Expected exponential loss for gaze-based video and volume ground truth annotation

TL;DR

This paper introduces a novel semi-supervised framework using eye gaze data and an Expected Exponential loss function to efficiently generate pixel-wise annotations for medical imaging, reducing annotation costs and improving segmentation performance.

Contribution

The paper proposes a new framework that leverages eye gaze data and a novel loss function to improve annotation efficiency and segmentation accuracy in medical imaging.

Findings

Outperforms existing annotation strategies across various medical imaging tasks

Effectively integrates with crowd-sourcing methods

Reduces annotation effort while maintaining high segmentation quality

Abstract

Many recent machine learning approaches used in medical imaging are highly reliant on large amounts of image and ground truth data. In the context of object segmentation, pixel-wise annotations are extremely expensive to collect, especially in video and 3D volumes. To reduce this annotation burden, we propose a novel framework to allow annotators to simply observe the object to segment and record where they have looked at with a \$200 eye gaze tracker. Our method then estimates pixel-wise probabilities for the presence of the object throughout the sequence from which we train a classifier in semi-supervised setting using a novel Expected Exponential loss function. We show that our framework provides superior performances on a wide range of medical image settings compared to existing strategies and that our method can be combined with current crowd-sourcing paradigms as well.