Predicting the parameters of a prostate IMRT objective function based on dose statistics under fixed parameter settings Renzhi Lu, Richard J. Radke 1,

Slides:



Advertisements
Similar presentations
Item Based Collaborative Filtering Recommendation Algorithms
Advertisements

Biologiske modeller i stråleterapi Dag Rune Olsen, The Norwegian Radium Hospital, University of Oslo.
THE COMPLETE ELECTRODE MODEL FOR IMAGING AND ELECTRODE CONTACT COMPENSATION IN ELECTRICAL IMPEDANCE TOMOGRAPHY G. Boverman 1, B.S. Kim 1, T.-J. Kao 3,
Particle Swarm Optimization (PSO)  Kennedy, J., Eberhart, R. C. (1995). Particle swarm optimization. Proc. IEEE International Conference.
Background:  IMRT has become the choice of treatment for disease sites that require critical structure sparing such as head and neck cancer.  It has.
Effects of Sampling in IMRT Optimization by Ronald L. Rardin Professor of Industrial Engineering Purdue University West Lafayette, Indiana, USA Caesarea.
What is radiation therapy (RT)? Cancer treatment Tumor versus normal tissues External photon beam RT.
The Calibration Process
Method for Determining Apparent Diffusion Coefficient Values for Cerebral Lesions from Diffusion Weighted Magnetic Resonance Imaging Examinations T.H.
Guidelines on Statistical Analysis and Reporting of DNA Microarray Studies of Clinical Outcome Richard Simon, D.Sc. Chief, Biometric Research Branch National.
Introduction Modern radiation therapies such as intensity-modulated radiation therapy (IMRT) and volume modulated arc therapy (VMAT) demand from dose calculation.
Discriminant Analysis Testing latent variables as predictors of groups.
Image Guided Surgery in Prostate Brachytherapy Rohit Saboo.
Results The measured-to-predicted dose ratio criteria used by the RPC to credential institutions is , however for this work, a criteria of
به نام خداوند بخشایندۀ بخشایشگر
1 Prediction of Software Reliability Using Neural Network and Fuzzy Logic Professor David Rine Seminar Notes.
Measurement of Dose to Critical Structures Surrounding the Prostate from Intensity-Modulated Radiation Therapy (IMRT) and Three Dimensional Conformal Radiation.
Comparison of Rectal Dose Volume Histograms for Definitive Prostate Radiotherapy Among Stereotactic Radiotherapy, IMRT, and 3D-CRT Techniques Author(s):
Data Mining to Aid Beam Angle Selection for IMRT Stuart Price-University of Maryland Bruce Golden- University of Maryland Edward Wasil- American University.
INTRODUCTION  The majority of clinical trials addressing outcomes in limited- stage small cell lung cancer (LS-SCLC) following definitive chemoradiotherapy.
H Ariyaratne1,2, H Chesham2, J Pettingell2, K Sikora2, R Alonzi1,2
Parameter selection in prostate IMRT Renzhi Lu, Richard J. Radke 1, Andrew Jackson 2 Rensselaer Polytechnic Institute 1,Memorial Sloan-Kettering Cancer.
Factors Influencing the Dose to Rectum During the Treatment of Prostate Cancer with IMRT Nandanuri M.S. Reddy, PhD, Brij M. Sood, MD, and Dattatreyudu.
Advances in Radiotherapy Planning Core problems:  shape modeling  image segmentation  organ tracking  radiation planning  dose optimization  Visualization.
Clinico-Dosimetric Correlation for Acute and Chronic Gastrointestinal Toxicity in Patients of Locally Advanced Carcinoma Cervix Treated With Conventional.
BREAST MRI IN RADIATION THERAPY PLANNING MARSHA HALEY, M.D. ASSISTANT PROFESSOR UNIVERSITY OF PITTSBURGH CANCER INSTITUTE PITTSBURGH, PENNSYLVANIA, USA.
IMRT QA Plan Site 5%/3mm3%/3mm2%/2mm 0% noise1% noise2% noise0% noise1% noise2% noise0% noise1% noise2% noise HN
Surface Reconstruction of Blood Vessels from 3D Fluorescence Microscopy Images Abstract This project aims at doing a surface reconstruction of 3D fluorescence.
3DCS Advanced Analyzer/Optimizer Module © Dimensional Control Systems Inc DCS Advanced Analyzer/Optimizer Equation Based Tolerance Analysis Quick.
Department of Electrical Engineering, Southern Taiwan University Robotic Interaction Learning Lab 1 The optimization of the application of fuzzy ant colony.
Medical considerations to guide mixed integer formulations of IMRT planning problems from MD to NP to CR Mark Langer, MD Radiation Oncology Indiana University.
Transportation Engineering (CIVTREN) notes of AM Fillone, DLSU-Manila
Investigation of 3D Dosimetry for an Anthropomorphic Spine Phantom R. Grant 1,2, G. Ibbott 1, J. Yang 1, J. Adamovics 3, D Followill 1 (1)M.D. Anderson.
