A Positive/Unlabeled Approach for the Segmentation of Medical Sequences using Point-Wise Supervision

TL;DR

This paper introduces a novel positive/unlabeled learning method for efficient medical image segmentation using sparse point annotations, combined with a Bayesian prior estimation and spatio-temporal regularization, outperforming existing techniques.

Contribution

It presents a new self-supervised approach that estimates class priors and improves segmentation quality with minimal annotation effort.

Findings

High segmentation accuracy across various modalities

Effective prior estimation without known class proportions

Outperforms state-of-the-art methods in experiments

Abstract

The ability to quickly annotate medical imaging data plays a critical role in training deep learning frameworks for segmentation. Doing so for image volumes or video sequences is even more pressing as annotating these is particularly burdensome. To alleviate this problem, this work proposes a new method to efficiently segment medical imaging volumes or videos using point-wise annotations only. This allows annotations to be collected extremely quickly and remains applicable to numerous segmentation tasks. Our approach trains a deep learning model using an appropriate Positive/Unlabeled objective function using sparse point-wise annotations. While most methods of this kind assume that the proportion of positive samples in the data is known a-priori, we introduce a novel self-supervised method to estimate this prior efficiently by combining a Bayesian estimation framework and new stopping criteria. Our method iteratively estimates appropriate class priors and yields high segmentation quality for a variety of object types and imaging modalities. In addition, by leveraging a spatio-temporal tracking framework, we regularize our predictions by leveraging the complete data volume. We show experimentally that our approach outperforms state-of-the-art methods tailored to the same problem.