Weakly-Supervised Lung Nodule Segmentation via Training-Free Guidance of 3D Rectified Flow
2026-04-09 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the challenge of labeling lung nodules in 3D medical images, which is normally very time-consuming and requires expert work. They propose a new method that uses existing pretrained models to help segment lung nodules without needing detailed labels for every voxel. Their approach combines a 3D rectified flow model with a predictor that is fine-tuned using only image-level labels, avoiding the need to retrain the entire system. Tests on the LUNA16 dataset show their method improves segmentation quality compared to previous weakly supervised methods.
weakly supervised learning3D medical imaginglung nodule segmentationrectified flowpredictor modelimage-level labelsLUNA16 datasetgenerative modelssegmentation masksvoxel-wise labeling
Authors
Richard Petersen, Fredrik Kahl, Jennifer Alvén
Abstract
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.