Individualizing glioma radiotherapy planning by optimization of a data and physics-informed discrete loss

Abstract Brain tumor growth is unique to each glioma patient and extends beyond what is visible in imaging scans, infiltrating surrounding brain tissue. Understanding these hidden patient-specific progressions is essential for effective therapies. Current treatment plans for brain tumors, such as ra...

Full description

Saved in:
Bibliographic Details
Main Authors: Michal Balcerak, Jonas Weidner, Petr Karnakov, Ivan Ezhov, Sergey Litvinov, Petros Koumoutsakos, Tamaz Amiranashvili, Ray Zirui Zhang, John S. Lowengrub, Igor Yakushev, Benedikt Wiestler, Bjoern Menze
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-60366-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849764595991838720
author Michal Balcerak
Jonas Weidner
Petr Karnakov
Ivan Ezhov
Sergey Litvinov
Petros Koumoutsakos
Tamaz Amiranashvili
Ray Zirui Zhang
John S. Lowengrub
Igor Yakushev
Benedikt Wiestler
Bjoern Menze
author_facet Michal Balcerak
Jonas Weidner
Petr Karnakov
Ivan Ezhov
Sergey Litvinov
Petros Koumoutsakos
Tamaz Amiranashvili
Ray Zirui Zhang
John S. Lowengrub
Igor Yakushev
Benedikt Wiestler
Bjoern Menze
author_sort Michal Balcerak
collection DOAJ
description Abstract Brain tumor growth is unique to each glioma patient and extends beyond what is visible in imaging scans, infiltrating surrounding brain tissue. Understanding these hidden patient-specific progressions is essential for effective therapies. Current treatment plans for brain tumors, such as radiotherapy, typically involve delineating a uniform margin around the visible tumor on pre-treatment scans to target this invisible tumor growth. This “one size fits all" approach is derived from population studies and often fails to account for the nuances of individual patient conditions. We present the Glioma Optimizing the Discrete Loss (GliODIL) framework, which infers the full spatial distribution of tumor cell concentration from available multi-modal imaging, leveraging a Fisher-Kolmogorov type physics model to describe tumor growth. This is achieved through the newly introduced method of Optimizing the Discrete Loss (ODIL), where both data and physics-based constraints are softly assimilated into the solution. Our test dataset comprises 152 glioblastoma patients with pre-treatment imaging and post-treatment follow-ups for tumor recurrence monitoring. By blending data-driven techniques with physics-based constraints, GliODIL enhances recurrence prediction in radiotherapy planning, challenging traditional uniform margins and strict adherence to the Fisher-Kolmogorov partial differential equation model, which is adapted for complex cases.
format Article
id doaj-art-a32b60ab9c474ce095731de35455474d
institution DOAJ
issn 2041-1723
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-a32b60ab9c474ce095731de35455474d2025-08-20T03:05:06ZengNature PortfolioNature Communications2041-17232025-07-0116111610.1038/s41467-025-60366-4Individualizing glioma radiotherapy planning by optimization of a data and physics-informed discrete lossMichal Balcerak0Jonas Weidner1Petr Karnakov2Ivan Ezhov3Sergey Litvinov4Petros Koumoutsakos5Tamaz Amiranashvili6Ray Zirui Zhang7John S. Lowengrub8Igor Yakushev9Benedikt Wiestler10Bjoern Menze11Department of Quantitative Biomedicine, University of ZurichDepartment of Computer Science, Technical University of MunichComputational Science and Engineering Laboratory, Harvard UniversityDepartment of Computer Science, Technical University of MunichComputational Science and Engineering Laboratory, Harvard UniversityComputational Science and Engineering Laboratory, Harvard UniversityDepartment of Quantitative Biomedicine, University of ZurichDepartment of Mathematics, University of CaliforniaDepartment of Mathematics, University of CaliforniaDepartment of Nuclear Medicine, Technical University of MunichMunich Center for Machine Learning (MCML)Department of