Exploring semantic consistency in unpaired image translation to generate data for surgical applications.

ABSTRACT:

Purpose

In surgical computer vision applications, data privacy and expert annotation challenges impede the acquisition of labeled training data. Unpaired image-to-image translation techniques have been explored to automatically generate annotated datasets by translating synthetic images into a realistic domain. The preservation of structure and semantic consistency, i.e., per-class distribution during translation, poses a significant challenge, particularly in cases of semantic distributional mismatch.

Method

This study empirically investigates various translation methods for generating data in surgical applications, explicitly focusing on semantic consistency. Through our analysis, we introduce a novel and simple combination of effective approaches, which we call ConStructS

SUBMITTER: Venkatesh DK 

PROVIDER: S-EPMC11599420 | biostudies-literature | 2024 Jun

REPOSITORIES: biostudies-literature