Learning to Segment Medical Images with Scribble-Supervision Alone

Abstract

Semantic segmentation of medical images is a crucial step for the quantification of healthy anatomy and diseases alike. The majority of the current state-of-the-art segmentation algorithms are based on deep neural networks and rely on large datasets with full pixel-wise annotations. Producing such annotations can often only be done by medical professionals and requires large amounts of valuable time. Training a medical image segmentation network with weak annotations remains a relatively unexplored topic. In this work we investigate training strategies to learn the parameters of a pixel-wise segmentation network from scribble annotations alone. We evaluate the techniques on public cardiac (ACDC) and prostate (NCI-ISBI) segmentation datasets. We find that the networks trained on scribbles suffer from a remarkably small degradation in Dice of only 2.9% (cardiac) and 4.5% (prostate) with respect to a network trained on full annotations.

arXiv commentAccepted for presentation at DLMIA 2018

References in corpus (1)

• BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

Cited by in corpus (4)

• Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
• A Survey on Deep Learning of Small Sample in Biomedical Image Analysis
• Recent Advances in Fibrosis and Scar Segmentation from Cardiac MRI: A State-of-the-Art Review and Future Perspectives
• Sparse Annotations with Random Walks for U-Net Segmentation of Biodegradable Bone Implants in Synchrotron Microtomograms