Weakly Supervised Volumetric Segmentation via Self-taught Shape Denoising Model

04/27/2021
by   Qian He, et al.
5

Weakly supervised segmentation is an important problem in medical image analysis due to the high cost of pixelwise annotation. Prior methods, while often focusing on weak labels of 2D images, exploit few structural cues of volumetric medical images. To address this, we propose a novel weakly-supervised segmentation strategy capable of better capturing 3D shape prior in both model prediction and learning. Our main idea is to extract a self-taught shape representation by leveraging weak labels, and then integrate this representation into segmentation prediction for shape refinement. To this end, we design a deep network consisting of a segmentation module and a shape denoising module, which are trained by an iterative learning strategy. Moreover, we introduce a weak annotation scheme with a hybrid label design for volumetric images, which improves model learning without increasing the overall annotation cost. The empirical experiments show that our approach outperforms existing SOTA strategies on three organ segmentation benchmarks with distinctive shape properties. Notably, we can achieve strong performance with even 10% labeled slices, which is significantly superior to other methods.

READ FULL TEXT

page 4

page 18

research
05/13/2022

Scribble2D5: Weakly-Supervised Volumetric Image Segmentation via Scribble Annotations

Recently, weakly-supervised image segmentation using weak annotations li...
research
11/17/2018

Weakly Supervised Semantic Image Segmentation with Self-correcting Networks

Building a large image dataset with high-quality object masks for semant...
research
01/25/2018

Self-Learning to Detect and Segment Cysts in Lung CT Images without Manual Annotation

Image segmentation is a fundamental problem in medical image analysis. I...
research
06/14/2022

Weakly-Supervised Crack Detection

Pixel-level crack segmentation is widely studied due to its high impact ...
research
11/17/2020

HiResCAM: Explainable Multi-Organ Multi-Abnormality Prediction in 3D Medical Images

Understanding model predictions is critical in healthcare, to facilitate...
research
07/10/2023

Weakly-supervised positional contrastive learning: application to cirrhosis classification

Large medical imaging datasets can be cheaply and quickly annotated with...
research
06/07/2019

Decompose-and-Integrate Learning for Multi-class Segmentation in Medical Images

Segmentation maps of medical images annotated by medical experts contain...

Please sign up or login with your details

Forgot password? Click here to reset