RESUMEN
Differential diagnosis between avascular necrosis (AVN) and transient osteoporosis of the hip (TOH) can be complicated even for experienced MSK radiologists. Our study attempted to use MR images in order to develop a deep learning methodology with the use of transfer learning and a convolutional neural network (CNN) ensemble, for the accurate differentiation between the two diseases. An augmented dataset of 210 hips with TOH and 210 hips with AVN was used to finetune three ImageNet-trained CNNs (VGG-16, InceptionResNetV2, and InceptionV3). An ensemble decision was reached in a hard-voting manner by selecting the outcome voted by at least two of the CNNs. Inception-ResNet-V2 achieved the highest AUC (97.62%) similar to the model ensemble, followed by InceptionV3 (AUC of 96.82%) and VGG-16 (AUC 96.03%). Precision for the diagnosis of AVN and recall for the detection of TOH were higher in the model ensemble compared to Inception-ResNet-V2. Ensemble performance was significantly higher than that of an MSK radiologist and a fellow (P < 0.001). Deep learning was highly successful in distinguishing TOH from AVN, with a potential to aid treatment decisions and lead to the avoidance of unnecessary surgery.
RESUMEN
Differentiation between transient osteoporosis (TOH) and avascular necrosis (AVN) of the hip is a longstanding challenge in musculoskeletal radiology. The purpose of this study was to utilize MRI-based radiomics and machine learning (ML) for accurate differentiation between the two entities. A total of 109 hips with TOH and 104 hips with AVN were retrospectively included. Femoral heads and necks with segmented radiomics features were extracted. Three ML classifiers (XGboost, CatBoost and SVM) using 38 relevant radiomics features were trained on 70% and validated on 30% of the dataset. ML performance was compared to two musculoskeletal radiologists, a general radiologist and two radiology residents. XGboost achieved the best performance with an area under the curve (AUC) of 93.7% (95% CI from 87.7 to 99.8%) among ML models. MSK radiologists achieved an AUC of 90.6% (95% CI from 86.7% to 94.5%) and 88.3% (95% CI from 84% to 92.7%), respectively, similar to residents. The general radiologist achieved an AUC of 84.5% (95% CI from 80% to 89%), significantly lower than of XGboost (p = 0.017). In conclusion, radiomics-based ML achieved a performance similar to MSK radiologists and significantly higher compared to general radiologists in differentiating between TOH and AVN.
RESUMEN
BACKGROUND: Vancomycin-resistant Enterococcus faecium (VRE) may cause outbreaks in neonatal intensive care units (NICU). We describe a biphasic VRE outbreak and identify risk factors for VRE acquisition. METHODS: After the occurrence of 2 cases of VRE infections in a 44-bed NICU, a bundle of interventions was implemented that included active surveillance cultures for VRE, enhanced infection control measures, and audits on antimicrobial use, from June to December 2008. Analysis was performed using polymerase chain reaction and pulse-field gel electrophoresis techniques. A case-control study was conducted to identify risk factors. RESULTS: Among 253 neonates screened, 101 (39.9%) were found to be colonized with VRE. During the first 9 weeks of the study period, 59 new cases were detected. Molecular analysis showed 1 predominant clone. During weeks 10-12, no new cases of VRE colonization were detected; however, at week 13, just when the outbreak appeared to be over, a second wave occurred, with 42 new cases and multiple clones detected. Multivariate analysis identified administration of antimicrobial therapy for late-onset neonatal sepsis and hospitalization during the first month of this outbreak as significant risk factors for VRE colonization. CONCLUSION: Both a high prevalence of VRE colonization and antimicrobial use promoted the transmission of VRE during this biphasic outbreak. Adherence to infection control measures and antimicrobial stewardship policies are of utmost importance.
Asunto(s)
Brotes de Enfermedades , Enterococcus faecium/clasificación , Enterococcus faecium/efectos de los fármacos , Infecciones por Bacterias Grampositivas/epidemiología , Resistencia a la Vancomicina , Antibacterianos/uso terapéutico , Estudios de Casos y Controles , ADN Bacteriano/genética , Utilización de Medicamentos/estadística & datos numéricos , Electroforesis en Gel de Campo Pulsado , Enterococcus faecium/genética , Enterococcus faecium/aislamiento & purificación , Femenino , Infecciones por Bacterias Grampositivas/microbiología , Humanos , Recién Nacido , Cuidado Intensivo Neonatal , Masculino , Epidemiología Molecular , Tipificación Molecular , Reacción en Cadena de la Polimerasa , Factores de RiesgoRESUMEN
Different degradation methods have been applied to assess the suitability of advanced oxidation process (AOPs) to promote mineralization of imazethapyr [(RS)-5-ethyl-2-(4-isopropyl-4-methyl-5-oxo-2-imidazolin-2-yl)nicotinic acid], a widely used imidazolinone class herbicide, the persistence of which has been demonstrated in surface and ground waters destined to human uses. Independent of the oxidation process assessed, the decomposition of imazethapyr always followed a pseudo-first order kinetic. The direct UV-irradiation (UV) of the herbicide as well as its oxidation with ozone (O3), and hydrogen peroxide tied to UV-irradiation (H2O2/UV) were sufficiently slow to permit the identification of intermediate products, the formation pathway of which has been proposed. Ozonation joined to UV-irradiation (O3/UV), ozonation joined to titanium dioxide photo-catalysis (TiO2/UV+O3), sole photo-catalysis (TiO2/UV), and photo-catalysis reinforced with hydrogen peroxide-oxidation (TiO2/UV+H2O2) were characterized by a faster degradation and rapid formation of a lot of small molecules, which were quickly degraded to complete mineralization. The most effective oxidation methods were those using titanium dioxide photo-catalysis enhanced either by ozonation or hydrogen peroxide. Most of all, these last processes were useful to avoid the development of dangerous by-products.