EVALUATION AND SCORING OF RADIOTHERAPY TREATMENT PLANS USING AN ARTIFICIAL NEURAL-NETWORK

Purpose: The objective of this work was to demonstrate the feasibility of using an artificial neural network to predict the clinical evaluat ion of radiotherapy treatment plans. Methods and Materials: Approximat ely 150 treatment plans were developed for 16 patients who received ex ternal-beam radiotherapy for soft-tissue sarcomas of the lower extremi ty. Plans were assigned a figure of merit by a radiation oncologist us ing a five-point rating scale, Plan scoring was performed by a single physician to ensure consistency in rating, Dose-volume information ext racted from a training set of 511 treatment plans on 14 patients was c orrelated to the physician-generated figure of merit using an artifici al neural network, The neural network was tested with a test set of 19 treatment plans on two patients whose plans were not used in the trai ning of the neural net. Results: Physician scoring of treatment plans was consistent to within one point on the rating scale 88% of the time , The neural net reproduced the physician scores in the training set t o within one point approximately 90% of the time. It reproduced the ph ysician scores in the test set to within one point approximately 83% o f the time. Conclusions: An artificial neural network can be trained t o generate a score for a treatment plan that can be correlated to a cl inically-based figure of merit, The accuracy of the neural net in scor ing plans compares well with the reproducibility of the clinical scori ng, The system of radiotherapy treatment plan evaluation using an arti ficial neural network demonstrates promise as a method for generating a clinically relevant figure of merit.