Purpose To document the imaging findings associated with congenital Zika virus infection as found in the Instituto de Pesquisa in Campina Grande State Paraiba (IPESQ) in northeastern Brazil, where the congenital infection has been particularly severe. Materials and Methods From June 2015 to May 2016, 438 patients were referred to the IPESQ for rash occurring during pregnancy or for suspected fetal central nervous system abnormality. Patients who underwent imaging at IPESQ were included, as well as those with documented Zika virus infection in fluid or tissue (n = 17, confirmed infection cohort) or those with brain findings suspicious for Zika virus infection, with intracranial calcifications (n = 28, presumed infection cohort). Imaging examinations included 12 fetal magnetic resonance (MR) examinations, 42 postnatal brain computed tomographic examinations, and 11 postnatal brain MR examinations. Images were reviewed by four radiologists, with final opinion achieved by means of consensus. Results Brain abnormalities seen in confirmed (n = 17) and presumed (n = 28) congenital Zika virus infections were similar, with ventriculomegaly in 16 of 17 (94%) and 27 of 28 (96%) infections, respectively; abnormalities of the corpus callosum in 16 of 17 (94%) and 22 of 28 (78%) infections, respectively; and cortical migrational abnormalities in 16 of 17 (94%) and 28 of 28 (100%) infections, respectively. Although most fetuses underwent at least one examination that showed head circumference below the 5th percentile, head circumference could be normal in the presence of severe ventriculomegaly (seen in three fetuses). Intracranial calcifications were most commonly seen at the gray matter-white matter junction, in 15 of 17 (88%) and 28 of 28 (100%) confirmed and presumed infections, respectively. The basal ganglia and/or thalamus were also commonly involved with calcifications in 11 of 17 (65%) and 18 of 28 (64%) infections, respectively. The skull frequently had a collapsed appearance with overlapping sutures and redundant skin folds and, occasionally, intracranial herniation of orbital fat and clot in the confluence of sinuses. Conclusion The spectrum of findings associated with congenital Zika virus infection in the IPESQ in northeastern Brazil is illustrated to aid the radiologist in identifying Zika virus infection at imaging. (©) RSNA, 2016 Online supplemental material is available for this article.
Purpose To determine if patient survival and mechanisms of right ventricular failure in pulmonary hypertension could be predicted by using supervised machine learning of three-dimensional patterns of systolic cardiac motion. Materials and Methods The study was approved by a research ethics committee, and participants gave written informed consent. Two hundred fifty-six patients (143 women; mean age ± standard deviation, 63 years ± 17) with newly diagnosed pulmonary hypertension underwent cardiac magnetic resonance (MR) imaging, right-sided heart catheterization, and 6-minute walk testing with a median follow-up of 4.0 years. Semiautomated segmentation of short-axis cine images was used to create a three-dimensional model of right ventricular motion. Supervised principal components analysis was used to identify patterns of systolic motion that were most strongly predictive of survival. Survival prediction was assessed by using difference in median survival time and area under the curve with time-dependent receiver operating characteristic analysis for 1-year survival. Results At the end of follow-up, 36% of patients (93 of 256) died, and one underwent lung transplantation. Poor outcome was predicted by a loss of effective contraction in the septum and free wall, coupled with reduced basal longitudinal motion. When added to conventional imaging and hemodynamic, functional, and clinical markers, three-dimensional cardiac motion improved survival prediction (area under the receiver operating characteristic curve, 0.73 vs 0.60, respectively; P < .001) and provided greater differentiation according to difference in median survival time between high- and low-risk groups (13.8 vs 10.7 years, respectively; P < .001). Conclusion A machine-learning survival model that uses three-dimensional cardiac motion predicts outcome independent of conventional risk factors in patients with newly diagnosed pulmonary hypertension. Online supplemental material is available for this article.
