Annotation by Clicks: A Point-Supervised Contrastive Variance Method for Medical Semantic Segmentation
Preprint
Abstract
Medical image segmentation methods typically rely on numerous dense annotated images for model training, which are notoriously expensive and time-consuming to collect. To alleviate this burden, weakly supervised techniques have been exploited to train segmentation models with less expensive annotations. In this paper, we propose a novel point-supervised contrastive variance method (PSCV) for medical image semantic segmentation, which only requires one pixel-point from each organ category to be annotated. The proposed method trains the base segmentation network by using a novel contrastive variance (CV) loss to exploit the unlabeled pixels and a partial cross-entropy loss on the labeled pixels. The CV loss function is designed to exploit the statistical spatial distribution properties of organs in medical images and their variance distribution map representations to enforce discriminative predictions over the unlabeled pixels. Experimental results on two standard medical image datasets demonstrate that the proposed method outperforms the state-of-the-art weakly supervised methods on point-supervised medical image semantic segmentation tasks.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Scribble-Supervised Medical Image Segmentation via Dual-Branch Network and Dynamically Mixed Pseudo Labels Supervision2022
- Inter Extreme Points Geodesics for End-to-End Weakly Supervised Image Segmentation2021
- Weakly Supervised Segmentation of COVID19 Infection with Scribble Annotation on CT ImagesPattern Recognition, 2021
- Embracing imperfect datasets: A review of deep learning solutions for medical image segmentationMedical Image Analysis, 2020
- Weakly Supervised Deep Nuclei Segmentation Using Partial Points Annotation in Histopathology ImagesIEEE Transactions on Medical Imaging, 2020
- Mumford–Shah Loss Functional for Image Segmentation With Deep LearningIEEE Transactions on Image Processing, 2019
- Learning Pixel-Level Semantic Affinity with Image-Level Supervision for Weakly Supervised Semantic Segmentation2018
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation2015
- A Multiphase Level Set Framework for Image Segmentation Using the Mumford and Shah ModelInternational Journal of Computer Vision, 2002
- Control of goal-directed and stimulus-driven attention in the brainNature Reviews Neuroscience, 2002