Portal dose image prediction using Monte Carlo generated transmission energy fluence maps of dynamic radiotherapy treatment plans: a deep learning approach
2025 (English)In: Biomedical Engineering & Physics Express, E-ISSN 2057-1976, Vol. 11, no 3, article id 035013Article in journal (Refereed) Published
Abstract [en]
Aims. This work aims to develop and investigate the feasibility of a hybrid model combining Monte Carlo (MC) simulations and deep learning (DL) to predict electronic portal imaging device (EPID) images based on MC-generated exit phase space energy fluence maps from dynamic radiotherapy treatment plans. Such predicted images can be used as reference images during in vivo dosimetry. Materials and methods. MC simulations involving a Varian True Beam linear accelerator model were performed using the EGSnrc code package. Two custom variants of the U-Net architecture were employed. The MLC dynamic chair sequence and 17 clinical treatment plans, spanning various cancer types and delivery methods, were used to acquire experimental data, and in the MC simulations. The proposed method was tested through 2D gamma index analysis, comparing predicted and measured EPID images. Results. Results showed gamma passing rates of 38.65%, 74.16% and 96.17% (minimum, median, maximum) for a simpler model variant and 52.72%, 80.61% and 96.80% for the more complex model variant. Conclusion. The study highlights the feasibility of integrating MC and DL methodologies for in vivo dosimetry quality assurance in complex radiotherapy delivery.
Place, publisher, year, edition, pages
Institute of Physics , 2025. Vol. 11, no 3, article id 035013
Keywords [en]
Algorithms; Computer Simulation; Deep Learning; Humans; Image Processing, Computer-Assisted; Monte Carlo Method; Neoplasms; Particle Accelerators; Phantoms, Imaging; Radiotherapy Dosage; Radiotherapy Planning, Computer-Assisted; Radiotherapy, Intensity-Modulated; Failure analysis; Gamma rays; Hadrons; Photons; Radiotherapy; Electronic portal imaging device dosimetry; Electronic portal imaging devices; Energy fluences; Monte carlo; Monte Carlo’s simulation; Radiotherapy treatment; Simulation; Transmission dosimetry; Treatment plans; Article; cancer radiotherapy; comparative study; deep learning; feasibility study; gamma radiation; human; in vivo dosimetry; intensity modulated radiation therapy; Monte Carlo method; prediction; radiation beam; radiation dose distribution; radiation energy; radiotherapy dosage; treatment planning; U-Net architecture; volumetric modulated arc therapy; algorithm; computer simulation; image processing; imaging phantom; magnetic and electromagnetic equipment; neoplasm; procedures; radiotherapy; radiotherapy dosage; radiotherapy planning system; Dosimetry
National Category
Clinical Medicine
Identifiers
URN: urn:nbn:se:ri:diva-78350DOI: 10.1088/2057-1976/adc73fScopus ID: 2-s2.0-105002288096OAI: oai:DiVA.org:ri-78350DiVA, id: diva2:1999856
Note
Financial support from King Gustav V’s Jubilee Clinic Foundation, the Swedish Radiation Safety Authority the Healthcare Committee, Region Västra Götaland are greatly acknowledged.
2025-09-222025-09-222025-09-23Bibliographically approved