A novel method for sub-arc VMAT dose delivery verification based on portal dosimetry with an EPID

A recurrent neural network for rapid detection of delivery errors during real-time portal dosimetry

Background and purpose

Real-time portal dosimetry compares measured images with predicted images to detect delivery errors as the radiotherapy treatment proceeds. This work aimed to investigate the performance of a recurrent neural network for processing image metrics so as to detect delivery errors as early as possible in the treatment.

Materials and methods

Volumetric modulated arc therapy (VMAT) plans of six prostate patients were used to generate sequences of predicted portal images. Errors were introduced into the treatment plans and the modified plans were delivered to a water-equivalent phantom. Four different metrics were used to detect errors. These metrics were applied to a threshold-based method to detect the errors as soon as possible during the delivery, and also to a recurrent neural network consisting of four layers. A leave-two-out approach was used to set thresholds and train the neural network then test the resulting systems.

Results

When using a combination of metrics in conjunction with optimal thresholds, the median segment index at which the errors were detected was 107 out of 180. When using the neural network, the median segment index for error detection was 66 out of 180, with no false positives. The neural network reduced the rate of false negative results from 0.36 to 0.24.

Conclusions

The recurrent neural network allowed the detection of errors around 30% earlier than when using conventional threshold techniques. By appropriate training of the network, false positive alerts could be prevented, thereby avoiding unnecessary disruption to the patient workflow.

Optimisation of a composite difference metric for prompt error detection in real-time portal dosimetry of simulated volumetric modulated arc therapy

OBJECTIVES

In real-time portal dosimetry, thresholds are set for several measures of difference between predicted and measured images, and signals larger than those thresholds signify an error. The aim of this work is to investigate the use of an additional composite difference metric (CDM) for earlier detection of errors.

METHODS

Portal images were predicted for the volumetric modulated arc therapy plans of six prostate patients. Errors in monitor units, aperture opening, aperture position and path length were deliberately introduced into all 180 segments of the treatment plans, and these plans were delivered to a water-equivalent phantom. Four different metrics, consisting of central axis signal, mean image value and two image difference measures, were used to identify errors, and a CDM was added, consisting of a weighted power sum of the individual metrics. To optimise the weights of the CDM and to evaluate the resulting timeliness of error detection, a leave-pair-out strategy was used. For each combination of four patients, the weights of the CDM were determined by an exhaustive search, and the result was evaluated on the remaining two patients.

RESULTS

The median segment index at which the errors were identified was 87 (range 40-130) when using all of the individual metrics separately. Using a CDM as well as multiple separate metrics reduced this to 73 (35-95). The median weighting factors of the four metrics constituting the composite were (0.15, 0.10, 0.15, 0.00). Due to selection of suitable threshold levels, there was only one false positive result in the six patients.

CONCLUSION

This study shows that, in conjunction with appropriate error thresholds, use of a CDM is able to identify increased image differences around 20% earlier than the separate measures.

ADVANCES IN KNOWLEDGE

This study shows the value of combining difference metrics to allow earlier detection of errors during real-time portal dosimetry for volumetric modulated arc therapy treatment.

A method to verify sections of arc during intrafraction portal dosimetry for prostate VMAT

This study investigates the use of a running sum of images during segment-resolved intrafraction portal dosimetry for volumetric modulated arc therapy (VMAT), so as to alert the operator to an error before it becomes irremediable. At the time of treatment planning, predicted portal images were created for each segment of the VMAT arc, and at the time of delivery, intrafraction monitoring software polled the portal imager to read new images as they became available. The predicted and measured images were compared and displayed on a segment basis. In particular, a running sum of images from ten segments (a 'section') was investigated, with mean absolute difference between predicted and measured images being quantified. Images for 13 prostate patients were used to identify appropriate tolerance values for this statistic. Errors in monitor units of 2%-10%, field size of 2-10 mm, field position of 2-10 mm and path length of 10-50 mm were deliberately introduced into the treatment plans and delivered to a water-equivalent phantom and the sensitivity of the method to these errors was investigated. Gross errors were also considered for one case. The patient images show considerable variability from segment to segment, but when using a section of the arc the variability is reduced, so that the maximum value of mean absolute difference between predicted and measured images is reduced to below 12%, after excluding the first 10% of segments. This tolerance level is also found to be applicable for delivery of the plans to a water-equivalent phantom. Using this as a tolerance level for the error plans, a 10% increase in monitor units is detected, 4 mm increase or shift in multileaf collimator settings can be detected, and an air gap of dimensions 40 mm  ×  50 mm is detected. Gross errors can also be detected instantly after the first 10% of segments. The running difference between predicted and measured images over ten segments is able to identify errors at specific regions of the arc, as well as in the overall treatment.