum. The predicted and true PMA were positively correlated (coefficient = 0.88, p < .001). MAE, RMSE, and ME of the external dataset of HS and DU were 1.57 and 1.33, 1.79 and 1.37, and 0.37 and 0.06 weeks, respectively. The brain maturation index negatively correlated with postnatal age (coefficient = - 0.24, p < .001). CONCLUSION: A model that calculates the regional brain volume can predict the PMA of neonates, which can then be utilized to show the brain maturation degree. CLINICAL RELEVANCE STATEMENT: A brain maturity index based on regional volume of neonate's brain can be used to measure brain maturation degree, which can help identify the status of early brain development. KEY POINTS: • Neonatal brain MRI segmentation model could be used to assess neonatal brain maturation status. • A postmenstrual age (PMA) prediction model was developed based on a neonatal brain MRI segmentation model. • The brain maturation index, derived from the PMA prediction model, enabled the estimation of the neonatal brain maturation status.

Fetal brain tissue annotation and segmentation challenge results.

In-utero fetal MRI is emerging as an important tool in the diagnosis and analysis of the developing human brain. Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context. However, manual segmentation of cerebral structures is time-consuming and prone to error and inter-observer variability. Therefore, we organized the Fetal Tissue Annotation (FeTA) Challenge in 2021 in order to encourage the development of automatic segmentation algorithms on an international level. The challenge utilized FeTA Dataset, an open dataset of fetal brain MRI reconstructions segmented into seven different tissues (external cerebrospinal fluid, gray matter, white matter, ventricles, cerebellum, brainstem, deep gray matter). 20 international teams participated in this challenge, submitting a total of 21 algorithms for evaluation. In this paper, we provide a detailed analysis of the results from both a technical and clinical perspective. All participants relied on deep learning methods, mainly U-Nets, with some variability present in the network architecture, optimization, and image pre- and post-processing. The majority of teams used existing medical imaging deep learning frameworks. The main differences between the submissions were the fine tuning done during training, and the specific pre- and post-processing steps performed. The challenge results showed that almost all submissions performed similarly. Four of the top five teams used ensemble learning methods. However, one team's algorithm performed significantly superior to the other submissions, and consisted of an asymmetrical U-Net network architecture. This paper provides a first of its kind benchmark for future automatic multi-tissue segmentation algorithms for the developing human brain in utero.

MRI-visible Perivascular Spaces in the Neonatal Brain.

Background Mounting evidence suggests that perivascular spaces (PVSs) visible at MRI reflect the function of the glymphatic system. Understanding PVS burden in neonates may guide research on early glymphatic-related pathologic abnormalities. Purpose To perform a visual and volumetric evaluation of PVSs that are visible at MRI in neonates and to evaluate potential associations with maturation, sex, and preterm birth. Materials and Methods In this retrospective study, T2-weighted brain MRI scans in neonates from the Developing Human Connectome Project were used for visual grading (grades 0-4) of PVSs in the basal ganglia (BG) and white matter (WM) and for volumetric analysis of BG PVSs. The BG PVS fraction was obtained by dividing the BG PVS volume by the deep gray matter volume. The association between postmenstrual age at MRI and BG PVS burden was evaluated using linear regression. PVS burden was compared according to sex and preterm birth using the Mann-Whitney test. Results A total of 244 neonates were evaluated (median gestational age at birth, 39 weeks; IQR, 6 weeks; 145 male neonates; 59%), including 88 preterm neonates (median gestational age at birth, 33 weeks; IQR, 6 weeks; 53 male neonates; 60%) and 156 term neonates (median gestational age at birth, 40 weeks; IQR, 2 weeks; 92 male neonates; 59%). For BG PVSs, all neonates showed either grade 0 (90 of 244; 37%) or grade 1 (154 of 244; 63%), and for WM PVSs, most neonates showed grade 0 (227 of 244; 93%). The BG PVS fraction demonstrated a negative relationship with postmenstrual age at MRI (r = -0.008; P < .001). No evidence of differences was found between the sexes for BG PVS volume (P = .07) or BG PVS fraction (P = .28). The BG PVS volume was smaller in preterm neonates than in term neonates (median, 45.3 mm3 [IQR, 15.2 mm3] vs 49.9 mm3 [IQR, 21.3 mm3], respectively; P = .04). Conclusion The fraction of perivascular spaces (PVSs) in the basal ganglia (BG) was lower with higher postmenstrual age at MRI. Preterm birth affected the volume of PVSs in the BG, but sex did not. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Huisman in this issue.

