Stereotactic arrhythmia radioablation in europe: treatment planning benchmark results of the STOPSTORM consortium

Funding Acknowledgements

Type of funding sources: Public grant(s) – EU funding. Main funding source(s): EU

Background

In patients with refractory ventricular tachycardia (VT), STereotactic Arrhythmia Radioablation (STAR) showed promising results for otherwise untreatable patients [1]. The STOPSTORM.eu project coordinates European efforts to clinically validate STAR and to refine protocols and guidelines to ensure treatment harmonization.

Purpose

The aim of this work is to present the current clinical STAR practise in Europe based on three examples as baseline for further optimization.

Methods

Target Volumes (TV) and Organs-at-Risk (OAR) were generated from previous consortium benchmarks and consensus definitions for three well-selected STAR cases [1]. Planning Target Volumes (PTV) were generated based on three different compensation strategies for cardiac and respiratory motion [2] and overlapped close OAR like coronary arteries or stomach in some areas. The STOPSTORM.eu members were asked to generate single fraction treatment plans with 25 Gy dose prescription based on ICRU report 91 for each case based on their clinical practise and preferences for STAR including multi-disciplinary discussion and plan approval. Resulting dose distributions were analysed independently using a customized platform for multi-center treatment planning studies [3].

Results

Twenty centers submitted 22, 23 and 22 treatment plans for case 1, 2 and 3, respectively, mostly (75% of all plans) using Intensity Modulated Arc Therapy (IMAT) with 6 MeV FFF beams (73% of the IMAT plans) among other commonly used techniques for stereotactic radiotherapy. At this current stage, used guidelines for STAR treatment planning and OAR dose limits vary greatly and are mostly based on the AAPM TG-101 report or the RAVENTA trial publication [4]. As a major finding, 73% of all plans submitted preferred close OAR sparing over achieving high PTV coverage arguing that lower doses down to 20 Gy may also result in clinical efficiency as recently suggested [5]. As a minor finding, 80% of the centers chose to override strong artifact regions originating from e.g. left ventricular assist devices.

Conclusion

From this first STOPSTORM.eu multi-center multi-platform treatment planning benchmark study we obtained important information concerning current clinical preference and practise from major European centers performing STereotactic Arrhythmia Radioablation for VT. Using the individual and strongly varying approaches of the centers, the key task for the STOPSTORM.eu project is now to find consensus in order to harmonize and optimize STAR practise in Europe.

Anthropogenic Marine Debris assessment with Unmanned Aerial Vehicle imagery and deep learning: A case study along the beaches of the Republic of Maldives

Anthropogenic Marine Debris (AMD) is one of the major environmental issues of our planet to date, and plastic accounts for 80% of total AMD. Beaches represent one of the main marine compartment where AMD accumulates, but few and scattered regional assessments are available from literature reporting quantitative estimation of AMD distributed on the shorelines. However, accessing information on the AMD accumulation rate on beaches, and the associated spatiotemporal oscillations, would be crucial to refining global estimation on the dispersal mechanisms. In our work, we address this issue by proposing an ad-hoc methodology for monitoring and automatically quantifying AMD, based on the combined use of a commercial Unmanned Aerial Vehicle (UAV) (equipped with an RGB high-resolution camera) and a deep-learning based software (i.e.: PlasticFinder). Remote areas were monitored by UAV and were inspected by operators on the ground to check and to categorise all AMD dispersed on the beach. The high-resolution images obtained from UAV allowed to visually detect a percentage of the objects on the shores higher than 87.8%, thus providing suitable images to populate training and testing datasets, as well as gold standards to evaluate the software performance. PlasticFinder reached a Sensitivity of 67%, with a Positive Predictive Value of 94%, in the automatic detection of AMD, but a limitation was found, due to reduced sunlight conditions, thus restricting to the use of the software in its present version. We, therefore, confirmed the efficiency of commercial UAVs as tools for AMD monitoring and demonstrated - for the first time - the potential of deep learning for the automatic detection and quantification of AMD.

A machine learning tool for re-planning and adaptive RT: A multicenter cohort investigation

PURPOSE

To predict patients who would benefit from adaptive radiotherapy (ART) and re-planning intervention based on machine learning from anatomical and dosimetric variations in a retrospective dataset.

MATERIALS AND METHODS

90 patients (pts) treated for head-neck cancer (H&N) formed a multicenter data-set. 41 H&N pts (45.6%) were considered for learning; 49 pts (54.4%) were used to test the tool. A homemade machine-learning classifier was developed to analyze volume and dose variations of parotid glands (PG). Using deformable image registration (DIR) and GPU, patients' conditions were analyzed automatically. Support Vector Machines (SVM) was used for time-series evaluation. "Inadequate" class identified patients that might benefit from replanning. Double-blind evaluation by two radiation oncologists (ROs) was carried out to validate day/week selected for re-planning by the classifier.

RESULTS

The cohort was affected by PG mean reduction of 23.7±8.8%. During the first 3weeks, 86.7% cases show PG deformation aligned with predefined tolerance, thus not requiring re-planning. From 4th week, an increased number of pts would potentially benefit from re-planning: a mean of 58% of cases, with an inter-center variability of 8.3%, showed "inadequate" conditions. 11% of cases showed "bias" due to DIR and script failure; 6% showed "warning" output due to potential positioning issues. Comparing re-planning suggested by tool with recommended by ROs, the 4th week seems the most favorable time in 70% cases.

CONCLUSIONS

SVM and decision-making tool was applied to overcome ART challenges. Pts would benefit from ART and ideal time for re-planning intervention was identified in this retrospective analysis.

Synthesis of magnetic gradients for NMR tomography

A numerical method is applied to calculate an optimal distribution of currents in air which generate the magnetic field gradients required to spatially encode the radiofrequency signal in a NMR tomographic experiment. We compare the performances of the gradient circuits for the whole body air-core electromagnet described by Bangert and Mansfield (J. Phys. E 15; 1982) with the results of our optimization.