Deriving margins in prostate cancer radiotherapy treatment: comparison of neural network and fuzzy logic models

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.

[1]  Icru.  Prescribing, recording, and reporting photon beam therapy , 1993 .

[2]  Chris Beltran,et al.  Planning target margin calculations for prostate radiotherapy based on intrafraction and interfraction motion using four localization methods. , 2008, International journal of radiation oncology, biology, physics.

[3]  Alexander E. Gegov.  Fuzzy Networks for Complex Systems - A Modular Rule Base Approach , 2010, Studies in Fuzziness and Soft Computing.

[4]  Andrzej Niemierko,et al.  A free program for calculating EUD-based NTCP and TCP in external beam radiotherapy. , 2007, Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics.

[5]  P. Rust,et al.  Dose-volume relationship for acute side effects during high dose conformal radiotherapy for prostate cancer. , 2002, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[6]  J. Dayhoff,et al.  Artificial neural networks , 2001, Cancer.

[7]  M. V. van Herk,et al.  The probability of correct target dosage: dose-population histograms for deriving treatment margins in radiotherapy. , 2000, International journal of radiation oncology, biology, physics.

[8]  J C Stroom,et al.  Inclusion of geometrical uncertainties in radiotherapy treatment planning by means of coverage probability. , 1999, International journal of radiation oncology, biology, physics.

[9]  Licheng Jiao,et al.  Adaptive Tracking for Periodically Time-Varying and Nonlinearly Parameterized Systems Using Multilayer Neural Networks , 2010, IEEE Transactions on Neural Networks.

[10]  D. Gladstone,et al.  A numerical simulation of organ motion and daily setup uncertainties: implications for radiation therapy. , 1997, International journal of radiation oncology, biology, physics.

[11]  T. Ross.  Fuzzy Logic with Engineering Applications , 1994 .

[12]  B. Michaelis,et al.  Using an Artificial Neural Network to Define the Planning Target Volume in Radiotherapy , 2004, Journal of Medical Systems.

[13]  Xiao-Jun Zeng,et al.  Approximation Capabilities of Hierarchical Fuzzy Systems , 2005, IEEE Transactions on Fuzzy Systems.

[14]  W. Kwan,et al.  Various techniques of contouring the rectum and their impact on rectal dose-volume histograms. , 2003, Medical dosimetry : official journal of the American Association of Medical Dosimetrists.

[15]  Bongile Mzenda,et al.  A fuzzy convolution model for radiobiologically optimized radiotherapy margins , 2010, Physics in medicine and biology.

[16]  M. Goitein,et al.  Fitting of normal tissue tolerance data to an analytic function. , 1991, International journal of radiation oncology, biology, physics.

[17]  M. Goitein,et al.  Tolerance of normal tissue to therapeutic irradiation. , 1991, International journal of radiation oncology, biology, physics.