MRI-visible Dilated Perivascular Space in the Brain by Age: The Human Connectome Project.

Background Dilated perivascular spaces (dPVS) are associated with aging and various disorders; however, the effect of age on dPVS burden in young populations and normative data have not been fully evaluated. Purpose To investigate the dPVS burden and provide normative data according to age in a healthy population, including children. Materials and Methods In this retrospective study, three-dimensional T2-weighted brain MRI scans from the Human Connectome Project data sets were used for visual grading (grade 0, 1, 2, 3, 4 for 0, 1-10, 11-20, 21-40, and >40 dPVS on a single section of either hemispheric region) and automated volumetry of dPVS in basal ganglia (BGdPVS) and white matter (WMdPVS). Linear and nonlinear regression were performed to assess the association of dPVS volume with age. Optimal cutoff ages were determined with use of the maximized continuous-scale C-index. Participants were grouped by cutoff values. Linear regression was performed to assess the age-dPVS volume relationship in each age group. Normative data of dPVS visual grades were provided per age decade. Results A total of 1789 participants (mean age, 35 years; age range, 8-100 years; 1006 female participants) were evaluated. Age was related to dPVS volume in all regression models (R2 range, 0.41-0.55; P < .001). Age-dPVS volume relationships were altered at the mid-30s and age 55 years; BGdPVS and WMdPVS volumes negatively correlated with age until the mid-30s (ß, -1.2 and -7.8), then positively until age 55 years (ß, 3.3 and 54.1) and beyond (ß, 3.9 and 42.8; P < .001). The 90th percentile for dPVS grades was grade 1 for age 49 years and younger, grade 2 for age 50-69 years, and grade 3 for age 70 years and older (overall, grade 2) for BGdPVS, and grade 3 for age 49 years and younger and grade 4 for age 50 years and older (overall, grade 3) for WMdPVS. Conclusion Dilated perivascular spaces (dPVS) showed a biphasic volume pattern with brain MRI, lower volumes until the mid-30s, then higher afterward. Grades of 3 or higher and 4 might be considered pathologic dPVS in basal ganglia and white matter, respectively. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Bapuraj and Chaudhary in this issue.

Evaluating the Image Quality of Neck Structures Scanned on Chest CT with Low-Concentration-Iodine Contrast Media.

BACKGROUND: The purpose of this study was to investigate and compare the image quality of low-concentration-iodine (240 mgI/mL) contrast media (CM) and high-concentration-iodine (320 mgI/mL) CM according to the radiation dose. METHODS: A total of 366 CT examinations were examined. Based on an assessment of quantitative and qualitative parameters by two radiologists, the quality was compared between Group A (low-concentration-iodine CM) and Group B (high-concentration-iodine CM) images of thyroid gland, sternocleidomastoid muscle (SCM), internal jugular vein (IJV), and common carotid artery (CCA). Another subgroup analysis compared Group a, (using ≤90 kVp in Group A), and Group b, (using ≥100 kVp in Group B) for finding the difference in image quality when the tube voltage is lowered. RESULTS: Image quality did not differ between Groups A and B or between Groups a and b. The signal-to-noise ratio and contrast-to-noise ratio were significantly higher for Group B than Group A for the thyroid gland, IJV, and CCA. No statistical differences were found in the comparison of all structures between Groups a and b. CONCLUSION: There was no significant difference in image quality based on CM concentration with variable radiation doses. Therefore, if an appropriate CT protocol is applied, clinically feasible neck CT images can be obtained even using low-concentration-iodine CM.

Accelerated 3D T2-weighted images using compressed sensing for pediatric brain imaging.

