Automatic Tongue Delineation from MRI Images with a Convolutional Neural Network Approach
This work addresses a domain-specific problem in medical imaging for researchers or clinicians, but it is incremental as it builds on existing methods with minor improvements.
The paper tackled automatic tongue contour extraction from MRI images using a U-Net convolutional neural network, achieving results that slightly outperform published benchmarks for tongue segmentation.
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.