Brain Imaging has been source of several studies in the literature, mostly due to its importanceboth to predict and to analyze certain diseases or conditions. Extracting the brain from patient images for medical analysis can provide useful diagnostic and prognostic information.To this end, digital image processing algorithms have been applied to medical tasks with a focus on the identification of the brain. This work proposes a brain extraction framework based on three major steps: 1) Dataset and Image Selection; 2) Preprocessing; and 3) Largest Connected Component extraction. Our data are obtained from the OASIS dataset.The preprocessing step is applied in order to enhance contrast and eliminate possible noise from the T1-weighted MRI. Largest Connected Component extraction is performed by initially detecting the largest element in the image (i.e. the brain gray matter) and then by extracting it through mathematical morphology operators. The unsupervised framework extracts the brain in different axial slices without adjustments. The main contribution of this work is a method using only digital image processing for automatically identifying the brain from several different slices, which differs from the literature since is performed without parameter resetting. Five metrics were applied to evaluate our results: Specificity, Recall, Accuracy, F-Measure, and Precision. In our first experiment, two metrics resulted in more than 90% in efficiency (Specificity and Precision), two of them surpassed 80% (F-Measure and Accuracy), and Sensitivity exceeded 70%. Our second experiment compares our results with those produced by related works, having been ranked in the top positions of Sensitivity and Specificity.
3 February 2024 in Construction and Building Materials
Ladle furnace slag is a waste composed essentially of quicklime or hydrated lime, whose contents depend on the raw material and the cooling process that led to the slag batch. With this chemical composition, it is used by civil construction as a hydraulic binder in cement matrices. The chemical compounds mentioned are also present in Portland cement, which are part of the chemical reactions of hydration and hardening. However, the quality of LFS batches calls for attention to volume expansion caused by chemical compounds whose presence and content can be controlled by the cooling method adopted in the production. Considering the use of this material as a partial replacement for Portland cement, the objective of this study was the physicochemical characterization of LFS samples to evaluate the influence of the cooling method on its potential as a complementary binder in cementitious matrices. In this sense, 3 samples from different batches were analyzed and the effects of each cooling process. The results include analysis of specific mass, laser diffraction for particle size analysis, X-ray fluorescence and X-Ray Diffraction tests. It was verified that the sample obtained by slow cooling is the most suitable as binder, as it features less possibility of expansive chemical reactions and presents greater fineness.
30 January 2026 in Archives of Computational Methods in Engineering
Mortars are among the most used materials in civil construction, and their mechanical properties are directly related to several parameters, namely structural behavior, durability, and failure mechanisms. As a result, predicting these parameters is essential for preventive and corrective diagnosis of structures composed of this material. Recently, machine learning models have been applied to improve these predictions. Until recently, such predictions were based on traditional empirical procedures, which are unable to capture the variability of material parameters. Nevertheless, as this is still an emerging research topic, many limitations and gaps remain to be investigated, such as the dependence on data structure and the appropriate selection of hyperparameters. Furthermore, most studies applying machine learning to mortars focus on additions, admixtures, or durability- and performance-related aspects, rather than on assessing the efficiency and robustness of the models themselves. In this context, this systematic and critical review aims to identify how machine learning models have been applied to predict the mechanical properties of different mortars. The main input parameters used for this prediction are discussed, and the hyperparameters of several machine learning models are critically analyzed and discussed. The results indicate that tree-based ensemble models perform better than other approaches, with XGBoost showing superior predictive performance.