Weakly supervised segmentation with point annotations for histopathology images via contrast-based variational model
This work addresses the annotation workload for histopathology images, which is an incremental improvement in domain-specific medical imaging.
The paper tackles the problem of expensive annotation for histopathology image segmentation by proposing a weakly supervised method using point annotations, which generates regionally consistent and smoother boundaries, as demonstrated on two histology datasets.
Image segmentation is a fundamental task in the field of imaging and vision. Supervised deep learning for segmentation has achieved unparalleled success when sufficient training data with annotated labels are available. However, annotation is known to be expensive to obtain, especially for histopathology images where the target regions are usually with high morphology variations and irregular shapes. Thus, weakly supervised learning with sparse annotations of points is promising to reduce the annotation workload. In this work, we propose a contrast-based variational model to generate segmentation results, which serve as reliable complementary supervision to train a deep segmentation model for histopathology images. The proposed method considers the common characteristics of target regions in histopathology images and can be trained in an end-to-end manner. It can generate more regionally consistent and smoother boundary segmentation, and is more robust to unlabeled `novel' regions. Experiments on two different histology datasets demonstrate its effectiveness and efficiency in comparison to previous models.