{"title":"Percolation Images: Fractal Geometry Features for Brain Tumor Classification.","authors":"Alessandra Lumini, Guilherme Freire Roberto, Leandro Alves Neves, Alessandro Santana Martins, Marcelo Zanchetta do Nascimento","doi":"10.1007/978-3-031-47606-8_29","DOIUrl":null,"url":null,"abstract":"<p><p>Brain tumor detection is crucial for clinical diagnosis and efficient therapy. In this work, we propose a hybrid approach for brain tumor classification based on both fractal geometry features and deep learning. In our proposed framework, we adopt the concept of fractal geometry to generate a \"percolation\" image with the aim of highlighting important spatial properties in brain images. Then both the original and the percolation images are provided as input to a convolutional neural network to detect the tumor. Extensive experiments, carried out on a well-known benchmark dataset, indicate that using percolation images can help the system perform better.</p>","PeriodicalId":7360,"journal":{"name":"Advances in neurobiology","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances in neurobiology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/978-3-031-47606-8_29","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Neuroscience","Score":null,"Total":0}
引用次数: 0
Abstract
Brain tumor detection is crucial for clinical diagnosis and efficient therapy. In this work, we propose a hybrid approach for brain tumor classification based on both fractal geometry features and deep learning. In our proposed framework, we adopt the concept of fractal geometry to generate a "percolation" image with the aim of highlighting important spatial properties in brain images. Then both the original and the percolation images are provided as input to a convolutional neural network to detect the tumor. Extensive experiments, carried out on a well-known benchmark dataset, indicate that using percolation images can help the system perform better.