ridm@nrct.go.th   ระบบคลังข้อมูลงานวิจัยไทย   รายการโปรดที่คุณเลือกไว้

Impact of multiple clusters on neural classification of ROIs in digital mammograms

หน่วยงาน Central Queensland University, Australia

รายละเอียด

ชื่อเรื่อง : Impact of multiple clusters on neural classification of ROIs in digital mammograms
นักวิจัย : Verma, Brijesh.
คำค้น : Applied research. , 920203 Diagnostic Methods. , TBA. , Breast , Diagnostic imaging , Pattern recognition systems. , Neural networks (Computer science) , Neural networks -- Digital mammography -- Clustering
หน่วยงาน : Central Queensland University, Australia
ผู้ร่วมงาน : -
ปีพิมพ์ : 2552
อ้างอิง : http://hdl.cqu.edu.au/10018/44496 , http://dx.doi.org/10.1109/IJCNN.2009.5178942
ที่มา : Verma, B 2009, 'Impact of multiple clusters on neural classification of ROIs in digital mammograms' in IEEE editors (eds.) Proceedings of the 2009 International Joint Conference on Neural Networks, Georgia, USA, 14-19 June 2009 , pp. 3220-3230.http://dx.doi.org/10.1109/IJCNN.2009.5178942 (viewed 7/5/10)
ความเชี่ยวชาญ : -
ความสัมพันธ์ : Proceedings of International Joint Conference on Neural Networks, Atlanta, Georgia, USA, June 14-19, 2009. NJ, USA. : IEEE, 2009. p. 3220-3230 11 pages Refereed 1098-7576 (online) 9781424435531 , ACQUIRE [electronic resource] : Central Queensland University Institutional Repository.
ขอบเขตของเนื้อหา : -
บทคัดย่อ/คำอธิบาย :

This paper evaluates the impact of multiple clusters on neural classification of regions of interest (ROIs) in digital mammograms. The training and test sets for neural networks usually contain inputs extracted from ROIs and relevant class such as benign and malignant. However, the patterns such as regions of interest in digital mammograms do not have just one cluster per class instead they have many clusters within benign and malignant classes. Therefore, neural network training may benefit in terms of accuracy and efficiency by creating and analyzing a number of clusters within a class. A novel multiple clusters based neural classification approach is presented. In this approach, input data is clustered into a number of clusters per class and a neural classifier is trained with clustered data which contain multiple clusters per class. The experiments on a benchmark database of digital mammograms are conducted. The results show that the multiple clusters per class have significant impact on neural classification and overall they achieve better accuracy than single cluster per class based classification of ROIs in digital mammograms.

บรรณานุกรม :
Verma, Brijesh. . (2552). Impact of multiple clusters on neural classification of ROIs in digital mammograms.
    กรุงเทพมหานคร : Central Queensland University, Australia.
Verma, Brijesh. . 2552. "Impact of multiple clusters on neural classification of ROIs in digital mammograms".
    กรุงเทพมหานคร : Central Queensland University, Australia.
Verma, Brijesh. . "Impact of multiple clusters on neural classification of ROIs in digital mammograms."
    กรุงเทพมหานคร : Central Queensland University, Australia, 2552. Print.
Verma, Brijesh. . Impact of multiple clusters on neural classification of ROIs in digital mammograms. กรุงเทพมหานคร : Central Queensland University, Australia; 2552.