Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

ShapePU: A New PU Learning Framework Regularized by Global Consistency for Scribble Supervised Cardiac Segmentation

About

Cardiac segmentation is an essential step for the diagnosis of cardiovascular diseases. However, pixel-wise dense labeling is both costly and time-consuming. Scribble, as a form of sparse annotation, is more accessible than full annotations. However, it's particularly challenging to train a segmentation network with weak supervision from scribbles. To tackle this problem, we propose a new scribble-guided method for cardiac segmentation, based on the Positive-Unlabeled (PU) learning framework and global consistency regularization, and termed as ShapePU. To leverage unlabeled pixels via PU learning, we first present an Expectation-Maximization (EM) algorithm to estimate the proportion of each class in the unlabeled pixels. Given the estimated ratios, we then introduce the marginal probability maximization to identify the classes of unlabeled pixels. To exploit shape knowledge, we apply cutout operations to training images, and penalize the inconsistent segmentation results. Evaluated on two open datasets, i.e, ACDC and MSCMRseg, our scribble-supervised ShapePU surpassed the fully supervised approach respectively by 1.4% and 9.8% in average Dice, and outperformed the state-of-the-art weakly supervised and PU learning methods by large margins. Our code is available at https://github.com/BWGZK/ShapePU.

Ke Zhang, Xiahai Zhuang• 2022

Related benchmarks

TaskDatasetResultRank
Medical Image SegmentationBTCV (test)--
28
Cardiac SegmentationACDC
Dice (LV)88.5
22
Irregular structure segmentationDecathlon BrainTumor
Dice (Tumor)75
13
Regular cardiac structure segmentationMSCMRseg LGE CMR
Dice (LV)88
13
Irregular segmentation of myocardial pathologiesMyoPS (test)
Dice (Scar)55.8
11
3D Medical Image SegmentationDecathlon Prostate (test)
Dice (Central gland)79.2
9
Medical Image SegmentationMSCMRseg 5-scribble supervised (test)
Dice (LV)75.8
9
Showing 7 of 7 rows

Other info

Follow for update