Suppression of the eyelash artifact in ultra-widefield retinal images Vanessa Ortiz-Rivera – Dr. Badrinath Roysam, Advisor –
Wang Chen, Dr. Miriam Leeser, Dr. Carey Rappaport Goal Speedup 3D Finite-Difference Time-Domain.
Guest lecture: Feature Selection Alan Qi Dec 2, 2004.
Visualization of Tumors in 4D Medical CT Datasets Visualization of Tumors in 4D Medical CT Datasets Burak Erem 1, David Kaeli 1, Dana Brooks 1, George.
Cancer.orgPredict Results of a multicentric in silico clinical trial (ROCOCO): comparing radiotherapy with photons and protons for non-small cell lung.
Correlation Evaluation of a Tumor Tracking System Using Multiple External Markers Hui Yan, Fang-Fang Yin, et al (Duke University Med. Ctr.)
Learning Photographic Global Tonal Adjustment with a Database of Input / Output Image Pairs.
Optimization of Volumetric Modulated Arc Therapy (VMAT) Planning Strategy Using Ring-shaped ROI for Localized Prostate cancer Kentaro Ishii, Masako Hosono,
Karolina Kokurewicz Supervisors: Dino Jaroszynski, Giuseppe Schettino
Quantitative Analysis of Mitochondrial Tubulation Using 3D Imaging Saritha Dwarakapuram*, Badrinath Roysam*, Gang Lin*, Kasturi Mitra§ Department of Electrical.
Downscaling Global Climate Model Forecasts by Using Neural Networks Mark Bailey, Becca Latto, Dr. Nabin Malakar, Dr. Barry Gross, Pedro Placido The City.
Optimal Relay Placement for Indoor Sensor Networks Cuiyao Xue †, Yanmin Zhu †, Lei Ni †, Minglu Li †, Bo Li ‡ † Shanghai Jiao Tong University ‡ HK University.
The current density at each interfacial layer. The forward voltage is continuous at every point inside the body. A Layered Model for Breasts in Electrical.
Fast and parallel implementation of Image Processing Algorithm using CUDA Technology On GPU Hardware Neha Patil Badrinath Roysam Department of Electrical.
Building Valid, Credible & Appropriately Detailed Simulation Models
Evaluation of an Automatic Algorithm Based on Kernel Principal Component Analysis for Segmentation of the Bladder and Prostate in CT Scans Siqi Chen and.
Big data classification using neural network
Deep Learning for Dual-Energy X-Ray
You Zhang, Jeffrey Meyer, Joubin Nasehi Tehrani, Jing Wang
Feasibility of hippocampal sparing radiation therapy for glioblastoma using helical Tomotherapy Dr Kamalram THIPPU JAYAPRAKASH1,2,3, Dr Raj JENA1,4 and.
Evaluation Of RTOG Guidelines For Monte Carlo Based Lung SBRT Planning
Evaluation of the AAA Treatment Planning Algorithm for SBRT Lung Treatment: Comparison with Monte Carlo and Homogeneous Pencil Beam Dose Calculations 
Comparison of carina- versus bony anatomy-based registration for setup verification in esophageal cancer image-guided radiotherapy Melanie Machiels* 1,
Courtesy from Dr. McNutt
Clustering (3) Center-based algorithms Fuzzy k-means
CONTACT Catalina A. Riley
Fig. 4. Percentage of passing rate between clinical and 544 plans.
Reducing Treatment Time and MUs by using Dynamic Conformal Arc Therapy for SBRT Breath-Hold Patients Timothy Miller, Sebastian Nunez Albermann, Besil Raju,
Unfolding Problem: A Machine Learning Approach
Volumetric Modulated Arc Therapy (VMAT) versus Intensity Modulated Radiation Therapy (IMRT) for Anal Carcinoma Heather Ortega, BSRT(T), CMD, Kerry Hibbitts,
Insert tables Insert graphs Insert figure
An Adaptive Middleware for Supporting Time-Critical Event Response
Overfitting and Underfitting
Samsung Austin Semiconductor
Facultad de Ingeniería, Centro de Cálculo
Figure 3 Target volume definitions
Average Dose-Volume Ratio
Presentation transcript:

Predicting the parameters of a prostate IMRT objective function based on dose statistics under fixed parameter settings Renzhi Lu, Richard J. Radke 1, Andrew Jackson 2 Rensselaer Polytechnic Institute 1,Memorial Sloan-Kettering Cancer Center 2 Abstract To simplify the trial-and-error process of adjusting objective function parameters (e.g. weights, dose limits) in prostate IMRT planning, we present a feasibility study showing that machine learning followed by a sensitivity-driven greedy search can quickly and automatically determine parameters that lead to a plan meeting the clinical requirements. The training database is composed of a large number of plans treated effectively under the 8640cGy prostate IMRT protocol. For each plan, the output features include the clinical setting of parameters, and the input features include simple dose statistics resulting from several fixed settings of parameters. We predict a new plan based on the 3 nearest plans in the training database that have similar input features. Starting from such a pre-plan, a sensitivity based automatic parameter search is applied to improve the plan’s deficiencies. Experiments on a 39-patient dataset showed that a clinically acceptable (based on simplified dose calculation) prostate IMRT plan could be automatically determined within 2 minutes of optimization. State-of-the-art Hunt et al. gave specified procedure for changes to be made in optimization parameters given specific deficits in