PURPOSE: The purpose of this study was to compare the image quality of the 3D T2-weighted images accelerated using conventional method (CAI-SPACE) with the images accelerated using compressed sensing (CS-SPACE) in pediatric brain imaging. METHODS: A total of 116 brain MRI (53 with CAI-SPACE and 63 with CS-SPACE) were obtained from children 16 years old or younger. Quantitative image quality was evaluated using the apparent signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). The sequences were qualitatively evaluated for overall image quality, general artifact, cerebrospinal fluid (CSF)-related artifact, and grey-white matter differentiation. The two sequences were compared for the total and two age groups (< 24 months vs. ≥ 24 months). RESULTS: Compressed sensing application in 3D T2-weighted imaging resulted in 8.5% reduction in scanning time. Quantitative image quality analysis showed higher apparent SNR (median [Interquartile range]; 29 [25] vs. 23 [14], P = 0.005) and CNR (0.231 [0.121] vs. 0.165 [0.120], P = 0.027) with CS-SPACE compared to CAI-SPACE. Qualitative image quality analysis showed better image quality with CS-SPACE for general (P = 0.024) and CSF-related artifact (P < 0.001). CSF-related artifacts reduction was prominent in the older age group (≥ 24 months). Overall image quality (P = 0.162) and grey-white matter differentiation (P = 0.397) were comparable between CAI-SPACE and CS-SPACE. CONCLUSION: Compressed sensing application in 3D T2-weighted images modestly reduced acquisition time and lowered CSF-related artifact compared to conventional images of the pediatric brain.

Highly accelerated 3D MPRAGE using deep neural network-based reconstruction for brain imaging in children and young adults.

OBJECTIVES: This study aimed to accelerate the 3D magnetization-prepared rapid gradient-echo (MPRAGE) sequence for brain imaging through the deep neural network (DNN). METHODS: This retrospective study used the k-space data of 240 scans (160 for the training set, mean ± standard deviation age, 93 ± 80 months, 94 males; 80 for the test set, 106 ± 83 months, 44 males) of conventional MPRAGE (C-MPRAGE) and 102 scans (77 ± 74 months, 52 males) of both C-MPRAGE and accelerated MPRAGE. All scans were acquired with 3T scanners. DNN was developed with simulated-acceleration data generated by under-sampling. Quantitative error metrics were compared between images reconstructed with DNN, GRAPPA, and E-SPIRIT using the paired t-test. Qualitative image quality was compared between C-MPRAGE and accelerated MPRAGE reconstructed with DNN (DNN-MPRAGE) by two readers. Lesions were segmented and the agreement between C-MPRAGE and DNN-MPRAGE was assessed using linear regression. RESULTS: Accelerated MPRAGE reduced scan times by 38% compared to C-MPRAGE (142 s vs. 320 s). For quantitative error metrics, DNN showed better performance than GRAPPA and E-SPIRIT (p < 0.001). For qualitative evaluation, overall image quality of DNN-MPRAGE was comparable (p > 0.999) or better (p = 0.025) than C-MPRAGE, depending on the reader. Pixelation was reduced in DNN-MPRAGE (p < 0.001). Other qualitative parameters were comparable (p > 0.05). Lesions in C-MPRAGE and DNN-MPRAGE showed good agreement for the dice similarity coefficient (= 0.68) and linear regression (R2 = 0.97; p < 0.001). CONCLUSIONS: DNN-MPRAGE reduced acquisition time by 38% and revealed comparable image quality to C-MPRAGE. KEY POINTS: • DNN-MPRAGE reduced acquisition times by 38%. • DNN-MPRAGE outperformed conventional reconstruction on accelerated scans (SSIM of DNN-MPRAGE = 0.96, GRAPPA = 0.43, E-SPIRIT = 0.88; p < 0.001). • Compared to C-MPRAGE scans, DNN-MPRAGE showed improved mean scores for overall image quality (2.46 vs. 2.52; p < 0.001) or comparable perceived SNR (2.56 vs. 2.58; p = 0.08).

Three-Dimensional Magnetic Resonance Fingerprinting in Neonates: Quantifying Regional Difference and Maturation in the Brain.

