Results 1 
6 of
6
Learning Evaluation Functions for Global Optimization and Boolean Satisfiability
 In Proc. of 15th National Conf. on Artificial Intelligence (AAAI
, 1998
"... This paper describes STAGE, a learning approach to automatically improving search performance on optimization problems. STAGE learns an evaluation function which predicts the outcome of a local search algorithm, such as hillclimbing or WALKSAT, as a function of state features along its search ..."
Abstract

Cited by 59 (3 self)
 Add to MetaCart
This paper describes STAGE, a learning approach to automatically improving search performance on optimization problems. STAGE learns an evaluation function which predicts the outcome of a local search algorithm, such as hillclimbing or WALKSAT, as a function of state features along its search trajectories. The learned evaluation function is used to bias future search trajectories toward better optima. We present positive results on six largescale optimization domains.
CARABEAMER: A Treatment Planner for a Robotic Radiosurgical System with General Kinematics
 Medical Image Analysis
, 1998
"... : Stereotactic radiosurgery is a minimally invasive procedure that uses a focused beam of radiation as an ablative instrument to destroy brain tumors. To deposit a high dose of radiation in a tumor, while reducing the dose to healthy tissue, a large number of beams are crossfired at the tumor from m ..."
Abstract

Cited by 14 (5 self)
 Add to MetaCart
: Stereotactic radiosurgery is a minimally invasive procedure that uses a focused beam of radiation as an ablative instrument to destroy brain tumors. To deposit a high dose of radiation in a tumor, while reducing the dose to healthy tissue, a large number of beams are crossfired at the tumor from multiple directions. The treatment planning problem (also called the inverse dosimetry problem) is to compute a set of beams that produces a desired dose distribution. So far, its investigation has focused on the generation of isocenterbased treatments in which the beam axes intersect at a common point, the isocenter. However, this restriction limits the applicability of the treatments to tumors having simple shapes. This paper describes carabeamer, a new treatment planner for a radiosurgical system in which the radiation source can be arbitrarily positioned and oriented by a sixdegreeoffreedom manipulator. This planner uses randomized techniques to guess a promising initial set of beams....
An optimization framework for conformal radiation treatment planning
 INFORMS Journal on Computing, forthcoming
, 2006
"... doi 10.1287/ijoc.1060.0179 ..."
Fast simultaneous angle, wedge, and beam intensity optimization in inverse radiotherapy planning. Optimization and Engineering
"... We present a new fast radiotherapy planning algorithm which determines approximatively optimal gantry and table angles, kinds of wedges, leaf positions and intensities simultaneously in a global way. Other parameters are optimized only independently of each other. The algorithm uses an elaborate fie ..."
Abstract

Cited by 6 (1 self)
 Add to MetaCart
We present a new fast radiotherapy planning algorithm which determines approximatively optimal gantry and table angles, kinds of wedges, leaf positions and intensities simultaneously in a global way. Other parameters are optimized only independently of each other. The algorithm uses an elaborate field management and field reduction. Beam intensities are determined via a variant of a projected Newton method of Bertsekas. The objective function is a standard piecewise quadratic penalty function, but it is built with efficient upper bounds which are calculated during the optimization process. Instead of pencil beams, basic leaf positions are included. The algorithm is implemented in the new beam modelling and dose optimization module Homo OptiS. 1
A PathPlanning Algorithm for ImageGuided Neurosurgery
"... . A computer algorithm for determining optimal surgical paths in the brain is presented. The algorithm computes a cost function associated with each point on the outer brain boundary, which is treated as a candidate entry point. The cost function is determined partly based on a segmentation of the p ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
. A computer algorithm for determining optimal surgical paths in the brain is presented. The algorithm computes a cost function associated with each point on the outer brain boundary, which is treated as a candidate entry point. The cost function is determined partly based on a segmentation of the patients images into gray and white matter, and partly based on a spatially transformed atlas of the human brain registered to the patient's MR images. The importance of various structures, such as thalamic nuclei, optic nerve and radiations, and individual Brodman's areas, can be defined on the atlas and transferred onto the patient's images through the spatial transformation. The cost of a particular path associated with each critical structure, as well as the total cost of each path are computed and displayed, allowing the surgeon to define a low cost path, to visualize an arbitrary crosssection through the patient's MR images that contains this path, and to examine all the crosssectiona...
Robotic Radiosurgery with NonCylindrical Collimators
"... : In radiosurgery, a moving beam of radiation acts as an ablative surgical instrument. Conventional systems for radiosurgery use a cylindrical radiation beam of fixed crosssection. The radiation source can only be moved along simple standardized paths. A new radiosurgical system based on a six degr ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
: In radiosurgery, a moving beam of radiation acts as an ablative surgical instrument. Conventional systems for radiosurgery use a cylindrical radiation beam of fixed crosssection. The radiation source can only be moved along simple standardized paths. A new radiosurgical system based on a six degreeoffreedom robotic arm has been developed to overcome limitations of conventional systems. We address the following question: Can dose distributions generated by robotic radiosurgery be improved by using noncylindrical radiation beams? This includes static noncylindrical collimators and collimators of adaptable crosssection. Geometric methods for planning the shape of the beam in addition to planning beam motion are developed. Design criteria considered in this context are: treatment time, radiation penumbra as well as transparency of interactive treatment planning. An experimental evaluation compares distributions generated with our new radiosurgical system using cylindrical beams to ...