plans. Barbiere et al. looked for the best optimization parameters via structured grid searches over historical plans. Berger et al. utilized the parameters of similar cases in the historical database for a new patient. The similarity measure was based on an ellipsoidal patient geometry. Challenges and significance Planning a prostate IMRT case can take many hours, even for an expert planner. The bottleneck of current IMRT systems is not optimization, but the trial and error procedure of adjusting optimization parameters. Circumventing or minimizing this procedure would save many person-hours of effort. Technical approach 1. Problem description Fig. 1 Prostate IMRT: visualization of beams and structures Input : Settings for 5 beams. Contours for 6 structures. Optimization : : find the best radiation intensities I for a fixed parameter set P. Adjustment : Change the parameters P, redo optimization. Clinical goal: Dose D in target is as prescribed, in normal tissues is minimized. Our task: Find a set of P* such that minimizing the corresponding objective function meets all clinical goals. Fig.3 C omparison of dose evaluation statistics (based on simplified dose calculation) for: Upper: predicted pre-plans versus clinical plans. Lower: adjusted plans versus clinical plans Left to right: PTV V95, rectwall V54, rectwall Dmax Fig. 4 Comparison of dose volume histogram (based on simplified dose calculation) for predicted plans after adjustment vs clinical plans. Left: Patient 1. Right: Patient 2. We conclude that machine learning that utilizes the knowledge of past plans can predict a good starting point for parameter selection in IMRT. Given the deficiencies of the prediction, a sensitivity-driven greedy algorithm can effectively automate the necessary adjustment. Publications Ack. NSF Support :R. Lu et al, “Reduced-order parameter optimization for prostate Intensity- modulated Radiotherapy”, Phy in Med & Bio, Vol. 52, , Feb 2007 R. Lu, Richard Radke et al, “Learning the Relationship between Patient Geometry and Beam Intensity in Breast Intensity-Modulated Radiotherapy,” IEEE Trans. on Biom Eng, Vol. 53, No. 5, pp , May Future Plans Use machine learning to predict the intensities for general IMRT planning References 1. Hunt et al, “Evaluation of concave dose distributions created using an inverse planning system,” Int J Radiat Oncol Biol Phys, Vol 54, pp , J. Barbiere et al, “ A parameter optimization algorithm for intensity- modulated radiotherapy prostate treatment planning.”, J of Applied Clinical Med Phy, 3:227–234, J. Berger, Roentgen: radiation therapy and case-based reasoning Proceedings of the Tenth Conference on Artificial Intelligence, ,1994. Contact information Richard J. Radke, Assistant Professor Dept. of Electrical, Computer, and Systems Engineering Rensselaer Polytechnic Institute th Street, Troy, NY phone: (518) , This work was supported in part by Gordon-CenSSIS, the Bernard M. Gordon Center for Subsurface Sensing and Imaging Systems, under the Engineering Research Centers Program of the National Science Foundation (Award Number EEC ). 2. System overview Fig. 2 Overview of our two-step approach 3. Generating a pre-plan using machine learning Given a large number of historical plans, we use K-Nearest-Neighbor method that locates the K(=3) “closest” training cases and predicts P* based on a weighted average of the K training outputs. Input features: dose statistics D i under 3 fixed parameter settings of PTV{V95, Dmin}, rectum wall {V54,V87, Dmax}, and bladder wall V54. Output features: optimization parameters P Feature weighting: The input statistics may have different influences for each output parameter. We weight each statistic differently according to the correlation coefficients between Di and P in the training data, shown in Table 1. KNN regression is based on the K nearest training samples with output Pi and Euclidean distance di: Table 1. PEAR correlations between output parameters in P* (columns) and input statistics at default parameters P0 (rows) 4. Sensitivity driven greedy search Given the deficiencies in the pre-plan, determine which parameters should be tuned (by global sensitivity) and to which extent (by local sensitivity). Global sensitivity: Pearson correlation coefficient for the input/output pairs from Monte Carlo simulation Local sensitivity: Forward differentiation Greedy search: Each iteration updates the most sensitive parameter Pi to be: 5. Results In Figure 3(upper row), the PTV coverage for the pre-plans generally agrees with the ground truth and satisfies the clinical criteria. However, several predicted plans violate the rectum constraint boundaries. In Figure 3 (lower row), after greedy search the adjusted plan greatly improves the dose deficiencies in the rectum. The mean absolute differences across 39 patients for PTV V95, rectwall V54 and Dmax are 1.1%, 2.6% and 0.9%, respectively. Figure 4 compares sample DVHs for two cases. The adjusted plans both satisfy the clinical constraints.