Label Propagation via Random Walk for Training Robust Thalamus Nuclei Parcellation Model from Noisy Annotations

2023/03/30 by Feng, Anqi, Xue, Yuan, Wang, Yuli +7 · 2 citations
#FOS: Biological sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Quantitative Methods (q-bio.QM) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2303.17706

Abstract

Data-driven thalamic nuclei parcellation depends on high-quality manual annotations. However, the small size and low contrast changes among thalamic nuclei, yield annotations that are often incomplete, noisy, or ambiguously labelled. To train a robust thalamic nuclei parcellation model with noisy annotations, we propose a label propagation algorithm based on random walker to refine the annotations before model training. A two-step model was trained to generate first the whole thalamus and then the nuclei masks. We conducted experiments on a mild traumatic brain injury~(mTBI) dataset with noisy thalamic nuclei annotations. Our model outperforms current state-of-the-art thalamic nuclei parcellations by a clear margin. We believe our method can also facilitate the training of other parcellation models with noisy labels.

Cited by

• CATNUS: Coordinate-Aware Thalamic Nuclei Segmentation Using T1-Weighted MRI
• Segmenting Thalamic Nuclei: T1 Maps Provide a Reliable and Efficient Solution

Related

• RATNUS: Rapid, Automatic Thalamic Nuclei Segmentation using Multimodal MRI inputs
• Segmenting thalamic nuclei from manifold projections of multi-contrast MRI
• STRUDEL: Self-Training with Uncertainty Dependent Label Refinement\n across Domains
• Denoising Diffusion Probabilistic Models for Image Inpainting of Cell Distributions in the Human Brain
• SingleStrip: learning skull-stripping from a single labeled example