Pseudo-Label-Assisted Self-Organizing Maps for Brain Tissue Segmentation in Magnetic Resonance Imaging.
Jonas Grande-BarretoPilar Gomez-GilPublished in: Journal of digital imaging (2022)
Brain tissue segmentation in magnetic resonance imaging volumes is an important image processing step for analyzing the human brain. This paper presents a novel approach named Pseudo-Label Assisted Self-Organizing Map (PLA-SOM) that enhances the result produced by a base segmentation method. Using the output of a base method, PLA-SOM calculates pseudo-labels in order to keep inter-class separation and intra-class compactness in the training phase. For the mapping phase, PLA-SOM uses a novel fuzzy function that combines feature space learned by the SOM's prototypes, topological ordering from the map, and spatial information from a brain atlas. We assessed PLA-SOM performance on synthetic and real MRIs of the brain, obtained from the BrainWeb and the Internet Brain Image Repository datasets. The experimental results showed evidence of segmentation improvement achieved by the proposed method over six different base methods. The best segmentation improvements reported by PLA-SOM on synthetic brain scans are 11%, 6%, and 4% for the tissue classes cerebrospinal fluid, gray matter, and white matter, respectively. On real brain scans, PLA-SOM achieved segmentation enhancements of 15%, 5%, and 12% for cerebrospinal fluid, gray matter, and white matter, respectively.
Keyphrases
- white matter
- deep learning
- resting state
- magnetic resonance imaging
- convolutional neural network
- multiple sclerosis
- functional connectivity
- cerebrospinal fluid
- computed tomography
- magnetic resonance
- machine learning
- contrast enhanced
- health information
- mass spectrometry
- high density
- brain injury
- subarachnoid hemorrhage
- blood brain barrier
- diffusion weighted imaging
- social media
- neural network
- liquid chromatography
- dual energy