Respiratory lung motion using an artificial neural network

One of the possibilities to enhance the accuracy of lung radiotherapy is to improve the understanding of the individual lung motion of each patient. Indeed, using this knowledge, it becomes possible to follow the evolution of the clinical target volume defined by a set of points according to the lung breathing phase. This paper presents an innovative method to simulate the positions of points in a person’s lungs for each breathing phase. Our method, based on an artificial neural network (ANN), allowed us to learn the lung motion of five different patients and then to simulate it accurately for three other patients using only beginning and end points. The training set for our ANN consisted of more than 1,100 points spread over ten breathing phases from the five patients on a specific area of the lungs. The points were defined by a medical expert. The first results are very promising: we obtain an average accuracy of 1.5 mm while the spatial resolution is 1  ×  1  ×  2.5 mm3. The accuracy of the method will be improved even more with additional data and providing complete lung coverage.

[1]  Stephen J. Wright,et al.  Numerical Optimization , 2018, Fundamental Statistical Inference.

[2]  Stephen J. Wright,et al.  Springer Series in Operations Research , 1999 .

[3]  Martin J Murphy,et al.  Optimization of an adaptive neural network to predict breathing. , 2008, Medical physics.

[4]  Hiroki Shirato,et al.  Hysteresis Analysis of Lung Tumor Motion in Radiation Treatment , 2008 .

[5]  J. Jaldén,et al.  On using an adaptive neural network to predict lung tumor motion during respiration for radiotherapy applications. , 2005, Medical physics.

[6]  Alen Docef,et al.  Nonlinear Set Membership time series prediction of breathing , 2008, 2008 16th European Signal Processing Conference.

[7]  F. Ernst,et al.  Prediction of respiratory motion with a multi-frequency based Extended Kalman Filter , 2007 .

[8]  William W. Hsieh.  Machine Learning Methods in the Environmental Sciences: Contents , 2009 .

[9]  Sylvain Contassot-Vivier,et al.  Dose calculations using artificial neural networks: A feasibility study for photon beams , 2008 .

[10]  Alfred Ultsch,et al.  Integration of Neural Networks and Knowledge-Based Systems in Medicine , 1995, AIME.

[11]  Steve B. Jiang,et al.  4D-CT lung motion estimation with deformable registration: quantification of motion nonlinearity and hysteresis. , 2008, Medical physics.

[12]  Abdulnasir Hossen,et al.  Identification of patients with congestive heart failure using different neural networks approaches. , 2009, Technology and health care : official journal of the European Society for Engineering and Medicine.

[13]  M. V. van Herk,et al.  Precise and real-time measurement of 3D tumor motion in lung due to breathing and heartbeat, measured during radiotherapy. , 2002, International journal of radiation oncology, biology, physics.

[14]  Zhou Zhihua,et al.  An intelligent medical image understanding method using two-tier neural network ensembles , 2005 .

[15]  Vlad Boldea.  Intégration de la respiration en radiothérapie: Apport du recalage déformable d'images , 2006 .

[16]  William W. Hsieh,et al.  Machine Learning Methods in the Environmental Sciences: Neural Networks and Kernels , 2009 .

[17]  Pierre-Frédéric Villard.  Simulation du Mouvement Pulmonaire pour un Traitement Oncologique , 2006 .

[18]  Patrick Clarysse,et al.  A Comparison Framework for Breathing Motion Estimation Methods From 4-D Imaging , 2007, IEEE Transactions on Medical Imaging.

[19]  Yi Sun,et al.  An EM Based Training Algorithm for Recurrent Neural Networks , 2009, ICANN.

[20]  Charles Soussen,et al.  Efficient Domain Decomposition for a Neural Network Learning Algorithm, Used for the Dose Evaluation in External Radiotherapy , 2010, ICANN.

[21]  Alexandre Hostettler,et al.  Real Time Simulation of Organ Motions Induced by Breathing: First Evaluation on Patient Data , 2006, ISBMS.

[22]  T. Bortfeld,et al.  The Use of Computers in Radiation Therapy , 2000, Springer Berlin Heidelberg.

[23]  Bo Yang,et al.  Evolving Hierarchical RBF Neural Networks for Breast Cancer Detection , 2006, ICONIP.

[24]  Julien Henriet,et al.  The future of new calculation concepts in dosimetry based on the Monte Carlo methods , 2009 .

[25]  John A. Mills,et al.  Respiratory motion prediction for adaptive radiotherapy , 2006 .

[26]  Michel Salomon,et al.  Avenir des nouveaux concepts des calculs dosimétriques basés sur les méthodes de Monte Carlo , 2009 .