Fully Automatic Data Labeling for Ultrasound Screen Detection

TL;DR

This paper introduces an automatic method to generate labeled ultrasound images from photographs, enabling rapid development of screen detection models without human annotation or DICOM data dependency.

Contribution

It presents a fully automated pipeline for extracting and rectifying ultrasound images from monitor photographs, bypassing the DICOM bottleneck for faster algorithm testing.

Findings

Achieved 0.79 balanced accuracy in classifying cardiac views from rectified images.

Eliminated the need for manual annotation and DICOM data in ultrasound image analysis.

Demonstrated the pipeline's effectiveness in a proof-of-concept study.

Abstract

Ultrasound (US) machines display images on a built-in monitor, but routine transfer to hospital systems relies on DICOM. We propose a fully automatic method to generate labeled data that can be used to train a screen detector model, and a pipeline to use that model to extract and rectify the US image from a photograph of the monitor, without any need for human annotation. This removes the DICOM bottleneck and enables rapid testing and prototyping of new algorithms. In a proof-of-concept study, the rectified images retained enough visual fidelity to classify cardiac views with a balanced accuracy of 0.79 with respect to the native DICOMs., the rectified images retained enough visual fidelity to classify cardiac views with a balanced accuracy of 0.79 with respect to the native DICOMs.