Adaptive Pseudo Label Selection for Individual Unlabeled Data by Positive and Unlabeled Learning

TL;DR

This paper introduces a novel pseudo-labeling approach for medical image segmentation that leverages Positive and Unlabeled Learning to effectively select pseudo-labels for individual images, improving segmentation accuracy.

Contribution

It presents a new pseudo-labeling method using PU learning tailored for individual medical images, enhancing pseudo-label selection for segmentation tasks.

Findings

Effective pseudo-label selection demonstrated on medical images

PU learning simplifies foreground-background discrimination

Improved segmentation accuracy shown in experiments

Abstract

This paper proposes a novel pseudo-labeling method for medical image segmentation that can perform learning on ``individual images'' to select effective pseudo-labels. We introduce Positive and Unlabeled Learning (PU learning), which uses only positive and unlabeled data for binary classification problems, to obtain the appropriate metric for discriminating foreground and background regions on each unlabeled image. Our PU learning makes us easy to select pseudo-labels for various background regions. The experimental results show the effectiveness of our method.