RESUMO
It is known that prematurity and low birth weight are associated with chronic kidney disease and hypertension. A positive correlation between kidney volume and birth weight was also described. In our ongoing observational study in 5-year-old children, we perceived highly abnormal kidney ultrasound and functions of a male patient born weighing 370 grams. It was his first nephrology examination since discharge from the hospital. We believe that thorough follow up and timely diagnosis of developing renal insufficiency may help us to initiate proper treatment in high-risk children (Tab. 1, Fig. 1, Ref. 7). Text in PDF www.elis.sk Keywords: prematurity; extremely low birth weight; chronic kidney disease; renal ultrasound; renal function.
Assuntos
Lactente Extremamente Prematuro , Rim , Nascimento Prematuro , Insuficiência Renal Crônica , Ultrassonografia , Humanos , Pré-Escolar , Rim/anormalidades , Rim/diagnóstico por imagem , Masculino , Insuficiência Renal Crônica/diagnóstico por imagem , Insuficiência Renal Crônica/prevenção & controleRESUMO
Background: To assess the impact of different clinical questions on radiation doses acquired during cardiac computed tomography in children. Methods: A total of 116 children who underwent cardiac CT on a third-generation dual-source CT scanner were included. The clinical questions were divided into three main categories: the extent of scanning in the z-axis, coronary artery assessment and cardiac function assessment. Radiation dose values represented as a dose-length product (DLP) in mGy*cm were recorded from the CT scanner protocols. Results: There were significantly higher doses in cases with cardiac function assessment (median DLP 348 versus 59 mGy*cm, p < 0.01) and in cases with coronary artery assessment (median DLP 133 versus 71 mGy*cm, p < 0.01). Conclusion: The most important factor was the assessment of cardiac function, where the median radiation dose was 4.3× higher in patients with a request for cardiac function assessment. We strongly recommend that clinical requests for cardiac CT should be carefully considered in the paediatric population.
RESUMO
OBJECTIVES: Currently, hurdles to implementation of artificial intelligence (AI) in radiology are a much-debated topic but have not been investigated in the community at large. Also, controversy exists if and to what extent AI should be incorporated into radiology residency programs. METHODS: Between April and July 2019, an international survey took place on AI regarding its impact on the profession and training. The survey was accessible for radiologists and residents and distributed through several radiological societies. Relationships of independent variables with opinions, hurdles, and education were assessed using multivariable logistic regression. RESULTS: The survey was completed by 1041 respondents from 54 countries. A majority (n = 855, 82%) expects that AI will cause a change to the radiology field within 10 years. Most frequently, expected roles of AI in clinical practice were second reader (n = 829, 78%) and work-flow optimization (n = 802, 77%). Ethical and legal issues (n = 630, 62%) and lack of knowledge (n = 584, 57%) were mentioned most often as hurdles to implementation. Expert respondents added lack of labelled images and generalizability issues. A majority (n = 819, 79%) indicated that AI should be incorporated in residency programs, while less support for imaging informatics and AI as a subspecialty was found (n = 241, 23%). CONCLUSIONS: Broad community demand exists for incorporation of AI into residency programs. Based on the results of the current study, integration of AI education seems advisable for radiology residents, including issues related to data management, ethics, and legislation. KEY POINTS: ⢠There is broad demand from the radiological community to incorporate AI into residency programs, but there is less support to recognize imaging informatics as a radiological subspecialty. ⢠Ethical and legal issues and lack of knowledge are recognized as major bottlenecks for AI implementation by the radiological community, while the shortage in labeled data and IT-infrastructure issues are less often recognized as hurdles. ⢠Integrating AI education in radiology curricula including technical aspects of data management, risk of bias, and ethical and legal issues may aid successful integration of AI into diagnostic radiology.
Assuntos
Inteligência Artificial , Radiologia , Humanos , Motivação , Radiologistas , Inquéritos e QuestionáriosRESUMO
BACKGROUND: Neonatal/infantile jaundice is relatively common, and most cases resolve spontaneously. However, in the setting of unresolved neonatal cholestasis, a prompt and accurate assessment for biliary atresia is vital to prevent poor outcomes. OBJECTIVE: To determine whether shear wave elastography (SWE) alone or combined with gray-scale imaging improves the diagnostic performance of US in discriminating biliary atresia from other causes of neonatal jaundice over that of gray-scale imaging alone. MATERIALS AND METHODS: Infants referred for cholestatic jaundice were assessed with SWE and gray-scale US. On gray-scale US, two radiology readers assessed liver heterogeneity, presence of the triangular cord sign, hepatic artery size, presence/absence of common bile duct and gallbladder, and gallbladder shape; associated interobserver correlation coefficients (ICC) were calculated. SWE speeds were performed on a Siemens S3000 using 6C2 and 9 L4 transducers with both point and two-dimensional (2-D) SWE US. Both univariable and multivariable analyses were performed, as were receiver operating characteristic curves (ROC) and statistical significance tests (chi-squared, analysis of variance, t-test and Wilcoxon rank sum) when appropriate. RESULTS: There were 212 infants with biliary atresia and 106 without biliary atresia. The median shear wave speed (SWS) for biliary atresia cases was significantly higher (P<0.001) than for non-biliary-atresia cases for all acquisition modes. For reference, the median L9 point SWS was 2.1 m/s (interquartile range [IQR] 1.7-2.4 m/s) in infants with biliary atresia and 1.5 m/s (IQR 1.3-1.9 m/s) in infants without biliary atresia (P<0.001). All gray-scale US findings were significantly different between biliary-atresia and non-biliary-atresia cohorts (P<0.001), intraclass correlation coefficient (ICC) range 0.7-1.0. Triangular cord sign was most predictive of biliary atresia independent of other gray-scale findings or SWS - 96% specific and 88% sensitive. Multistep univariable/multivariable analysis of both gray-scale findings and SWE resulted in three groups being predictive of biliary atresia likelihood. Abnormal common bile duct/gallbladder and enlarged hepatic artery were highly predictive of biliary atresia independent of SWS (100% for girls and 95-100% for boys). Presence of both the common bile duct and the gallbladder along with a normal hepatic artery usually excluded biliary atresia independent of SWS. Other gray-scale combinations were equivocal, and including SWE improved discrimination between biliary-atresia and non-biliary-atresia cases. CONCLUSION: Shear wave elastography independent of gray-scale US significantly differentiated biliary-atresia from non-biliary-atresia cases. However, gray-scale findings were more predictive of biliary atresia than elastography. SWE was useful for differentiating biliary-atresia from non-biliary-atresia cases in the setting of equivocal gray-scale findings.
