Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Окт. 7, 2024

MRI imaging primarily focuses on the soft tissues of human body, typically performed prior to a patient's transfer surgical suite for medical procedure. However, utilizing images tumor diagnosis is time-consuming process. To address these challenges, new method automatic brain was developed, employing combination image segmentation, feature extraction, and classification techniques isolate specific region interest in an corresponding tumor. The proposed this study comprises five distinct steps. Firstly, pre-processing conducted, various filters enhance quality. Subsequently, thresholding applied facilitate segmentation. Following extraction performed, analyzing morphological structural properties images. Then, selection carried out using principal component analysis (PCA). Finally, artificial neural network (ANN). In total, 74 unique features were extracted from each image, resulting dataset 144 observations. Principal employed select top 8 most effective features. Artificial Neural Networks (ANNs) leverage comprehensive data selective knowledge. Consequently, approach evaluated compared with alternative methods, significant improvements precision, accuracy, F1 score. demonstrated notable increases 99.3%, 97.3%, 98.5% Sensitivity These findings highlight efficiency accurately segmenting classifying

Язык: Английский