Purpose To examine the effects of subconcussive impacts resulting from a single season of youth (age range, 8-13 years) football on changes in specific white matter (WM) tracts as detected with diffusion-tensor imaging in the absence of clinically diagnosed concussions. Materials and Methods Head impact data were recorded by using the Head Impact Telemetry system and quantified as the combined-probability risk-weighted cumulative exposure (RWECP). Twenty-five male participants were evaluated for seasonal fractional anisotropy (FA) changes in specific WM tracts: the inferior fronto-occipital fasciculus (IFOF), inferior longitudinal fasciculus, and superior longitudinal fasciculus (SLF). Fiber tracts were segmented into a central core and two fiber terminals. The relationship between seasonal FA change in the whole fiber, central core, and the fiber terminals with RWECP was also investigated. Linear regression analysis was conducted to determine the association between RWECP and change in fiber tract FA during the season. Results There were statistically significant linear relationships between RWEcp and decreased FA in the whole (R(2) = 0.433; P = .003), core (R(2) = 0.3649; P = .007), and terminals (R(2) = 0.5666; P < .001) of left IFOF. A trend toward statistical significance (P = .08) in right SLF was observed. A statistically significant correlation between decrease in FA of the right SLF terminal and RWECP was also observed (R(2) = 0.2893; P = .028). Conclusion This study found a statistically significant relationship between head impact exposure and change of FA fractional anisotropy value of whole, core, and terminals of left IFOF and right SLF's terminals where WM and gray matter intersect, in the absence of a clinically diagnosed concussion. (©) RSNA, 2016.
Purpose To evaluate the efficacy of deep convolutional neural networks (DCNNs) for detecting tuberculosis (TB) on chest radiographs. Materials and Methods Four deidentified HIPAA-compliant datasets were used in this study that were exempted from review by the institutional review board, which consisted of 1007 posteroanterior chest radiographs. The datasets were split into training (68.0%), validation (17.1%), and test (14.9%). Two different DCNNs, AlexNet and GoogLeNet, were used to classify the images as having manifestations of pulmonary TB or as healthy. Both untrained and pretrained networks on ImageNet were used, and augmentation with multiple preprocessing techniques. Ensembles were performed on the best-performing algorithms. For cases where the classifiers were in disagreement, an independent board-certified cardiothoracic radiologist blindly interpreted the images to evaluate a potential radiologist-augmented workflow. Receiver operating characteristic curves and areas under the curve (AUCs) were used to assess model performance by using the DeLong method for statistical comparison of receiver operating characteristic curves. Results The best-performing classifier had an AUC of 0.99, which was an ensemble of the AlexNet and GoogLeNet DCNNs. The AUCs of the pretrained models were greater than that of the untrained models (P < .001). Augmenting the dataset further increased accuracy (P values for AlexNet and GoogLeNet were .03 and .02, respectively). The DCNNs had disagreement in 13 of the 150 test cases, which were blindly reviewed by a cardiothoracic radiologist, who correctly interpreted all 13 cases (100%). This radiologist-augmented approach resulted in a sensitivity of 97.3% and specificity 100%. Conclusion Deep learning with DCNNs can accurately classify TB at chest radiography with an AUC of 0.99. A radiologist-augmented approach for cases where there was disagreement among the classifiers further improved accuracy. (©) RSNA, 2017.
Purpose To investigate the association between N-terminal pro-B-type natriuretic peptide (NT-proBNP), which is a marker of heart disease, and markers of subclinical brain damage on magnetic resonance (MR) images in community-dwelling middle-aged and elderly subjects without dementia and without a clinical diagnosis of heart disease. Materials and Methods This prospective population-based cohort study was approved by a medical ethics committee overseen by the national government, and all participants gave written informed consent. Serum levels of NT-proBNP were measured in 2397 participants without dementia or stroke (mean age, 56.6 years; age range, 45.7-87.3 years) and without clinical diagnosis of heart disease who were drawn from the population-based Rotterdam Study. All participants were examined with a 1.5-T MR imager. Multivariable linear and logistic regression analyses were used to investigate the association between NT-proBNP level and MR imaging markers of subclinical brain damage, including volumetric, focal, and microstructural markers. Results A higher NT-proBNP level was associated with smaller total brain volume (mean difference in z score per standard deviation increase in NT-proBNP level, -0.021; 95% confidence interval [CI]: -0.034, -0.007; P = .003) and was predominantly driven by gray matter volume (mean difference in z score per standard deviation increase in NT-proBNP level, -0.037; 95% CI: -0.057, -0.017; P < .001). Higher NT-proBNP level was associated with larger white matter lesion volume (mean difference in z score per standard deviation increase in NT-proBNP level, 0.090; 95% CI: 0.051, 0.129; P < .001), with lower fractional anisotropy (mean difference in z score per standard deviation increase in NT-proBNP level, -0.048; 95% CI: -0.088, -0.008; P = .019) and higher mean diffusivity (mean difference in z score per standard deviation increase in NT-proBNP level, 0.054; 95% CI: 0.018, 0.091; P = .004) of normal-appearing white matter. Conclusion In community-dwelling persons, higher serum NT-proBNP levels are associated with volumetric and microstructural MR imaging markers of subclinical brain damage. (©) RSNA, 2016 Online supplemental material is available for this article.
