Saved in:
Bibliographic Details
Main Authors: Petersen, Richard, Kahl, Fredrik, Alvén, Jennifer
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.08313
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910148367220736
author Petersen, Richard
Kahl, Fredrik
Alvén, Jennifer
author_facet Petersen, Richard
Kahl, Fredrik
Alvén, Jennifer
contents Dense annotations, such as segmentation masks, are expensive and time-consuming to obtain, especially for 3D medical images where expert voxel-wise labeling is required. Weakly supervised approaches aim to address this limitation, but often rely on attribution-based methods that struggle to accurately capture small structures such as lung nodules. In this paper, we propose a weakly-supervised segmentation method for lung nodules by combining pretrained state-of-the-art rectified flow and predictor models in a plug-and-play manner. Our approach uses training-free guidance of a 3D rectified flow model, requiring only fine-tuning of the predictor using image-level labels and no retraining of the generative model. The proposed method produces improved-quality segmentations for two separate predictors, consistently detecting lung nodules of varying size and shapes. Experiments on LUNA16 demonstrate improvements over baseline methods, highlighting the potential of generative foundation models as tools for weakly supervised 3D medical image segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2604_08313
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Weakly-Supervised Lung Nodule Segmentation via Training-Free Guidance of 3D Rectified Flow
Petersen, Richard
Kahl, Fredrik
Alvén, Jennifer
Computer Vision and Pattern Recognition
Dense annotations, such as segmentation masks, are expensive and time-consuming to obtain, especially for 3D medical images where expert voxel-wise labeling is required. Weakly supervised approaches aim to address this limitation, but often rely on attribution-based methods that struggle to accurately capture small structures such as lung nodules. In this paper, we propose a weakly-supervised segmentation method for lung nodules by combining pretrained state-of-the-art rectified flow and predictor models in a plug-and-play manner. Our approach uses training-free guidance of a 3D rectified flow model, requiring only fine-tuning of the predictor using image-level labels and no retraining of the generative model. The proposed method produces improved-quality segmentations for two separate predictors, consistently detecting lung nodules of varying size and shapes. Experiments on LUNA16 demonstrate improvements over baseline methods, highlighting the potential of generative foundation models as tools for weakly supervised 3D medical image segmentation.
title Weakly-Supervised Lung Nodule Segmentation via Training-Free Guidance of 3D Rectified Flow
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.08313