Nilesh L. Jain

Integrated software tools for the evaluation of radiotherapy treatment plans

PURPOSE This article announces the availability of a convenient and useful software environment for the evaluation of three-dimensional (3D) radiotherapy treatment plans. MATERIALS AND METHODS Using standards such as American National Standards for Information Systems C and the X Window System allowed us to bring the computation and display of dose-volume histograms, dose statistics, tumor control probabilities, normal tissue complication probabilities, and a figure of merit together under one user interface. These plan evaluation tools are not stand alone, but must interact with a 3D radiation therapy planning system to obtain the required dose matrices and patient anatomical contours. Installation of the software involves a programmer who writes a software bridge between the radiation therapy planning system and the tools, thereby providing access to local data files. This design strategy confines portability issues to one area of the software. RESULTS Access to the other tools is through the Graphical Plan Evaluation Tool (GPET). GPET coordinates the use of each of the tools and provides graphical facilities for display of their results. Importantly, GPET assures that the displayed results of each tool have been computed with the same input specifications for all treatment plans being compared. For added convenience, the user can rearrange the resultant data to be reviewed in various ways on the video screen. The software design also allows incorporation of customized algorithms and input data for computing tumor control probability and normal tissue complication probabilities, since those currently available are controversial. CONCLUSION The Graphical Plan Evaluation Tool unifies the simultaneous computation for several analytical tools and graphical display of their results. Within the constraints of the X Window System environment, this assemblage of software tools provides a portable, flexible, and convenient method for the quantitative evaluation of several radiotherapy treatment plans.

Ranking radiotherapy treatment plans using decision-analytic and heuristic techniques

Radiotherapy treatment optimization is done by generating a set of tentative treatment plans, evaluating them, and selecting the plan closest to achieving a set of conflicting treatment objectives. The evaluation of potential plans involves making trade-offs among competing possible outcomes. Multiattribute decision theory provides a framework for specifying such trade-offs and using them to select optimal actions. Using these concepts, we have developed a plan-ranking model which ranks a set of tentative treatment plans from best to worst. Heuristics are used to refine this model so that it reflects the clinical condition of the patient being treated and the practice preference of the physician prescribing the treatment. A figure of merit is computed for each tentative plan and is used to rank the plans. The approach described is very general and can be used for other medical domains having similar characteristics. The figure of merit can also be used as an objective function by computer programs that attempt to automatically generate an optimal treatment plan.

Clinical Decision-Support Systems in Radiation Therapy

Computers have been used in radiation therapy since the early 1960s to perform dose calculations. In the last decade, researchers have developed computer-based clinical decisionsupport systems for assisting in different decision-making tasks in radiation therapy. This paper reviews eleven prototype systems developed for target volume delineation, treatment planning, treatment plan evaluation, and treatment machine diagnosis. The advent of three-dimensional (3D) conformal radiation therapy (CRT) provides radiation oncologists with the opportunity to consider innovative beam arrangements which were not possible in two-dimensional class solutions. The difficulty of manually generating the thousands of clinically plausible 3D treatment plans calls for the... Read complete abstract on page 2.

Objective evaluation of radiation treatment plans.

The evaluation of radiation treatment plans involves making trade-offs among doses delivered to the tumor volumes and nearby normal tissues. Evaluating state-of-the-art three-dimensional (3D) plans is a difficult task because of the huge amount of planning data that needs to be deciphered. Multiattribute utility theory provides a methodology for specifying trade-offs and selecting the optimal plan from many competing plans. Using multiattribute utility theory, we are developing a clinically meaningful objective plan-evaluation model for 3D radiation treatment plans. Our model incorporates three of the factors involved in radiation treatment evaluation--treatment preferences of the radiation oncologist, clinical condition of the patient, and complexity of the treatment plan.

Research Proposal: Preference Acquisition through Reconciliation of Inconsistencies

The quality of performance of a decision-support system (or an expert system) is determined to a large extent by its underlying preference model (or knowledge base). The difficulties in preference and knowledge acquisition make them a major focus of current research in decision-support and expert systems. Researchers have used various concepts to develop promising acquisition techniques. One of the concepts used is knowledge maintenance where the knowledge base is changed in response to incorrect or inadequate performance by the expert system. This dissertation investigates a preference acquisition technique based on the reconciliation of inconsistencies between the preference model and the decision maker by allowing the decision maker to modify the preference model interactively. The technique can be used in the class of decision-support systems which objectively evaluate competing plans and select the best plan. The technique will be implemented in the domain of evaluating three-dimensional (3-D) radiation treatment plans. Another major aim of the dissertation is to develop a clinically-relevant objective plan-evaluation model for 3-D radiation treatment plans, and to build a clinical decision-support system to assist in that task using the new preference acquisition method. The author was partially supported by National Library of Medicine Training Grant 5-T-15-LM07049. This work was partially supported by National Cancer Institute Contract N01-CM-97564.