Supervised Segmentation with Domain Adaptation for Small Sampled Orbital CT Images

TL;DR

This paper proposes a domain adaptation method to improve supervised segmentation of orbital CT images with small samples, leveraging transfer learning from larger datasets to enhance performance on rare disease imaging tasks.

Contribution

It introduces a novel domain adaptation approach that enhances attention U-Net segmentation performance on small orbital CT datasets, addressing data scarcity in medical imaging.

Findings

Improved segmentation accuracy on orbital CT datasets.

Effective transfer learning from cross-domain datasets.

Code and dataset publicly available for reproducibility.

Abstract

Deep neural networks (DNNs) have been widely used for medical image analysis. However, the lack of access a to large-scale annotated dataset poses a great challenge, especially in the case of rare diseases, or new domains for the research society. Transfer of pre-trained features, from the relatively large dataset is a considerable solution. In this paper, we have explored supervised segmentation using domain adaptation for optic nerve and orbital tumor, when only small sampled CT images are given. Even the lung image database consortium image collection (LIDC-IDRI) is a cross-domain to orbital CT, but the proposed domain adaptation method improved the performance of attention U-Net for the segmentation in public optic nerve dataset and our clinical orbital tumor dataset. The code and dataset are available at https://github.com/cmcbigdata.