Logarithmic simulated annealing for X-ray diagnosis

Albrecht, Andreas A., Steinhofel, Kathleen, Taupitz, M. and Wong, C. K. (2001) Logarithmic simulated annealing for X-ray diagnosis. Artificial Intelligence in Medicine, 22 (3) . pp. 249-260. ISSN 0933-3657 [Article] (doi:10.1016/S0933-3657(00)00112-3)


We present a new stochastic learning algorithm and first results of computational experiments on fragments of liver CT images. The algorithm is designed to compute a depth-three threshold circuit, where the first layer is calculated by an extension of the Perceptron algorithm by a special type of simulated annealing. The fragments of CT images are of size 119×119 with eight bit grey levels. From 348 positive (focal liver tumours) and 348 negative examples a number of hypotheses of the type w1x1+⋯+wnxn≥ϑ were calculated for n=14161. The threshold functions at levels two and three were determined by computational experiments. The circuit was tested on various sets of 50+50 additional positive and negative examples. For depth-three circuits, we obtained a correct classification of about 97%. The input to the algorithm is derived from the DICOM standard representation of CT images. The simulated annealing procedure employs a logarithmic cooling schedule View the MathML source, where Γ is a parameter that depends on the underlying configuration space. In our experiments, the parameter Γ is chosen according to estimations of the maximum escape depth from local minima of the associated energy landscape.

Item Type: Article
Keywords (uncontrolled): CT images; Perceptron algorithm; simulated annealing; logarithmic cooling schedule; threshold functions; focal liver tumour
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 12408
Depositing User: Andreas Albrecht
Date Deposited: 12 Nov 2013 08:08
Last Modified: 12 Jun 2019 12:44
URI: https://eprints.mdx.ac.uk/id/eprint/12408

Actions (login required)

View Item View Item


Activity Overview
6 month trend
6 month trend

Additional statistics are available via IRStats2.