Answers are grounded in this paper and cite their sources.
Acquired brain anomalies are crucial and life killing disease among the other diseases. As a result, fast and accurate disease diagnosis and classification are critical for human survival. In this research, a machine learning strategy is given for distinguishing and classifying meningioma brain images from non-meningioma brain images. In this paper, brain pictures are recognized and classified using the Neural Network (NN) classification method. This suggested method comprises of a preprocessing module that uses the shearlet transform for transformation of pixels. Local Binary Pattern (LBP) features are then calculated using the shearlet coefficients. The computed final characteristics are input into the NN classifier to produce classification results. The meningioma detection system using the suggested NN classification approach obtains 96.45% of SET, 96.57% of SPT, 97.34% of MSA, 97.38% of PR, and 97.3% of FS. The meningioma detection system using the suggested NN classification approach obtains 97.16% of SET, 97.25% of SPT, 97.97% of MSA, 98.19% of PR, and 98. The shearlet transform combined with NN classification algorithm improves the performance of the entire meningioma detection rate.
No takes yet. Share an insight, caveat, or question.
Krishnakumar et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: