e-Περιοδικό Επιστήμης & Τεχνολογίας

e-Journal of Science & Technology, (e-JST)


Accelerating the design of probabilistic neural networks for computer aided diagnosis in Mammography, employing graphics processing units

Konstantinos Sidiropoulos1, Dionisis Cavouras2, Nikolaos Pagonis3, Nikos Dimitropoulos4 and John Stonham1

1 School of Engineering and Design, Brunel University West London, Uxbridge,

Middlesex, UB8 3PH, UK, e-mail: Konstantinos.Sidiropoulos@brunel.ac.uk

2 Medical Image & Signal Processing Laboratory, Department of Medical Instrumentation Technology, Technological Educational Institution of Athens, 12210, Athens, Greece.

3 Medical Image Processing and Analysis Group (MIPA), Laboratory of Medical Physics, School of Medicine, University of Patras, 26500 Rio, Greece.

4 Medical Imaging Department, EUROMEDICA Medical Center, Athens, Greece.

Abstract. The aim of this study is to propose a Probabilistic Neural Network (PNN) classifier system that can operate on a consumer-level graphics processing unit (GPU) and thus, harvest its tremendous parallel computation potential in order to accelerate the training phase. Therefore, the computationally intensive training of a PNN classifier system incorporating the exhaustive search of feature combinations and the leave-one-out techniques, was effectively ported on a medium class GPU device. Programming of the GPU was accomplished by means of the CUDA framework. The proposed system was tested on a real training dataset comprising 80 patterns, each consisting of 20 textural features extracted from digital mammograms (40 normal and 40 containing micro-calcifications) by an experienced physician. The developed GPU-based classifier was trained and the required time was measured. The latter was then compared with the respective training time of the same classifier running on a typical CPU and programmed in the C programming language. According to experimental results, the proposed GPU-based classifier achieved significantly higher training speed, outperforming the CPU-based system by a factor that ranged from 10 to 75 times.


Keywords: probabilistic neural networks, graphics processing units.