rtificial intelligence (AI) algorithms have existed for decades and have recently been propelled to the forefront of medical imaging research. To a large extent, this is related to improvements in computing power, availability of a large amount of training data, and innovative and improved neural network architectures, with the recognition that certain types of algorithms are well suited to image analysis. The latter discovery was accelerated by the ImageNet competition and represents a fundamental transformation in research mechanics and methods in computer vision.Currently, in most studies, researchers collect data, perform analysis, and publish results. The same researchers may continue to augment and expand the data set and perform subsequent analysis with resulting publications. The data for each study are held quite closely and are rarely shared among institutions outside of multicenter trials. Competitions represent a different model of research: Research data are made available to the public, usually with a baseline performance metric. Groups around the world are invited to analyze the data and create algorithms to beat the performance of the prior generation. For example, the baseline performance metric for this challenge was set by the previous skeletal age model developed by Larson et al (1).The Radiological Society of North America (RSNA) Pediatric Bone Age Machine Learning Challenge was created to evaluate the performance of computer algorithms in executing a common image analysis activity that is familiar to many pediatric radiologists: estimating the bone age of pediatric patients based on radiographs of their hand (1-5). This challenge used a data set of pediatric
Geometallurgy aims to develop and deploy predictive spatial models based on tangible and quantitative resource characteristics that are used to optimize the efficiency of minerals beneficiation and extractive metallurgy operations. While most current applications of geometallurgy are focused on the major commodity to be recovered from a mineral deposit, this contribution delineates the opportunity to use a geometallurgical approach to provide an early assessment of the economic potential of by-product recovery from an ongoing mining operation. As a case study for this methodology, possible rare earth element (REE) recovery as a by-product of Nb production at the Chapadão mine in the Catalão I carbonatite complex is used. Catalão I is part of the Alto Paranaíba igneous province in the Goias Province of Brazil. Currently, niobium is produced in the complex as a by-product of the Chapadão phosphates mine. This production is performed in the Tailings plant, the focus of this study. REEs, albeit present in significant concentrations, are currently not recovered as by-products. Nine samples from different stages of the Nb beneficiation process in the Tailings plant were taken and characterized by mineral liberation analyzer, X-ray powder diffraction, and bulk-rock chemistry. The recovery of REEs in each of the tailing streams was quantified by mass balance. The quantitative mineralogical and microstructural data are used to identify the most suitable approach to recover REEs as a by-product—without placing limitations on niobium production. Monazite, the most common rare earth mineral identified in the feed, occurs as Ce-rich and La-rich varieties that can be easily distinguished by scanning electron microscopy (SEM)-based image analysis. Quartz, Fe-Ti oxides, and several phosphate minerals are the main gangue minerals. The highest rare earth oxide content concentrations (1.75 wt % total rare earth oxides) and the greatest potential for REE processing are reported for the final flotation tailings stream. To place tentative economic constraints on REE recovery from the tailings material, an analogy to the Browns Range deposit in Australia is drawn. Its technical flow sheet was used to estimate the cost for a hypothetical REE production at Chapadão. Parameters derived from SEM-based image analysis were used to model possible monazite recovery and concentrate grades. This exercise illustrates that a marketable REE concentrate could be obtained at Chapadão if the process recovers at least 53% of the particles with no less than 60% of monazite on their surface. Applying capital expenditure and operational expenditure values similar to those of Browns Range suggests that such an operation would be profitable at current REE prices.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.