Paper Proffered Program Therapy Physics

Analysis of Real-Time Cardiorespiratory Motion Prediction Algorithms for Mrigrt Stereotactic Arrhythmia Radioablation

Abstract
Purpose

Ventricular tachycardia (VT) arises when abnormal electrical impulses create rapid, self-sustaining ventricular activation instead of normal sinus rhythms. Stereotactic arrhythmia radioablation (STAR) is increasingly used as salvage treatment in refractory VT patients. Magnetic resonance–guided radiotherapy with multi-leaf collimator (MLC) tracking under cine-MRI guidance for STAR is expected to further enhance precision and reduce side effects. However, predicting combined cardiorespiratory motion is challenging for classical methods such as linear regression (LR), making system latency an unresolved issue.

Methods

We have collected multi-institutional cine-MRI (8-11 Hz) of the left ventricle and extracted cardiorespiratory motion traces totaling 190min using Segment Anything Model 2 (SAM2). The segmentation accuracy of SAM2 was evaluated against manual segmentations from 4 observers. Long-short-term-memory networks (LSTMs) trained on synthetic and cine-MRI cardiorespiratory motion traces, assuming 360ms MRI-linac latency, were compared to LR on four independent test sets. Both methods were updated online using the most recent data. Next, we evaluated how each prediction algorithm performed on deconvolved cardiorespiratory motion components, obtained through frequency filtering. Root-mean-square-error (RMSE) and the Wilcoxon signed-rank test were used as metric and statistical test.

Results

The RMSE between the segmentation center-of-mass of SAM2 against observer 1 (2.7±2.0 mm) and the average observer variation (3.4±1.5 mm) were comparable (p=0.14). The online LSTM (median±IQR RMSE: 2.4±1.1mm) outperformed LR (2.8±1.2mm) for combined motion (p<0.0001). The LSTM clearly outperformed the LR for respiratory motion (1.3±0.5mm vs. 2.0±1.0mm, p<0.0001). Both models performed comparably for cardiac motion (1.8±0.8mm vs. 1.9±0.6mm, p=0.98), suggesting that LR failed to predict the low-frequency motion component. Inference times of 5±1ms and online retraining times of 34±12ms (LSTM), 4±1ms (LR), and 49ms (SAM2) were measured.

Conclusion

We demonstrated that state-of-the-art online LSTMs can model cardiorespiratory motion simultaneously, which LR did not achieve. Online LSTMs exhibited a prediction performance comparable to the segmentation accuracy of SAM2.

People
Axel HengesseAuthors · Department of Radiation Oncology, LMU University Hospital, LMU Munich Elia Lombardo, PhDAuthors · Department of Radiation Oncology, LMU University Hospital, LMU Munich Tom Julius BlöckerAuthors · Department of Radiation Oncology, LMU University Hospital, LMU Munich Nicolas MühlschlegelPresenting Author · Department of Radiation Oncology, LMU University Hospital, LMU Munich Manon AubertAuthors · Department of Radiotherapy, University Medical Center Utrecht Michael KitzbergerAuthors · Smart Imaging Lab, Institute for Diagnostic Radiology, University Hospital Erlangen and Friedrich-Alexander University Erlangen-Nuremberg Christianna I. PapadopoulouAuthors · Department of Radiation Oncology, LMU University Hospital, LMU Munich Alexandre PfefferAuthors · Greater Paris University Hospitals - APHP, INSERM UMR-S 942 Guillaume PoirotAuthors · Department of Cardiothoracic Imaging, Hôpital Cardiologique du Haut-Lévêque, CHU de Bordeaux Martin DomanskyAuthors · Department of Oncology, 2nd Faculty of Medicine, Charles University Prague and Motol Denis DudasAuthors · Department of Radiation Oncology, LMU University Hospital, LMU Munich Jana Hutter, PhDAuthors · Smart Imaging Lab, Institute for Diagnostic Radiology, University Hospital Erlangen and Friedrich-Alexander University Erlangen-Nuremberg Olaf Dietrich, PhDAuthors · Department of Radiology, LMU University Hospital Munich Claus Belka, PhDAuthors · Bavarian Cancer Research Center (BZKF) Marco Riboldi, PhDAuthors · Department of Medical Physics, Ludwig-Maximilians-Universität München (LMU Munich) Stefanie Corradini, PhDAuthors · Department of Radiation Oncology, LMU University Hospital, LMU Munich Christopher Kurz, PhDAuthors · Department of Radiation Oncology, LMU University Hospital, LMU Munich Martin F. Fast, PhDAuthors · Department of Radiotherapy, University Medical Center Utrecht Guillaume Landry, PhDAuthors · Department of Radiation Oncology, LMU University Hospital, LMU Munich Rabea Klaar, PhDAuthors · Department of Radiology, LMU University Hospital, LMU Munich

Related

Similar sessions

Poster Poster Program
Jul 19 · 07:00
Python-Based Automation Framework for Annual Machine QA Data Archiving In Qatrack+

Annual water-tank measurements help ensure beam characteristics remain consistent with commissioning baselines. However, the lack of a standardized processing workflow and decentralized data storage makes it difficult to analyze...

Syed Bilal Ahmad, PhD
Therapy Physics 0 people interested
Poster Poster Program
Jul 19 · 07:00
User Expectations and Current Availability of HDR Brachytherapy Audits In Europe

The aim of this work was to evaluate the need to implement more dosimetric audits in high‐dose‐rate brachytherapy (HDR-BT) in Europe and to identify which characteristics such audits should meet according to users.

Javier Vijande, PhD Laura Oliver Cañamás
Therapy Physics 0 people interested