Weakly supervised segmentation from extreme points

TL;DR

This paper introduces a weakly supervised segmentation method using minimal user input of extreme points in 3D medical images, significantly reducing annotation effort while enabling effective training of segmentation models.

Contribution

It presents a novel approach combining extreme point annotations with a random walker algorithm and CNN training, improving medical image segmentation efficiency.

Findings

Effective segmentation with minimal user input

Iterative refinement improves accuracy

Potential to accelerate dataset creation for medical imaging

Abstract

Annotation of medical images has been a major bottleneck for the development of accurate and robust machine learning models. Annotation is costly and time-consuming and typically requires expert knowledge, especially in the medical domain. Here, we propose to use minimal user interaction in the form of extreme point clicks in order to train a segmentation model that can, in turn, be used to speed up the annotation of medical images. We use extreme points in each dimension of a 3D medical image to constrain an initial segmentation based on the random walker algorithm. This segmentation is then used as a weak supervisory signal to train a fully convolutional network that can segment the organ of interest based on the provided user clicks. We show that the network's predictions can be refined through several iterations of training and prediction using the same weakly annotated data. Ultimately, our method has the potential to speed up the generation process of new training datasets for the development of new machine learning and deep learning-based models for, but not exclusively, medical image analysis.