Self-supervised Registration and Segmentation of the Ossicles with A Single Ground Truth Label
This work addresses the labor-intensive data preparation for surgeons in image-guided cochlear implant surgeries, though it is incremental as it builds on existing atlas-based and self-supervised techniques.
The paper tackles the problem of reducing manual labeling effort for segmenting ossicles in cochlear implant surgery by introducing a self-supervised 3D-UNet that uses a single ground truth label to generate a dense deformation field for atlas-based segmentation, resulting in an 8.51% improvement in mean Dice coefficient compared to traditional methods.
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.