Automatic Tongue Delineation from MRI Images with a Convolutional Neural Network Approach

TL;DR

This paper introduces a U-Net based convolutional neural network for automatic tongue contour extraction from real-time MRI images, achieving high accuracy and outperforming previous methods.

Contribution

The study presents a novel application of U-Net CNN for tongue delineation in MRI images with validated intra- and inter-subject results.

Findings

High accuracy in tongue contour detection

Outperforms previous automatic segmentation methods

Effective post-processing for precise contours

Abstract

Tongue contour extraction from real-time magnetic resonance images is a nontrivial task due to the presence of artifacts manifesting in form of blurring or ghostly contours. In this work, we present results of automatic tongue delineation achieved by means of U-Net auto-encoder convolutional neural network. We present both intra- and inter-subject validation. We used real-time magnetic resonance images and manually annotated 1-pixel wide contours as inputs. Predicted probability maps were post-processed in order to obtain 1-pixel wide tongue contours. The results are very good and slightly outperform published results on automatic tongue segmentation.