OBJECTIVES: Magnetic resonance fingerprinting (MRF) allows the simultaneous measurement of multiple tissue properties in a single acquisition. Three-dimensional (3D) MRF with high spatial resolution can be used for neonatal brain imaging. The aim of this study is to apply 3D MRF to neonates and show regional differences and maturation in the brain. MATERIALS AND METHODS: In this prospective study, 3D MRF using hybrid radial-interleaved acquisition was performed on phantoms and neonates from December 2019 to October 2020. For the reconstruction of 3D MRF, singular value decomposition was applied to reduce reconstruction time, and the iterative reconstruction technique was applied to improve image quality. The accuracies of T1 and T2 values derived from 3D MRF were evaluated in a phantom experiment. Regional T1 and T2 values were obtained from neonates' brain T1 and T2 maps derived from 3D MRF. Regional T1 and T2 values were compared, and their changes according to corrected gestational age were evaluated. RESULTS: The acquisition time for 3D MRF with a spatial resolution of 0.7 × 0.7 × 2 mm3 was less than 5 minutes. The phantom study showed high correlation between T1 and T2 values derived from 3D MRF and those from conventional spin echo sequences (T1, R2 = 0.998, P < 0.001; T2, R2 = 0.998, P < 0.001). Three-dimensional MRF was performed in 25 neonates (15 boys, 10 girls; median corrected gestational age, 263 days; interquartile range, 10 days). In neonates, T1 and T2 values differed in the frontal (median [interquartile range], 2785 [2684-2888] milliseconds and 189.8 [176.7-222.9] milliseconds), parietal (2849 [2741-2950] milliseconds and 191.6 [167.5-232.9] milliseconds), and occipital white matter (2621 [2513-2722] milliseconds and 162.9 [143.5-186.1] milliseconds), showing lower values in occipital white matter (P < 0.001). Regional T1 values showed a negative relationship with corrected gestational age (coefficient, -0.775 to -0.480; P < 0.05). CONCLUSIONS: Fast and high spatial resolution 3D MRF was applied to neonates. T1 and T2 maps derived from 3D MRF enabled the quantification of regional differences and maturation in the neonatal brain.

Association of Cerebral Blood Flow and Brain Tissue Relaxation Time With Neurodevelopmental Outcomes of Preterm Neonates: Multidelay Arterial Spin Labeling and Synthetic MRI Study.

OBJECTIVES: Both cerebral blood flow (CBF) and brain tissue relaxation times are known to reflect maturation in the neonatal brain. However, we do not yet know if these factors are associated with neurodevelopmental outcomes. The objective of this study was to acquire CBF and relaxation time in preterm neonates, using multidelay arterial spin labeling and synthetic magnetic resonance imaging (MRI), and show their association with later neurodevelopmental outcomes. MATERIALS AND METHODS: In this prospective study, preterm neonates were recruited, and multidelay arterial spin labeling and synthetic MRI were performed between September 2017 and December 2018. These neonates underwent the Bayley Scales of Infant Development test at 18 months of age, and both cognitive and motor outcome scores were measured. Transit time-corrected CBF and T1 and T2 relaxation time values were measured for different brain regions. The measured values were correlated with gestational age (GA) at birth and corrected GA at the MRI scan. Simple and multiple linear regression analyses were performed for the measured values and neurodevelopmental outcome scores. RESULTS: Forty-nine neonates (median [interquartile range] GA, 30 [2] weeks, 209 [17] days; 28 boys) underwent MRI scans at or near term-equivalent age (median [interquartile range] corrected GA, 37 [2] weeks, 258 [14] days). Transit time-corrected CBF (coefficient, 0.31-0.59) and relaxation time (coefficient, -0.39 to -0.86) values showed significant correlation with corrected GA but not with GA. After controlling for GA, the frontal white matter CBF in preterm neonates showed a negative relationship with cognitive outcome scores (ß = -0.97; P = 0.029). Frontal white matter T1 relaxation times showed a positive relationship with cognitive outcome scores (ß = 0.03; P = 0.025) after controlling for GA. CONCLUSIONS: Higher CBF values and lower T1 relaxation times in frontal white matter were associated with poorer cognitive outcomes. As quantitative neuroimaging markers, CBF and relaxation times may help predict neurodevelopmental outcomes in preterm neonates.