Assuntos
Atresia Biliar , Colestase , Técnicas de Imagem por Elasticidade , Icterícia Neonatal , Atresia Biliar/diagnóstico por imagem , Feminino , Humanos , Lactente , Recém-Nascido , Icterícia Neonatal/diagnóstico por imagem , Masculino , UltrassonografiaRESUMO
OBJECTIVES: Radiologists' perception is likely to influence the adoption of artificial intelligence (AI) into clinical practice. We investigated knowledge and attitude towards AI by radiologists and residents in Europe and beyond. METHODS: Between April and July 2019, a survey on fear of replacement, knowledge, and attitude towards AI was accessible to radiologists and residents. The survey was distributed through several radiological societies, author networks, and social media. Independent predictors of fear of replacement and a positive attitude towards AI were assessed using multivariable logistic regression. RESULTS: The survey was completed by 1,041 respondents from 54 mostly European countries. Most respondents were male (n = 670, 65%), median age was 38 (24-74) years, n = 142 (35%) residents, and n = 471 (45%) worked in an academic center. Basic AI-specific knowledge was associated with fear (adjusted OR 1.56, 95% CI 1.10-2.21, p = 0.01), while intermediate AI-specific knowledge (adjusted OR 0.40, 95% CI 0.20-0.80, p = 0.01) or advanced AI-specific knowledge (adjusted OR 0.43, 95% CI 0.21-0.90, p = 0.03) was inversely associated with fear. A positive attitude towards AI was observed in 48% (n = 501) and was associated with only having heard of AI, intermediate (adjusted OR 11.65, 95% CI 4.25-31.92, p < 0.001), or advanced AI-specific knowledge (adjusted OR 17.65, 95% CI 6.16-50.54, p < 0.001). CONCLUSIONS: Limited AI-specific knowledge levels among radiology residents and radiologists are associated with fear, while intermediate to advanced AI-specific knowledge levels are associated with a positive attitude towards AI. Additional training may therefore improve clinical adoption. KEY POINTS: ⢠Forty-eight percent of radiologists and residents have an open and proactive attitude towards artificial intelligence (AI), while 38% fear of replacement by AI. ⢠Intermediate and advanced AI-specific knowledge levels may enhance adoption of AI in clinical practice, while rudimentary knowledge levels appear to be inhibitive. ⢠AI should be incorporated in radiology training curricula to help facilitate its clinical adoption.
Assuntos
Inteligência Artificial , Radiologia , Adulto , Medo , Humanos , Masculino , Radiologistas , Inquéritos e QuestionáriosRESUMO
PURPOSE: To develop a segmentation pipeline for segmentation of aortic dissection CT angiograms into true and false lumina on multiplanar reformations (MPRs) perpendicular to the aortic centerline and derive quantitative morphologic features, specifically aortic diameter and true- or false-lumen cross-sectional area. MATERIALS AND METHODS: An automated segmentation pipeline including two convolutional neural network (CNN) segmentation algorithms was developed. The algorithm derives the aortic centerline, generates MPRs orthogonal to the centerline, and segments the true and false lumina. A total of 153 CT angiograms obtained from 45 retrospectively identified patients (mean age, 50 years; range, 22-79 years) were used to train (n = 103), validate (n = 22), and test (n = 28) the CNN pipeline. Accuracy was evaluated by using the Dice similarity coefficient (DSC). Segmentations were then used to derive the maximal diameter of test-set patients and cross-sectional area profiles of the true and false lumina. RESULTS: The segmentation pipeline yielded a mean DSC of 0.873 ± 0.056 for the true lumina and 0.894 ± 0.040 for the false lumina of test-set cases. Automated maximal diameter measurements correlated well with manual measurements (R 2 = 0.95). Profiles of cross-sectional diameter, true-lumen area, and false-lumen area over several follow-up examinations were derived. CONCLUSION: A segmentation pipeline was used to accurately identify true and false lumina on CT angiograms of aortic dissection. These segmentations can be used to obtain diameter and other morphologic parameters for surveillance and risk stratification.Supplemental material is available for this article.© RSNA, 2020.
RESUMO
BACKGROUND: This study evaluated the accuracy of postnatal computed tomography (CT) imaging in the identification of congenital bronchopulmonary malformation (BPM) in comparison with histopathological analysis. METHODS: CT scans of prenatally diagnosed BPMs from 24 patients with available histology were analysed retrospectively. The CT images were reviewed blinded to histological findings by two radiologists. Specific diagnosis was assigned based on predetermined criteria. The accuracy of CT was evaluated. RESULTS: The agreement rate in CT diagnosis between two radiologists was 100%. In 75% the lesions were located in the lower lobes. An overlap of 71% in CT and histopathological diagnoses was reached. The least matching diagnosis was type 2 CPAM. CONCLUSION: Contrast enhanced chest CT is very accurate in characterizing the BPM spectrum and provides important information on lesion type and structure.