Gray Matter Segmentation in Ultra High Resolution 7 Tesla ex vivo T2w MRI of Human Brain Hemispheres
This work addresses the problem of limited automated segmentation methods for ex vivo MRI, which is crucial for neuroanatomy research, though it is incremental as it benchmarks existing architectures rather than introducing a new method.
The authors tackled automated cortical segmentation in ex vivo MRI by benchmarking nine neural network architectures on a high-resolution 7 Tesla dataset of 32 human brain specimens, achieving excellent generalization across whole hemispheres and unseen images with different acquisition parameters.
Ex vivo MRI of the brain provides remarkable advantages over in vivo MRI for visualizing and characterizing detailed neuroanatomy. However, automated cortical segmentation methods in ex vivo MRI are not well developed, primarily due to limited availability of labeled datasets, and heterogeneity in scanner hardware and acquisition protocols. In this work, we present a high resolution 7 Tesla dataset of 32 ex vivo human brain specimens. We benchmark the cortical mantle segmentation performance of nine neural network architectures, trained and evaluated using manually-segmented 3D patches sampled from specific cortical regions, and show excellent generalizing capabilities across whole brain hemispheres in different specimens, and also on unseen images acquired at different magnetic field strength and imaging sequences. Finally, we provide cortical thickness measurements across key regions in 3D ex vivo human brain images. Our code and processed datasets are publicly available at https://github.com/Pulkit-Khandelwal/picsl-ex-vivo-segmentation.