Feature selection for computer-aided polyp detection using MRMR

Xiaoyun Yang*, Boray Tek, Gareth Beddoe, Greg Slabaugh

*Bu çalışma için yazışmadan sorumlu yazar

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde BölümKonferans katkısıbilirkişi

4 Atıf (Scopus)

Özet

In building robust classifiers for computer-aided detection (CAD) of lesions, selection of relevant features is of fundamental importance. Typically one is interested in determining which, of a large number of potentially redundant or noisy features, are most discriminative for classification. Searching all possible subsets of features is impractical computationally. This paper proposes a feature selection scheme combining AdaBoost with the Minimum Redundancy Maximum Relevance (MRMR) to focus on the most discriminative features. A fitness function is designed to determine the optimal number of features in a forward wrapper search. Bagging is applied to reduce the variance of the classifier and make a reliable selection. Experiments demonstrate that by selecting just 11 percent of the total features, the classifier can achieve better prediction on independent test data compared to the 70 percent of the total features selected by AdaBoost.

Orijinal dilİngilizce
Ana bilgisayar yayını başlığıMedical Imaging 2010
Ana bilgisayar yayını alt yazısıComputer-Aided Diagnosis
EditörlerRonald M. Summers, Nico Karssemeijer
YayınlayanSPIE
ISBN (Elektronik)9780819480255
DOI'lar
Yayın durumuYayınlandı - 2010
Harici olarak yayınlandıEvet
EtkinlikMedical Imaging 2010: Computer-Aided Diagnosis - San Diego, United States
Süre: 16 Şub 201018 Şub 2010

Yayın serisi

AdıProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Hacim7624
ISSN (Basılı)1605-7422

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???Medical Imaging 2010: Computer-Aided Diagnosis
Ülke/BölgeUnited States
ŞehirSan Diego
Periyot16/02/1018/02/10

Bibliyografik not

Publisher Copyright:
© 2010 SPIE.

Parmak izi

Feature selection for computer-aided polyp detection using MRMR' araştırma başlıklarına git. Birlikte benzersiz bir parmak izi oluştururlar.

Alıntı Yap