Banan Alnemri and Arwa Basbrain, Department of Computer Science, Faculty of Computing and Information Technology King Abdulaziz University, Jeddah, Saudi Arabia
Accurate segmentation and precise morphological analysis of neuronal cells in fluorescence microscopy images are crucial steps in neuroscience and biomedical imaging applications. However, this process is time-consuming and labor-intensive, requiring significant manual effort and expertise to ensure reliable results. This work presents a pipeline for neuron instance segmentation and measurement based on a high-resolution dataset of stem-cell-derived neurons. The proposed method uses YOLOv8, trained on manually annotated microscopy images. The model achieved high segmentation accuracy, exceeding 97%. In addition, the pipeline utilized both ground truth and predicted masks to extract biologically significant features, including cell length, width, area, and grayscale intensity values. The overall accuracy of the extracted morphological measurements reached 75.32%, further supporting the effectiveness of the proposed approach. This integrated framework offers a valuable tool for automated analysis in cell imaging and neuroscience research, reducing the need for manual annotation and enabling scalable, precise quantification of neuron morphology.
Neuron Segmentation, Fluorescence Microscopy, YOLOv8, Morphological Analysis, Instance Segmentation.
Lenardo Silva, Gustavo Oliveira, Luciano Cabral, Rodrigo Silva, Luam dos Santos, Thyago de Oliveira, Breno da Costa, Joana Lobo, Dalgoberto Pinho J´unior, Nicholas da Cruz, Rafael Silva, and Bruno Pimentel,Center for Excellence in Social Technologies Av. Lourival Melo Mota, S/N, Macei´o, 57072-970, Alagoas, Brazil
The lack of accurate information about the estimated number of students to enroll in a school can lead to losses for the government, the school, and, mainly, for the students. Examples include (insuf- ficient or excessive) financial transfers from the government to schools and the inadequate allocation of resources (e.g., number of teachers and availability of teaching materials) to students. In our experiments, we used a dataset from the Brazilian school census provided by the Ministry of Education, which contains 340 characteristic attributes of schools and their respective teaching stages. The large quantity and nature of this data make data analysis more complex, which requires an appropriate method for feature selection to enrollment predictive models. In this sense, this study explores the application of Machine Learning algorithms as a solution to the problem of predicting enrollment. The ML algorithms used in this study included random forest, multilayer perceptron, linear regression, and support vector regression. We eval- uated the performance of the models using the cross-validation method, calculating the MAE, MSE, and RMSE metrics, in addition to the execution time and descriptive statistics about the number of features suggested by the selection methods employed. The results revealed that the Spearman correlation method with thresholds of 0.6 and 0.65 can reduce the dimensionality of the data and the execution time of the predictive models tested for enrollment prediction.
Feature Selection, Comparative Analysis, Forecasting, Enrollment Schools, Brazil.
