A deep learning model for predicting the modified micro-dosimetric kinetic model-based dose and the dose-averaged linear energy transfer for prostate cancer in carbon ion therapy

Liwen Zhang; Weiwei Wang; Ping Li; Qing Zhang; Rongcheng Han

Physics and Imaging in Radiation Oncology (Oct 2024)

A deep learning model for predicting the modified micro-dosimetric kinetic model-based dose and the dose-averaged linear energy transfer for prostate cancer in carbon ion therapy

Liwen Zhang,
Weiwei Wang,
Ping Li,
Qing Zhang,
Rongcheng Han

Affiliations

Liwen Zhang: Department of Medical Physics, Shanghai Proton and Heavy Ion Center, Shanghai 201321, China; Shanghai Key Laboratory of Radiation Oncology, China; Shanghai Engineering Research Center of Proton and Heavy Ion Radiation Therapy, China
Weiwei Wang: Department of Medical Physics, Shanghai Proton and Heavy Ion Center, Shanghai 201321, China; Shanghai Key Laboratory of Radiation Oncology, China; Shanghai Engineering Research Center of Proton and Heavy Ion Radiation Therapy, China
Ping Li: Shanghai Key Laboratory of Radiation Oncology, China; Shanghai Engineering Research Center of Proton and Heavy Ion Radiation Therapy, China; Department of Radiation Oncology, Shanghai Proton and Heavy Ion Center, Fudan University Cancer Hospital, Shanghai 201321, China
Qing Zhang: Shanghai Key Laboratory of Radiation Oncology, China; Shanghai Engineering Research Center of Proton and Heavy Ion Radiation Therapy, China; Department of Radiation Oncology, Shanghai Proton and Heavy Ion Center, Fudan University Cancer Hospital, Shanghai 201321, China; Corresponding authors at: 4365 Kangxin Road, Pudong, Shanghai, China.
Rongcheng Han: Department of Medical Physics, Shanghai Proton and Heavy Ion Center, Shanghai 201321, China; Shanghai Key Laboratory of Radiation Oncology, China; Shanghai Engineering Research Center of Proton and Heavy Ion Radiation Therapy, China; Corresponding authors at: 4365 Kangxin Road, Pudong, Shanghai, China.

Journal volume & issue: Vol. 32
p. 100671

Abstract

Read online

Adaptive carbon ion radiotherapy for localized prostate cancer requires accurate evaluation of biological dose and dose-averaged linear energy transfer (LETd) changes. This study developed a deep learning model to rapidly predict the modified micro-dosimetric kinetic model (mMKM)-based dose and LETd distributions. Using data from fifty patients for training and testing, the model achieved gamma passing rates exceeding 96% compared to true mMKM-based dose and LETd recalculated from local effect model I (LEM I) plans. Incorporating computed tomography images, contours, physical dose, and LEM I-based dose as inputs, this model provided a rapid, accurate tool for comprehensive evaluations.

Published in Physics and Imaging in Radiation Oncology

ISSN: 2405-6316 (Online)
Publisher: Elsevier
Country of publisher: Ireland
LCC subjects: Medicine: Medicine (General): Medical physics. Medical radiology. Nuclear medicine; Medicine: Internal medicine: Neoplasms. Tumors. Oncology. Including cancer and carcinogens
Website: https://www.journals.elsevier.com/physics-and-imaging-in-radiation-oncology/

About the journal

Abstract

Keywords