3D MR fingerprinting (MRF) for simultaneous T1 and T2 quantification of the bone metastasis: Initial validation in prostate cancer patients.

PURPOSE: To investigate the feasibility of using 3-dimensional MRF for bone marrow evaluation in the field of view of prostate MRI for T1 and T2 quantification of prostate cancer bone metastases, as well as comparing it to the ADC value. METHODS: In this retrospective study, 30 prostate MRIs were included: 14 cases with prostate cancer bone metastasis and 16 cases without prostate cancer (control). MRF was obtained twice before (nonenhanced [NE] MRF) and after contrast injection (contrast-enhanced [CE] MRF), and T1 and T2 maps were generated from each MRF. Two radiologists independently drew regions of interest (ROIs) on the MRF maps and the ADC maps. Mann-Whitney U tests and the area under the receiver operating characteristic curve (AUROC) evaluated the two-reader means of T1, T2 and ADC values between bone metastasis and normal bone. RESULTS: There were 83 ROIs, including 39 bone metastases and 44 normal bone. The two-reader average ADC, NE T2 and CE T2 values were significantly lower and NE T1 and CE T1 values were significantly higher in metastatic bone compared with normal bone (P < 0.001). The AUROC of the ADC was lowest (0.685), which was significantly lower than those of NE T1 (1.0, P = 0.001), NE T2 (0.932, P = 0.004), and CE T2 (0.876, P = 0.031). CONCLUSION: MRF to assess the pelvic bone during a prostate gland evaluation provides a reliable parametric map for skeletal work-up. With higher diagnostic performance than the ADC value, NE MRF is a potential alternative for quantifying bone marrow metastases in prostate cancer patients.

Genetic Analysis Using a Next Generation Sequencing-Based Gene Panel in Patients With Skeletal Dysplasia: A Single-Center Experience.

Skeletal dysplasia (SD), a heterogeneous disease group with rare incidence and various clinical manifestations, is associated with multiple causative genes. For clinicians, accurate diagnosis of SD is clinically and genetically difficult. The development of next-generation sequencing (NGS) has substantially aided in the genetic diagnosis of SD. In this study, we conducted a targeted NGS of 437 genes - included in the nosology of SD published in 2019 - in 31 patients with a suspected SD. The clinical and genetic diagnoses were confirmed in 16 out of the 31 patients, and the diagnostic yield was 51.9%. In these patients, 18 pathogenic variants were found in 13 genes (COL2A1, MYH3, COMP, MATN3, CTSK, EBP, CLCN7, COL1A2, EXT1, TGFBR1, SMAD3, FIG4, and ARID1B), of which, four were novel variants. The diagnosis rate was very high in patients with a suspected familial SD and with radiological evidence indicating clinical SD (11 out of 15, 73.3%). In patients with skeletal involvement and other clinical manifestations including dysmorphism or multiple congenital anomalies, and various degrees of developmental delay/intellectual disability, the diagnosis rate was low (5 out of 16, 31.2%) but rare syndromic SD could be diagnosed. In conclusion, NGS-based gene panel sequencing can be helpful in diagnosing SD which has clinical and genetic heterogeneity. To increase the diagnostic yield of suspected SD patients, it is important to categorize patients based on the clinical features, family history, and radiographic evidence.

Deep learning for end-to-end kidney cancer diagnosis on multi-phase abdominal computed tomography.

