Generalizing MRI Subcortical Segmentation to Neurodegeneration
- 31 December 2020
- book chapter
- conference paper
- Published by Springer Science and Business Media LLC
- Vol. 12449, 139-147
- https://doi.org/10.1007/978-3-030-66843-3_14
Abstract
Many neurodegenerative diseases like Huntington’s disease (HD) affect the subcortical structures of the brain, especially the caudate and the putamen. Automated segmentation of subcortical structures from MRI scans is thus important in HD studies. LiviaNET [ 2 ] is the state-of-the-art deep learning approach for subcortical segmentation. As all learning-based models, this approach requires appropriate training data. While annotated healthy control images are relatively easy to obtain, generating such annotations for each new disease population can be prohibitively expensive. In this work, we explore LiviaNET variants using well-known strategies for improving performance, to make it more generalizable to patients with substantial neurodegeneration. Specifically, we explored Res-blocks in our convolutional neural network, and we also explored manipulating the input to the network as well as random elastic deformations for data augmentation. We tested our method on images from the PREDICT-HD dataset, which includes control and HD subjects. We trained on control subjects and tested on both controls and HD patients. Compared to the original LiviaNET, we improved the accuracy of most structures, both for controls and for HD patients. The caudate has the most pronounced improvement in HD subjects with the proposed modifications to LiviaNET, which is noteworthy since caudate is known to be severely atrophied in HD. This suggests our extensions may improve the generalization ability of LiviaNET to cohorts where significant neurodegeneration is present, without needing to be retrained.Keywords
This publication has 13 references indexed in Scilit:
- Multivariate prediction of motor diagnosis in Huntington's disease: 12 years of PREDICT‐HDMovement Disorders, 2015
- Preliminary analysis using multi-atlas labeling algorithms for tracing longitudinal changeFrontiers in Neuroscience, 2015
- Huntington diseaseNature Reviews Disease Primers, 2015
- Prediction of manifest Huntington's disease with clinical and imaging measures: a prospective observational studyThe Lancet Neurology, 2014
- Multi-atlas segmentation of subcortical brain structures via the AutoSeg software pipelineFrontiers in Neuroscience, 2014
- Tracking motor impairments in the progression of Huntington's diseaseMovement Disorders, 2013
- Robust multi-site MR data processing: iterative optimization of bias correction, tissue classification, and registrationFrontiers in Neuroscience, 2013
- Automated subcortical segmentation using FIRST: Test-retest reliability, interscanner reliability, and comparison to manual segmentationHuman Brain Mapping, 2012
- Indexing disease progression at study entry with individuals at‐risk for Huntington diseaseNeuropsychiatric Genetics, Part B of the American Journal of Medical Genetics (AJMG), 2011
- Fully automated analysis using BRAINS: AutoWorkupNeuroImage, 2011