Combining Bayesian and Deep Learning Methods for the Delineation of the Fan in Ultrasound Images

TL;DR

This paper introduces a fast, parametric probabilistic method to delineate the ultrasound fan area in images, enabling efficient training of deep learning models for annotation removal, significantly reducing processing time.

Contribution

A novel parametric probabilistic approach for ultrasound fan detection that enables rapid training of deep learning segmentation models without additional data.

Findings

The method is 160 times faster than previous approaches.

Generated segmentation masks improve annotation removal.

First parametric approach for ultrasound fan detection using only image data.

Abstract

Ultrasound (US) images usually contain identifying information outside the ultrasound fan area and manual annotations placed by the sonographers during exams. For those images to be exploitable in a Deep Learning framework, one needs to first delineate the border of the fan which delimits the ultrasound fan area and then remove other annotations inside. We propose a parametric probabilistic approach for the first task. We make use of this method to generate a training data set with segmentation masks of the region of interest (ROI) and train a U-Net to perform the same task in a supervised way, thus considerably reducing computational time of the method, one hundred and sixty times faster. These images are then processed with existing inpainting methods to remove annotations present inside the fan area. To the best of our knowledge, this is the first parametric approach to quickly detect the fan in an ultrasound image without any other information than the image itself.