Conditional Iterative α-(de)Blending Model for CBCT-to-sCT Synthesis: Towards a Deterministic and Simple Process

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

Abstract

Cone-beam CT (CBCT) is widely used in adaptive radiotherapy (ART) but often suffers from image artifacts and poor soft tissue contrast, limiting its wider application in ART workflows including segmentation and dose calculation. In this work, we propose a conditional Iterative α-(de)Blending (cIADB) for CBCT image quality improvement. cIADB employs a deterministic blending-deblending mechanism that reduces sampling randomness, enabling more stable and efficient image generation compared to conventional conditional denoising diffusion probabilistic model (cDDPM), which relies on stochastic sampling. We comprehensively evaluate the proposed method on head-and-neck CBCTs across different training approaches and anatomical planes. Quantitative results demonstrate that cIADB achieves better performance compared to cDDPM in terms of PSNR, SSIM, and SSE, while qualitative assessments further confirm improved denoising effect and structural fidelity. Moreover, the lightweight inference process of cIADB facilitates its potential integration into ART workflows. Our study highlights the promise of deterministic IADB model as a robust solution for clinical CBCT enhancement.
Original languageEnglish
Title of host publicationSimulation and Synthesis in Medical Imaging
Subtitle of host publication10th International Workshop, SASHIMI 2025, Held in Conjunction with MICCAI 2025, Daejeon, South Korea, September 23, 2025, Proceedings
EditorsVirginia Fernandez, David Wiesner, Lianrui Zuo, Adrià Casamitjana, Samuel W. Remedios
Place of PublicationCham
PublisherSpringer Cham
Pages149–158
Number of pages10
ISBN (Electronic)9783032055736
ISBN (Print)9783032055729
DOIs
Publication statusPublished - 21 Sept 2025
EventInternational Workshop on Simulation and Synthesis in Medical Imaging - Daejeon, Korea, Democratic People's Republic of
Duration: 23 Sept 202523 Sept 2025

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume16085
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceInternational Workshop on Simulation and Synthesis in Medical Imaging
Country/TerritoryKorea, Democratic People's Republic of
CityDaejeon
Period23/09/2523/09/25

Fingerprint

Dive into the research topics of 'Conditional Iterative α-(de)Blending Model for CBCT-to-sCT Synthesis: Towards a Deterministic and Simple Process'. Together they form a unique fingerprint.

Cite this