Quantitative Biomedicine, University of ZurichAbstract Brain tumor growth is unique to each glioma patient and extends beyond what is visible in imaging scans, infiltrating surrounding brain tissue. Understanding these hidden patient-specific progressions is essential for effective therapies. Current treatment plans for brain tumors, such as radiotherapy, typically involve delineating a uniform margin around the visible tumor on pre-treatment scans to target this invisible tumor growth. This “one size fits all" approach is derived from population studies and often fails to account for the nuances of individual patient conditions. We present the Glioma Optimizing the Discrete Loss (GliODIL) framework, which infers the full spatial distribution of tumor cell concentration from available multi-modal imaging, leveraging a Fisher-Kolmogorov type physics model to describe tumor growth. This is achieved through the newly introduced method of Optimizing the Discrete Loss (ODIL), where both data and physics-based constraints are softly assimilated into the solution. Our test dataset comprises 152 glioblastoma patients with pre-treatment imaging and post-treatment follow-ups for tumor recurrence monitoring. By blending data-driven techniques with physics-based constraints, GliODIL enhances recurrence prediction in radiotherapy planning, challenging traditional uniform margins and strict adherence to the Fisher-Kolmogorov partial differential equation model, which is adapted for complex cases.https://doi.org/10.1038/s41467-025-60366-4
spellingShingle Michal Balcerak
Jonas Weidner
Petr Karnakov
Ivan Ezhov
Sergey Litvinov
Petros Koumoutsakos
Tamaz Amiranashvili
Ray Zirui Zhang
John S. Lowengrub
Igor Yakushev
Benedikt Wiestler
Bjoern Menze
Individualizing glioma radiotherapy planning by optimization of a data and physics-informed discrete loss
Nature Communications
title Individualizing glioma radiotherapy planning by optimization of a data and physics-informed discrete loss
title_full Individualizing glioma radiotherapy planning by optimization of a data and physics-informed discrete loss
title_fullStr Individualizing glioma radiotherapy planning by optimization of a data and physics-informed discrete loss
title_full_unstemmed Individualizing glioma radiotherapy planning by optimization of a data and physics-informed discrete loss
title_short Individualizing glioma radiotherapy planning by optimization of a data and physics-informed discrete loss
title_sort individualizing glioma radiotherapy planning by optimization of a data and physics informed discrete loss
url https://doi.org/10.1038/s41467-025-60366-4
work_keys_str_mv AT michalbalcerak individualizinggliomaradiotherapyplanningbyoptimizationofadataandphysicsinformeddiscreteloss
AT jonasweidner individualizinggliomaradiotherapyplanningbyoptimizationofadataandphysicsinformeddiscreteloss
AT petrkarnakov individualizinggliomaradiotherapyplanningbyoptimizationofadataandphysicsinformeddiscreteloss
AT ivanezhov individualizinggliomaradiotherapyplanningbyoptimizationofadataandphysicsinformeddiscreteloss
AT sergeylitvinov individualizinggliomaradiotherapyplanningbyoptimizationofadataandphysicsinformeddiscreteloss
AT petroskoumoutsakos individualizinggliomaradiotherapyplanningbyoptimizationofadataandphysicsinformeddiscreteloss
AT tamazamiranashvili individualizinggliomaradiotherapyplanningbyoptimizationofadataandphysicsinformeddiscreteloss
AT rayziruizhang individualizinggliomaradiotherapyplanningbyoptimizationofadataandphysicsinformeddiscreteloss
AT johnslowengrub individualizinggliomaradiotherapyplanningbyoptimizationofadataandphysicsinformeddiscreteloss
AT igoryakushev individualizinggliomaradiotherapyplanningbyoptimizationofadataandphysicsinformeddiscreteloss
AT benediktwiestler individualizinggliomaradiotherapyplanningbyoptimizationofadataandphysicsinformeddiscreteloss
AT bjoernmenze individualizinggliomaradiotherapyplanningbyoptimizationofadataandphysicsinformeddiscreteloss