Weakly-Supervised Lung Nodule Segmentation via Training-Free Guidance of 3D Rectified Flow
This work addresses the challenge of reducing annotation costs for 3D medical image segmentation, particularly for small structures like lung nodules, though it appears incremental by combining existing models in a plug-and-play manner.
The paper tackles the problem of expensive dense annotations for 3D medical images by proposing a weakly-supervised segmentation method for lung nodules, achieving improved-quality segmentations and consistent detection across varying sizes and shapes, as demonstrated on the LUNA16 dataset.
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.