In 2020, it is estimated that 73,750 kidney cancer cases were diagnosed, and 14,830 people died from cancer in the United States. Preoperative multi-phase abdominal computed tomography (CT) is often used for detecting lesions and classifying histologic subtypes of renal tumor to avoid unnecessary biopsy or surgery. However, there exists inter-observer variability due to subtle differences in the imaging features of tumor subtypes, which makes decisions on treatment challenging. While deep learning has been recently applied to the automated diagnosis of renal tumor, classification of a wide range of subtype classes has not been sufficiently studied yet. In this paper, we propose an end-to-end deep learning model for the differential diagnosis of five major histologic subtypes of renal tumors including both benign and malignant tumors on multi-phase CT. Our model is a unified framework to simultaneously identify lesions and classify subtypes for the diagnosis without manual intervention. We trained and tested the model using CT data from 308 patients who underwent nephrectomy for renal tumors. The model achieved an area under the curve (AUC) of 0.889, and outperformed radiologists for most subtypes. We further validated the model on an independent dataset of 184 patients from The Cancer Imaging Archive (TCIA). The AUC for this dataset was 0.855, and the model performed comparably to the radiologists. These results indicate that our model can achieve similar or better diagnostic performance than radiologists in differentiating a wide range of renal tumors on multi-phase CT.

Growth of ZnO Nanorods on ITO Film for Piezoelectric Nanogenerators.

Piezoelectric nanogenerators (NGs) consist of zinc oxide nanorods (ZNRs), and polydimethylsiloxane (PDMS) layers were fabricated on indium tin oxide (ITO)-coated substrate for the energy harvesting system. The formation of seed layers by an optimized aqueous solution method greatly helped the growth of well-aligned ZNRs for NGs. Polyethylenimine (PEI) was added to increase the aspect ratio of ZNRs, which reached up to 24:1, showing the best energy harvesting performance of NGs. The formation of PDMS layers on the ZNRs increased the work function difference for the top Ag electrode. The thickness of PDMS layers was optimized as 80 µm, which showed the maximum work function difference, resulting in the enhancement of charge density. Piezoelectric NGs made of ZNRs of the highest aspect ratio of 24:1 with an 80-µm-thick PDMS layer achieved the highest current density of 2270.1 nA/cm2, which could be sufficient to drive low-power electronics.

Establishment of Local Diagnostic Reference Levels of Pediatric Abdominopelvic and Chest CT Examinations Based on the Body Weight and Size in Korea.

OBJECTIVE: The purposes of this study were to analyze the radiation doses for pediatric abdominopelvic and chest CT examinations from university hospitals in Korea and to establish the local diagnostic reference levels (DRLs) based on the body weight and size. MATERIALS AND METHODS: At seven university hospitals in Korea, 2494 CT examinations of patients aged 15 years or younger (1625 abdominopelvic and 869 chest CT examinations) between January and December 2017 were analyzed in this study. CT scans were transferred to commercial automated dose management software for the analysis after being de-identified. DRLs were calculated after grouping the patients according to the body weight and effective diameter. DRLs were set at the 75th percentile of the distribution of each institution's typical values. RESULTS: For body weights of 5, 15, 30, 50, and 80 kg, DRLs (volume CT dose index [CTDIvol]) were 1.4, 2.2, 2.7, 4.0, and 4.7 mGy, respectively, for abdominopelvic CT and 1.2, 1.5, 2.3, 3.7, and 5.8 mGy, respectively, for chest CT. For effective diameters of < 13 cm, 14-16 cm, 17-20 cm, 21-24 cm, and > 24 cm, DRLs (size-specific dose estimates [SSDE]) were 4.1, 5.0, 5.7, 7.1, and 7.2 mGy, respectively, for abdominopelvic CT and 2.8, 4.6, 4.3, 5.3, and 7.5 mGy, respectively, for chest CT. SSDE was greater than CTDIvol in all age groups. Overall, the local DRL was lower than DRLs in previously conducted dose surveys and other countries. CONCLUSION: Our study set local DRLs in pediatric abdominopelvic and chest CT examinations for the body weight and size. Further research involving more facilities and CT examinations is required to develop national DRLs and update the current DRLs.

Brain MRI radiomics analysis may predict poor psychomotor outcome in preterm neonates.

