Unsupervised cross domain learning with applications to 7 layer segmentation of OCTs

TL;DR

This paper presents an unsupervised cross-domain learning method for OCT 7-layer segmentation, enabling effective application in medical imaging where labeled data is scarce or unavailable in target domains.

Contribution

The proposed approach allows deep learning models to adapt across domains without labeled target data, addressing a key challenge in medical image segmentation.

Findings

Effective segmentation in unseen domains

Reduces need for labeled target data

Applicable to various medical imaging tasks

Abstract

Unsupervised cross domain adaptation for OCT 7 layer segmentation and other medical applications where labeled training data is only available in a source domain and unavailable in the target domain. Our proposed method helps generalize of deep learning to many areas in the medical field where labeled training data are expensive and time consuming to acquire or where target domains are too novel to have had labelling.