LAUSR.org creates dashboard-style pages of related content for over 1.5 million academic articles. Sign Up to like articles & get recommendations!

Robust machine learning segmentation for large-scale analysis of heterogeneous clinical brain MRI datasets

Photo from wikipedia

Significance SynthSeg+ is an image segmentation tool for automated analysis of highly heterogeneous brain MRI clinical scans. Our method relies on a new strategy to train deep neural networks, such… Click to show full abstract

Significance SynthSeg+ is an image segmentation tool for automated analysis of highly heterogeneous brain MRI clinical scans. Our method relies on a new strategy to train deep neural networks, such that it can robustly analyze scans of any contrast and resolution without retraining, which was previously impossible. Moreover, SynthSeg+ enables scalable quality control of the produced results by automatic detection of faulty segmentations. Our tool is publicly available with FreeSurfer and can be used “out-of-the-box”, which facilitates its use and enhances reproducibility. By unlocking the analysis of heterogeneous clinical data, SynthSeg+ has the potential to transform neuroimaging studies, given the considerable abundance of clinical scans compared to the size of datasets used in research.

Keywords: brain mri; segmentation; analysis; heterogeneous clinical; analysis heterogeneous

Journal Title: Proceedings of the National Academy of Sciences of the United States of America
Year Published: 2022

Link to full text (if available)


Share on Social Media:                               Sign Up to like & get
recommendations!

Related content

More Information              News              Social Media              Video              Recommended



                Click one of the above tabs to view related content.