Learning from imperfect training data using a robust loss function: application to brain image segmentation
This addresses segmentation accuracy for medical imaging applications like EEG/MEG, but it appears incremental as it builds on existing deep learning approaches with a focus on robustness to label noise.
The authors tackled brain MRI segmentation using a deep learning framework that segments brain, skull, and extra-cranial tissue from T1-weighted MRI, and they developed a robust training method to handle noisy labels.
Segmentation is one of the most important tasks in MRI medical image analysis and is often the first and the most critical step in many clinical applications. In brain MRI analysis, head segmentation is commonly used for measuring and visualizing the brain's anatomical structures and is also a necessary step for other applications such as current-source reconstruction in electroencephalography and magnetoencephalography (EEG/MEG). Here we propose a deep learning framework that can segment brain, skull, and extra-cranial tissue using only T1-weighted MRI as input. In addition, we describe a robust method for training the model in the presence of noisy labels.