Francisco Berumen Murillo
Bio
Francisco is a PhD student at Université Laval in the CAMPEP accredited Medical Physics program working under the supervision of Dr. Luc Beaulieu and the co-supervision of Dr. Shirin Enger. Before moving to Quebec City in Canada, Francisco finished an MSc in Medical Physics at UNAM (National Autonomous University of Mexico) and a BSc in Physics at UAZ (Autonomous University of Zacatecas).
Current Projects
1. Dose prediction in LDR brachytherapy using deep learning methods.
2. Monte Carlo simulations using the TOPAS toolkit.
2024
Aleatoric and epistemic uncertainty extraction of patient-specific deep learning-based dose predictions in LDR prostate brachytherapy Journal Article
In: Physics in Medicine & Biology, vol. 69, no. 8, 2024.
@article{berumen2024aleatoric,
title = {Aleatoric and epistemic uncertainty extraction of patient-specific deep learning-based dose predictions in LDR prostate brachytherapy},
author = {Francisco Berumen and Samuel Ouellet and Shirin Enger and Luc Beaulieu},
doi = {10.1088/1361-6560/ad3418},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
journal = {Physics in Medicine & Biology},
volume = {69},
number = {8},
publisher = {IOP Publishing},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2023
Fast DM,M calculation in LDR brachytherapy using deep learning methods Journal Article
In: Physics in Medicine & Biology, 2023.
@article{nokey_29,
title = {Fast DM,M calculation in LDR brachytherapy using deep learning methods},
author = {Francisco Berumen and Shirin A. Enger and Luc Beaulieu},
doi = {10.1088/1361-6560/accd42},
year = {2023},
date = {2023-05-23},
urldate = {2023-05-23},
journal = {Physics in Medicine & Biology},
abstract = {Objective.The Monte Carlo (MC) method provides a complete solution to the tissue heterogeneity effects in low-energy low-dose rate (LDR) brachytherapy. However, long computation times limit the clinical implementation of MC-based treatment planning solutions. This work aims to apply deep learning (DL) methods, specifically a model trained with MC simulations, to predict accurate dose to medium in medium (DM,M) distributions in LDR prostate brachytherapy.Approach.To train the DL model, 2369 single-seed configurations, corresponding to 44 prostate patient plans, were used. These patients underwent LDR brachytherapy treatments in which125I SelectSeed sources were implanted. For each seed configuration, the patient geometry, the MC dose volume and the single-seed plan volume were used to train a 3D Unet convolutional neural network. Previous knowledge was included in the network as anr2kernel related to the first-order dose dependency in brachytherapy. MC and DL dose distributions were compared through the dose maps, isodose lines, and dose-volume histograms. Features enclosed in the model were visualized.Main results.Model features started from the symmetrical kernel and finalized with an anisotropic representation that considered the patient organs and their interfaces, the source position, and the low- and high-dose regions. For a full prostate patient, small differences were seen below the 20% isodose line. When comparing DL-based and MC-based calculations, the predicted CTVD90metric had an average difference of -0.1%. Average differences for OARs were -1.3%, 0.07%, and 4.9% for the rectumD2cc, the bladderD2cc, and the urethraD0.1cc. The model took 1.8 ms to predict a complete 3DDM,Mvolume (1.18 M voxels).Significance.The proposed DL model stands for a simple and fast engine which includes prior physics knowledge of the problem. Such an engine considers the anisotropy of a brachytherapy source and the patient tissue composition.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Objective.The Monte Carlo (MC) method provides a complete solution to the tissue heterogeneity effects in low-energy low-dose rate (LDR) brachytherapy. However, long computation times limit the clinical implementation of MC-based treatment planning solutions. This work aims to apply deep learning (DL) methods, specifically a model trained with MC simulations, to predict accurate dose to medium in medium (DM,M) distributions in LDR prostate brachytherapy.Approach.To train the DL model, 2369 single-seed configurations, corresponding to 44 prostate patient plans, were used. These patients underwent LDR brachytherapy treatments in which125I SelectSeed sources were implanted. For each seed configuration, the patient geometry, the MC dose volume and the single-seed plan volume were used to train a 3D Unet convolutional neural network. Previous knowledge was included in the network as anr2kernel related to the first-order dose dependency in brachytherapy. MC and DL dose distributions were compared through the dose maps, isodose lines, and dose-volume histograms. Features enclosed in the model were visualized.Main results.Model features started from the symmetrical kernel and finalized with an anisotropic representation that considered the patient organs and their interfaces, the source position, and the low- and high-dose regions. For a full prostate patient, small differences were seen below the 20% isodose line. When comparing DL-based and MC-based calculations, the predicted CTVD90metric had an average difference of -0.1%. Average differences for OARs were -1.3%, 0.07%, and 4.9% for the rectumD2cc, the bladderD2cc, and the urethraD0.1cc. The model took 1.8 ms to predict a complete 3DDM,Mvolume (1.18 M voxels).Significance.The proposed DL model stands for a simple and fast engine which includes prior physics knowledge of the problem. Such an engine considers the anisotropy of a brachytherapy source and the patient tissue composition.
2022
Sub-Second D (M, M) Calculation for LDR Prostate Brachytherapy Using Deep Learning Methods Proceedings Article
In: MEDICAL PHYSICS, pp. E163–E163, WILEY 111 RIVER ST, HOBOKEN 07030-5774, NJ USA 2022.
@inproceedings{berumen2022sub,
title = {Sub-Second D (M, M) Calculation for LDR Prostate Brachytherapy Using Deep Learning Methods},
author = {Francisco Berumen-Murillo and Shirin A. Enger and Luc Beaulieu},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {MEDICAL PHYSICS},
volume = {49},
number = {6},
pages = {E163--E163},
organization = {WILEY 111 RIVER ST, HOBOKEN 07030-5774, NJ USA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}