Purpose To investigate whether the blood-brain barrier (BBB) leaks blood-circulating substances in patients with early forms of Alzheimer disease (AD), and if so, to examine the extent and pattern of leakage. Materials and Methods This study was approved by the local medical ethical committees of the Maastricht University Medical Center and Leiden University Medical Center, and written informed consent was obtained from all subjects. For this pilot study, 16 patients with early AD and 17 healthy age-matched control subjects underwent dynamic contrast material-enhanced magnetic resonance (MR) imaging sequence with dual time resolution for 25 minutes. The Patlak graphical approach was used to quantify the BBB leakage rate and local blood plasma volume. Subsequent histogram analysis was used to determine the volume fraction of the leaking brain tissue. Differences were assessed with linear regression analysis, adjusted for confounding variables. Results The BBB leakage rate was significantly higher in patients compared with that in control subjects in the total gray matter (P < .05) and cortex (P = .03). Patients had a significantly higher volume fraction of the leaking brain tissue in the gray matter (P = .004), normal-appearing white matter (P < .04), deep gray matter (P = .01), and cortex (P = .004). When all subjects were considered, scores on the Mini-Mental State Examination decreased significantly with increasing leakage in the deep gray matter (P = .007) and cortex (P < .05). Conclusion The results of this study showed global BBB leakage in patients with early AD that is associated with cognitive decline. A compromised BBB may be part of a cascade of pathologic events that eventually lead to cognitive decline and dementia. (©)RSNA, 2016 Online supplemental material is available for this article.
Purpose To investigate the sustained-attention and memory-enhancing neural correlates of the oral administration of methylene blue in the healthy human brain. Materials and Methods The institutional review board approved this prospective, HIPAA-compliant, randomized, double-blinded, placebo-controlled clinical trial, and all patients provided informed consent. Twenty-six subjects (age range, 22-62 years) were enrolled. Functional magnetic resonance (MR) imaging was performed with a psychomotor vigilance task (sustained attention) and delayed match-to-sample tasks (short-term memory) before and 1 hour after administration of low-dose methylene blue or a placebo. Cerebrovascular reactivity effects were also measured with the carbon dioxide challenge, in which a 2 × 2 repeated-measures analysis of variance was performed with a drug (methylene blue vs placebo) and time (before vs after administration of the drug) as factors to assess drug × time between group interactions. Multiple comparison correction was applied, with cluster-corrected P < .05 indicating a significant difference. Results Administration of methylene blue increased response in the bilateral insular cortex during a psychomotor vigilance task (Z = 2.9-3.4, P = .01-.008) and functional MR imaging response during a short-term memory task involving the prefrontal, parietal, and occipital cortex (Z = 2.9-4.2, P = .03-.0003). Methylene blue was also associated with a 7% increase in correct responses during memory retrieval (P = .01). Conclusion Low-dose methylene blue can increase functional MR imaging activity during sustained attention and short-term memory tasks and enhance memory retrieval. (©) RSNA, 2016 Online supplemental material is available for this article.
Purpose To develop a machine learning model that allows high-risk breast lesions (HRLs) diagnosed with image-guided needle biopsy that require surgical excision to be distinguished from HRLs that are at low risk for upgrade to cancer at surgery and thus could be surveilled. Materials and Methods Consecutive patients with biopsy-proven HRLs who underwent surgery or at least 2 years of imaging follow-up from June 2006 to April 2015 were identified. A random forest machine learning model was developed to identify HRLs at low risk for upgrade to cancer. Traditional features such as age and HRL histologic results were used in the model, as were text features from the biopsy pathologic report. Results One thousand six HRLs were identified, with a cancer upgrade rate of 11.4% (115 of 1006). A machine learning random forest model was developed with 671 HRLs and tested with an independent set of 335 HRLs. Among the most important traditional features were age and HRL histologic results (eg, atypical ductal hyperplasia). An important text feature from the pathologic reports was “severely atypical.” Instead of surgical excision of all HRLs, if those categorized with the model to be at low risk for upgrade were surveilled and the remainder were excised, then 97.4% (37 of 38) of malignancies would have been diagnosed at surgery, and 30.6% (91 of 297) of surgeries of benign lesions could have been avoided. Conclusion This study provides proof of concept that a machine learning model can be applied to predict the risk of upgrade of HRLs to cancer. Use of this model could decrease unnecessary surgery by nearly one-third and could help guide clinical decision making with regard to surveillance versus surgical excision of HRLs. (©) RSNA, 2017.
