Title: Deriving margins in prostate cancer radiotherapy treatment: comparison of neural network and fuzzy logic models
Authors: Bongile Mzenda; Alexander Gegov; David J. Brown; Nedyalko Petrov
Addresses: CancerPartnersUK, Tremona Road, Southampton, SO16 6UY, UK ' School of Computing, University of Portsmouth, Buckingham Building, Lion Terrace, Portsmouth, PO1 3HE, UK ' Institute of Industrial Research, University of Portsmouth, Mercantile House, Portsmouth, PO1 2EG, UK ' School of Computing, University of Portsmouth, Buckingham Building, Lion Terrace, Portsmouth, PO1 3HE, UK
Abstract: This study investigates the feasibility of using Artificial Neural Network (ANN) and fuzzy logic based techniques to select treatment margins for dynamically moving targets in the radiotherapy treatment of prostate cancer. The use of data from 15 patients relating error effects to the Tumour Control Probability (TCP) and Normal Tissue Complication Probability (NTCP) radiobiological indices was contrasted against the use of data based on the prostate volume receiving 99% of the prescribed dose (V99%) and the rectum volume receiving more than 60Gy (V60). For the same input data, the results of the ANN were compared to results obtained using a fuzzy system, a fuzzy network and current clinically used statistical techniques. Compared to fuzzy and statistical methods, the ANN derived margins were found to be up to 2 mm larger at small and high input errors and up to 3.5 mm larger at medium input error magnitudes.
Keywords: artificial neural networks; ANNs; fuzzy logic; cancer treatment margins; moving target; variable set-up errors; prostate cancer; radiotherapy treatment; modelling; tumour control; tissue complication.
International Journal of Bioinformatics Research and Applications, 2012 Vol.8 No.5/6, pp.325 - 341
Published online: 10 Oct 2012 *Full-text access for editors Access for subscribers Purchase this article Comment on this article