OBJECTIVES: This study aimed to apply a radiomics approach to predict poor psychomotor development in preterm neonates using brain MRI. METHODS: Prospectively enrolled preterm neonates underwent brain MRI near or at term-equivalent age and neurodevelopment was assessed at a corrected age of 12 months. Two radiologists visually assessed the degree of white matter injury. The radiomics analysis on white matter was performed using T1-weighted images (T1WI) and T2-weighted images (T2WI). A total of 1906 features were extracted from the images and the minimum redundancy maximum relevance algorithm was used to select features. A prediction model for the binary classification of the psychomotor developmental index was developed and eightfold cross-validation was performed. The diagnostic performance of the model was evaluated using the AUC with and without including significant clinical and DTI parameters. RESULTS: A total of 46 preterm neonates (median gestational age, 29 weeks; 26 males) underwent brain MRI (median corrected gestational age, 37 weeks). Thirteen of 46 (28.3%) neonates showed poor psychomotor outcomes. There was one neonate among 46 with moderate to severe white matter injury on visual assessment. For the radiomics analysis, twenty features were selected for each analysis. The AUCs of prediction models based on T1WI, T2WI, and both T1WI and T2WI were 0.925, 0.834, and 0.902. Including gestational age or DTI parameters did not improve the prediction performance of T1WI. CONCLUSIONS: A radiomics analysis of white matter using early T1WI or T2WI could predict poor psychomotor outcomes in preterm neonates. KEY POINTS: • Radiomics analysis on T1-weighted images of preterm neonates showed the highest diagnostic performance (AUC, 0.925) for predicting poor psychomotor outcomes. • In spite of 45 of 46 neonates having no significant white matter injury on visual assessment, the radiomics analysis of early brain MRI showed good diagnostic performance (sensitivity, 84.6%; specificity, 78.8%) for predicting poor psychomotor outcomes. • Radiomics analysis on early brain MRI can help to predict poor neurodevelopmental outcomes in preterm neonates.

Split-Attention U-Net: A Fully Convolutional Network for Robust Multi-Label Segmentation from Brain MRI.

Multi-label brain segmentation from brain magnetic resonance imaging (MRI) provides valuable structural information for most neurological analyses. Due to the complexity of the brain segmentation algorithm, it could delay the delivery of neuroimaging findings. Therefore, we introduce Split-Attention U-Net (SAU-Net), a convolutional neural network with skip pathways and a split-attention module that segments brain MRI scans. The proposed architecture employs split-attention blocks, skip pathways with pyramid levels, and evolving normalization layers. For efficient training, we performed pre-training and fine-tuning with the original and manually modified FreeSurfer labels, respectively. This learning strategy enables involvement of heterogeneous neuroimaging data in the training without the need for many manual annotations. Using nine evaluation datasets, we demonstrated that SAU-Net achieved better segmentation accuracy with better reliability that surpasses those of state-of-the-art methods. We believe that SAU-Net has excellent potential due to its robustness to neuroanatomical variability that would enable almost instantaneous access to accurate neuroimaging biomarkers and its swift processing runtime compared to other methods investigated.

Diagnostic performance of contrast-enhanced ultrasound for acute pyelonephritis in children.

The objective of our study was to evaluate the performance of renal contrast-enhanced ultrasound (CEUS) against the 99m-labeled dimercaptosuccinic acid (DMSA) scan and computed tomography (CT) in children for the diagnosis of acute pyelonephritis. We included children who underwent both renal CEUS and the DMSA scan or CT. A total of 33 children (21 males and 12 females, mean age 26 ± 36 months) were included. Using the DMSA scan as the reference standard, the sensitivity, specificity, positive predictive value, and negative predictive value of CEUS was 86.8%, 71.4%, 80.5%, and 80.0%, respectively. When CT was used as the reference standard, the sensitivity, specificity, positive predictive value, and negative predictive value of CEUS was 87.5%, 80.0%, 87.5%, and 80.0%, respectively. The diagnostic accuracy of CEUS for the diagnosis of acute pyelonephritis was 80.3% and 84.6% compared to the DMSA scan and CT, respectively. Inter-observer (kappa = 0.54) and intra-observer agreement (kappa = 0.59) for renal CEUS was moderate. In conclusion, CEUS had good diagnostic accuracy for diagnosing acute pyelonephritis with moderate inter- and intra-observer agreement. As CEUS does not require radiation or sedation, it could play an important role in the future when diagnosing acute pyelonephritis in children.