Purpose To compare mortality rates from all causes, specific causes, total cancers, and specific cancers to assess whether differences between radiologists and psychiatrists are consistent with known risks of radiation exposure and the changes in radiation exposure to radiologists over time. Materials and Methods The authors used the American Medical Association Physician Masterfile to construct a cohort of 43 763 radiologists (20% women) and 64 990 psychiatrists (27% women) (comparison group) who graduated from medical school in 1916-2006. Vital status was obtained from record linkages with the Social Security Administration and commercial databases, and cause of death was obtained from the National Death Index. Poisson regression was used to estimate relative risks (RRs) and 95% confidence intervals (CIs) for all causes and specific causes of death. Results During the follow-up period (1979-2008), 4260 male radiologists and 7815 male psychiatrists died. The male radiologists had lower death rates (all causes) compared with the psychiatrists (RR = 0.94; 95% CI: 0.90, 0.97), similar cancer death rates overall (RR = 1.00; 95% CI: 0.93, 1.07), but increased acute myeloid leukemia and/or myelodysplastic syndrome death rates (RR = 1.62; 95% CI: 1.05, 2.50); these rates were driven by those who graduated before 1940 (RR = 4.68; 95% CI: 0.91, 24.18). In these earliest workers (before 1940) there were also increased death rates from melanoma (RR = 8.75; 95% CI: 1.89, 40.53), non-Hodgkin lymphoma (NHL) (RR = 2.69; 95% CI: 1.33, 5.45), and cerebrovascular disease (RR = 1.49; 95% CI: 1.11, 2.01). The 208 deaths in female radiologists precluded detailed investigation, and the number of female radiologists who graduated before 1940 was very small (n = 47). Conclusion The excess risk of acute myeloid leukemia and/or myelodysplastic syndrome mortality in radiologists who graduated before 1940 is likely due to occupational radiation exposure. The melanoma, NHL, and cerebrovascular disease mortality risks are possibly due to radiation. The authors found no evidence of excess mortality in radiologists who graduated more recently, possibly because of increased radiation protection and/or lifestyle changes. (©) RSNA, 2016 Online supplemental material is available for this article.
Purpose To demonstrate the feasibility of the use of a rapid, noninvasive, in vivo imaging method to measure fatty acid fractions of breast adipose tissue during diagnostic breast magnetic resonance (MR) examinations and to investigate associations between fatty acid fractions in breast adipose tissue and breast cancer status by using this method. Materials and Methods The institutional review board approved this retrospective HIPAA-compliant study and informed consent was waived. Between July 2013 and September 2014, multiple-echo three-dimensional gradient-echo data were acquired for 89 women. Spectra were generated and used to estimate fractions of monounsaturated fatty acid (MUFA), polyunsaturated fatty acid (PUFA), and saturated fatty acid (SFA) in the breast adipose tissue. Analysis of covariance and exact Mann-Whitney tests were used to compare groups and the Spearman rank correlation coefficient was used to characterize the association of each imaging measure with each attribute. Results For postmenopausal women, MUFA was lower (0.38 ± 0.06 vs 0.46 ± 0.10; P < .05) and SFA was higher (0.31 ± 0.07 vs 0.19 ± 0.11; P < .05) for women with invasive ductal carcinoma than for those with benign tissue. No correlation was found between body mass index (BMI) and fatty acid fractions in breast adipose tissue. In women with benign tissue, postmenopausal women had a higher PUFA (0.35 ± 0.06 vs 0.27 ± 0.05; P < .01) and lower SFA (0.19 ± 0.11 vs 0.30 ± 0.12; P < .05) than premenopausal women. Conclusion There is a possible link between the presence of invasive ductal carcinoma and fatty acid fractions in breast adipose tissue for postmenopausal women in whom BMI values are not correlated with the fatty acid fractions. (©) RSNA, 2016 Online supplemental material is available for this article.