Enhanced diffusion model with 3D structural and segmentation priors for lung cancer radiotherapy dose prediction

Objective. Diffusion models show strong potential for high-fidelity radiotherapy dose prediction, but their performance depends heavily on the conditioning mechanism. This study introduces a novel conditioning strategy that improves volumetric consistency in slice-wise dose generation while reducing reliance on manually annotated organ-at-risk (OAR) masks. Approach. We propose a diffusion-based dose prediction framework conditioned on features from the full 3D computed tomography (CT) volume and a pre-trained medical image segmentation model. A 3D feature extractor encodes global anatomical information from the entire CT volume to preserve spatial coherence across 2D dose predictions. Rather than relying on manual OAR masks, the model uses anatomical representations from the pre-trained segmentation network, integrated via cross-attention to enable anatomy-aware dose prediction. Main results. The framework, Diff-Seg3D, was evaluated on three lung cancer radiotherapy datasets representing Volumetric Modulated Arc Therapy (VMAT), Fixed Gantry Intensity-Modulated Radiation Therapy (FGIMRT), and 3D Conformal Radiation Therapy (3DCRT) planning techniques. It achieved the numerically lowest mean absolute error (MAE) on all three datasets, with values of 3.16, 4.38, and 4.02 Gy, respectively, and the best dose-volume histogram (DVH) scores (2.64 and 3.82) on VMAT and FGIMRT, while remaining competitive on 3DCRT. Pre-trained 3D anatomical and segmentation encoders improved the baseline diffusion model, with segmentation features improving performance without requiring explicit OAR contours at inference. Significance. This conditioning strategy improves volumetric consistency and anatomical awareness in diffusion-based dose prediction. The framework can serve as a tool for generating treatment-specific, anatomy-conditioned dose priors to guide radiotherapy planning.

Authors

Institutions

Publication Details

Journal
Physics in Medicine and Biology
Published
2026-11-19
DOI
https://doi.org/10.1088/1361-6560/aec499
Primary Topic
Advanced Radiotherapy Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Enhanced diffusion model with 3D structural and segmentation priors for lung cancer radiotherapy dose prediction

Milos Manic, Swagat Das, Victor Cobilean, Elisabeth Weiss et al.
Physics in Medicine and Biology
Advanced Radiotherapy Techniques
article

Enhanced diffusion model with 3D structural and segmentation priors for lung cancer radiotherapy dose prediction

Milos Manic, Swagat Das, Victor Cobilean, Elisabeth Weiss, Devin Drake, Lulin Yuan, Harindra Mavikumbure, Ibtisam Almajnooni
article en

Abstract

Objective. Diffusion models show strong potential for high-fidelity radiotherapy dose prediction, but their performance depends heavily on the conditioning mechanism. This study introduces a novel conditioning strategy that improves volumetric consistency in slice-wise dose generation while reducing reliance on manually annotated organ-at-risk (OAR) masks. Approach. We propose a diffusion-based dose prediction framework conditioned on features from the full 3D computed tomography (CT) volume and a pre-trained medical image segmentation model. A 3D feature extractor encodes global anatomical information from the entire CT volume to preserve spatial coherence across 2D dose predictions. Rather than relying on manual OAR masks, the model uses anatomical representations from the pre-trained segmentation network, integrated via cross-attention to enable anatomy-aware dose prediction. Main results. The framework, Diff-Seg3D, was evaluated on three lung cancer radiotherapy datasets representing Volumetric Modulated Arc Therapy (VMAT), Fixed Gantry Intensity-Modulated Radiation Therapy (FGIMRT), and 3D Conformal Radiation Therapy (3DCRT) planning techniques. It achieved the numerically lowest mean absolute error (MAE) on all three datasets, with values of 3.16, 4.38, and 4.02 Gy, respectively, and the best dose-volume histogram (DVH) scores (2.64 and 3.82) on VMAT and FGIMRT, while remaining competitive on 3DCRT. Pre-trained 3D anatomical and segmentation encoders improved the baseline diffusion model, with segmentation features improving performance without requiring explicit OAR contours at inference. Significance. This conditioning strategy improves volumetric consistency and anatomical awareness in diffusion-based dose prediction. The framework can serve as a tool for generating treatment-specific, anatomy-conditioned dose priors to guide radiotherapy planning.

Physics in Medicine and Biology
Virginia Commonwealth University (US)
Advanced Radiotherapy Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon