Saved in:
Bibliographic Details
Main Authors: Huang, Ruirui, Li, Jiacheng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.00350
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914174654742528
author Huang, Ruirui
Li, Jiacheng
author_facet Huang, Ruirui
Li, Jiacheng
contents We introduce MedCondDiff, a diffusion-based framework for multi-organ medical image segmentation that is efficient and anatomically grounded. The model conditions the denoising process on semantic priors extracted by a Pyramid Vision Transformer (PVT) backbone, yielding a semantically guided and lightweight diffusion architecture. This design improves robustness while reducing both inference time and VRAM usage compared to conventional diffusion models. Experiments on multi-organ, multi-modality datasets demonstrate that MedCondDiff delivers competitive performance across anatomical regions and imaging modalities, underscoring the potential of semantically guided diffusion models as an effective class of architectures for medical imaging tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00350
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MedCondDiff: Lightweight, Robust, Semantically Guided Diffusion for Medical Image Segmentation
Huang, Ruirui
Li, Jiacheng
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
We introduce MedCondDiff, a diffusion-based framework for multi-organ medical image segmentation that is efficient and anatomically grounded. The model conditions the denoising process on semantic priors extracted by a Pyramid Vision Transformer (PVT) backbone, yielding a semantically guided and lightweight diffusion architecture. This design improves robustness while reducing both inference time and VRAM usage compared to conventional diffusion models. Experiments on multi-organ, multi-modality datasets demonstrate that MedCondDiff delivers competitive performance across anatomical regions and imaging modalities, underscoring the potential of semantically guided diffusion models as an effective class of architectures for medical imaging tasks.
title MedCondDiff: Lightweight, Robust, Semantically Guided Diffusion for Medical Image Segmentation
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2512.00350