Pub Date : 2020-12-11DOI: 10.1109/MPCIT51588.2020.9350416
Deepak O. Patil, S. Hamde
Brain tumor has a low survival rate and also affect a patient’s social life. Early detection and further treatment of the abnormal growth of mass is a significant step during treatment to restrict the progression. MR image screening by the medical expert is a time-consuming and tedious task. This paper presents the development of computer-aided tool to detect brain tumor images. The proposed algorithm employs monogenic wavelet phase-encoded features for tumor detection. Phase component of the monogenic wavelet efficiently extracts the structural information from the input magnetic resonance images. The dimensionality of CLBP textural descriptors extracted from the phase component is further reduced using neighborhood component analysis feature selection. Finally, the support vector machine classifies the test magnetic resonance image as healthy or abnormal. The proposed approach is evaluated using two popular MR imaging databases and simulation results show enhanced performance compared to other existing algorithms.
{"title":"Monogenic Wavelet Phase Encoded Descriptors for Brain Tumor Image Detection","authors":"Deepak O. Patil, S. Hamde","doi":"10.1109/MPCIT51588.2020.9350416","DOIUrl":"https://doi.org/10.1109/MPCIT51588.2020.9350416","url":null,"abstract":"Brain tumor has a low survival rate and also affect a patient’s social life. Early detection and further treatment of the abnormal growth of mass is a significant step during treatment to restrict the progression. MR image screening by the medical expert is a time-consuming and tedious task. This paper presents the development of computer-aided tool to detect brain tumor images. The proposed algorithm employs monogenic wavelet phase-encoded features for tumor detection. Phase component of the monogenic wavelet efficiently extracts the structural information from the input magnetic resonance images. The dimensionality of CLBP textural descriptors extracted from the phase component is further reduced using neighborhood component analysis feature selection. Finally, the support vector machine classifies the test magnetic resonance image as healthy or abnormal. The proposed approach is evaluated using two popular MR imaging databases and simulation results show enhanced performance compared to other existing algorithms.","PeriodicalId":136514,"journal":{"name":"2020 Third International Conference on Multimedia Processing, Communication & Information Technology (MPCIT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132931096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：