Purpose: The objective is to develop a software brachytherapy nomogram equivalent. Although modern techniques obviated much nomogram usage, situations arise where nomograms prove useful. If site dimensions are unknown, they can be measured followed by nomogram treatment planning. Regulatory agencies mandate independent checks. Deploying this software could easily meet this requirement. A graphical nomogram is fixed and cannot be modified. In contrast, the nomogram equivalent is configurable. This field‐customizable tool should further empower clinicians. Method and Materials: The nomogram equivalent is a three‐layer feed‐forward neural network (NN). The inputs consist of three site dimensions and volumes. The hidden layer has ten processing elements (PE's). The output layer is a single PE representing air kerma strength. The PE inputs are weighted, summed and applied to the sigmoid function, defining the PE output. A training algorithm based on differential evolution was developed. A group of fifty competing NN's are continuously evolved by simulating biological evolutionary processes. The weights are initially assigned random values. During training they are evolved to decrease the error between the NN output and desired value. Training data consist of three dimensions, volumes and air kerma strengths from past implants. The software cycles through the training data, altering the weights. The sum‐of‐squares difference between the outputs and air kerma strengths drives the training process. Once trained the NN can predict air kerma strengths for new implants. Results: The differential evolution training algorithm successfully determined NN weights for predicting required air kerma strengths. In most cases the network predicted air kerma strength within 11 percent. Consistent training data representing the full range of possible implant site dimensions and volumes are important for obtaining accurate predictions. Conclusion: The software is ready for clinical use. The authors believe that the NN paradigm is a sound method for implementing a field‐customizable nomogram equivalent.
Purpose: The accuracy of measured small cone parameters is important in the treatment of certain disorders like trigeminal neuralgia, where a single large dose is delivered via a small cone. The purpose of this presentation is to identify practical dosimeters for commissioning the cone accurately and efficiently in a community clinic. Method and Materials: Relative output factors for 5, 12.5, and 15 mm cones were measured using microMOSFET, Kodak EDR2 film, and TLD microcubes. TMRs for the 5 mm cone were measured using microMOSFET and BANG®polymer gel. OARs for the 5 mm cone were measured using radiographic and radiochromic films. Results: The output factor for the 5 mm cone measured with microMOSFET was 0.654 for a 6 MV beam and agreed with data published elsewhere. MicroMOSFET measurements agreed with EDR2 film and TLD microcubes measurements within 4.3% and 3.2% respectively for the 5 mm cone. All techniques were within 2.5% agreement for the 12.5 and 15 mm cones. TMR values measured with microMOSFET and polymer gel agreed within 3%. Radiographic and radiochromic film off‐axis ratio measurements showed differences not exceeding 1% above the 10% relative dose level. The measurements were verified using a MD Anderson Cancer Center phantom for a single static beam and polymer gel for a clinical set of three arcs. The doses reported by the institution and MDACC at dmax and 7.5 cm depth agreed within 4% and 3% respectively. The volumetric doses between the treatment planning system and the polymer gel were within 4%. Conclusion: The overall precision and accuracy of microMOSFET‐based measurement techniques are clinically acceptable. The microMOSFET is a feasible alternative with some advantages to TLD microcubes for dosimetric measurements of very small cones and fields. The polymer gel was found to be the only commercially available 3D‐dimensional verification dosimeter for these cones.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.