A novel soft cluster neural network for the classification of suspicious areas in digital mammograms

Verma, Brijesh and McLeod, Peter and Klevansky, Alan (2009) A novel soft cluster neural network for the classification of suspicious areas in digital mammograms. Pattern Recognition, 42 (9). pp. 1845-1852. ISSN 0031-3203

Abstract

This paper presents a novel soft cluster neural network technique for the classification of suspicious areas in digital mammograms. The technique introduces the concept of soft clusters within a neural network layer and combines them with least squares for optimising neural network weights. The idea of soft clusters is proposed in order to increase the generalisation ability of the neural network by providing a mechanism to more aptly depict the relationship between the input features and the subsequent classification as either a benign or malignant class. Soft clusters with least squares make the training process faster and avoid iterative processes which have many problems. The proposed neural network technique has been tested on the DDSM benchmark database. The results are analysed and discussed in this paper.


Statistics for USQ ePrint 26519
Statistics for this ePrint Item
Item Type: Article (Commonwealth Reporting Category C)
Refereed: Yes
Item Status: Live Archive
Additional Information: Permanent restricted access to Published version due to publisher copyright policy.
Faculty / Department / School: Current - USQ Other
Date Deposited: 08 Jan 2015 02:20
Last Modified: 08 Jan 2015 03:06
Uncontrolled Keywords: pattern classification; neural networks; clustering algorithms
Fields of Research : 08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080109 Pattern Recognition and Data Mining
10 Technology > 1004 Medical Biotechnology > 100402 Medical Biotechnology Diagnostics (incl. Biosensors)
11 Medical and Health Sciences > 1103 Clinical Sciences > 110320 Radiology and Organ Imaging
Identification Number or DOI: 10.1016/j.patcog.2009.02.009
URI: http://eprints.usq.edu.au/id/eprint/26519

Actions (login required)

View Item Archive Repository Staff Only