Self-supervised Registration and Segmentation of the Ossicles with A Single Ground Truth Label

TL;DR

This paper introduces a self-supervised 3D-UNet approach for ossicle segmentation in medical images, reducing reliance on manual labels and improving boundary accuracy for image-guided surgeries.

Contribution

A novel self-supervised 3D-UNet method for ossicle segmentation that outperforms traditional techniques without requiring extensive manual labels.

Findings

Improved Dice coefficient by 8.51%.

More accurate boundary segmentation of ossicles.

Outperforms traditional segmentation methods.

Abstract

AI-assisted surgeries have drawn the attention of the medical image research community due to their real-world impact on improving surgery success rates. For image-guided surgeries, such as Cochlear Implants (CIs), accurate object segmentation can provide useful information for surgeons before an operation. Recently published image segmentation methods that leverage machine learning usually rely on a large number of manually predefined ground truth labels. However, it is a laborious and time-consuming task to prepare the dataset. This paper presents a novel technique using a self-supervised 3D-UNet that produces a dense deformation field between an atlas and a target image that can be used for atlas-based segmentation of the ossicles. Our results show that our method outperforms traditional image segmentation methods and generates a more accurate boundary around the ossicles based on Dice similarity coefficient and point-to-point error comparison. The mean Dice coefficient is improved by 8.51% with our proposed method.