Quantum-Inspired Hamiltonian Descent for Radiation Therapy Treatment Planning
Abstract
Direct incorporation of dose-volume constraints into inverse radiotherapy planning leads to large mixed-integer optimization problems that accurately represent clinical requirements but are computationally challenging. We develop and evaluate a quantum-inspired approach for automated dose-volume-constrained intensity-modulated radiation therapy (IMRT) and intensity-modulated proton therapy (IMPT) planning. Clinical requirements are formulated as mixed-integer optimization problems, with binary variables representing dose-volume constraint violations. Patient-specific dose-influence matrices are generated at the photon control-point and proton spot levels, and intensities are optimized using Quantum-Inspired Hamiltonian Descent (QIHD). We evaluate QIHD on eight clinical cases: four IMRT (two prostate, one head-and-neck, and one liver) and four IMPT (two lung, one prostate, and one liver). The IMRT formulations contain 27,621 to 112,565 variables and are solved in 5 to 32 minutes, while the IMPT formulations contain 69,861 to 221,342 variables and are solved in 11 to 35 minutes on an NVIDIA RTX 4060 GPU. QIHD produces dose distributions satisfying clinical protocols without manual intervention. In comparison, a CPU implementation of Gurobi fails to solve most tested mixed-integer formulations within several hours. These results demonstrate the computational feasibility of GPU-accelerated QIHD for automated photon and proton treatment planning. Prospective clinical validation and implementation of decomposed subproblems on quantum hardware remain future directions.
Related
- An unified approach for the (inverted) quantum harmonic oscillator and the Berry-Keating hamiltonian
- A Quantum-Inspired Dequantization Method for Diagonally Weighted Matrix Functions: Application to Learning with Optimized Random Features
- Strict non-tightness of the level-3 quantum bootstrap for a natural three-dimensional Hamiltonian, at an excited level
- Deformed W-algebras and chiralized cluster seeds: subregular W-algebras and Inverse Quantum Hamiltonian Reduction
- Sustained growth of quantum circuit complexity in many-body Hamiltonian dynamics
BibTeX
@misc{mohammadisiahroydi2026quantuminspired,
title = {{Quantum-Inspired Hamiltonian Descent for Radiation Therapy Treatment Planning}},
author = {Mohammadhossein Mohammadisiahroydi and Yuxiang Peng and Jiaqi Leng and Robabeh Rahimi and Arezoo Modiri and Wei Zou and Tamas Terlaky and Xiaodi Wu},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.00989},
eprint = {2611.00989},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.00989},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Quantum-Inspired Hamiltonian Descent for Radiation Therapy Treatment Planning
AU - Mohammadhossein Mohammadisiahroydi
AU - Yuxiang Peng
AU - Jiaqi Leng
AU - Robabeh Rahimi
AU - Arezoo Modiri
AU - Wei Zou
AU - Tamas Terlaky
AU - Xiaodi Wu
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.00989
UR - https://arxiv.org/abs/2611.00989
AB - Direct incorporation of dose-volume constraints into inverse radiotherapy planning leads to large mixed-integer optimization problems that accurately represent clinical requirements but are computationally challenging. We develop and evaluate a quantum-inspired approach for automated dose-volume-constrained intensity-modulated radiation therapy (IMRT) and intensity-modulated proton therapy (IMPT) planning. Clinical requirements are formulated as mixed-integer optimization problems, with binary variables representing dose-volume constraint violations. Patient-specific dose-influence matrices are generated at the photon control-point and proton spot levels, and intensities are optimized using Quantum-Inspired Hamiltonian Descent (QIHD). We evaluate QIHD on eight clinical cases: four IMRT (two prostate, one head-and-neck, and one liver) and four IMPT (two lung, one prostate, and one liver). The IMRT formulations contain 27,621 to 112,565 variables and are solved in 5 to 32 minutes, while the IMPT formulations contain 69,861 to 221,342 variables and are solved in 11 to 35 minutes on an NVIDIA RTX 4060 GPU. QIHD produces dose distributions satisfying clinical protocols without manual intervention. In comparison, a CPU implementation of Gurobi fails to solve most tested mixed-integer formulations within several hours. These results demonstrate the computational feasibility of GPU-accelerated QIHD for automated photon and proton treatment planning. Prospective clinical validation and implementation of decomposed subproblems on quantum hardware remain future directions.
ER -