Conference proceeding
Longitudinal subcortical segmentation with deep learning
MEDICAL IMAGING 2021: IMAGE PROCESSING, Vol.11596
2021
DOI: 10.1117/12.2582340
PMCID: PMC8643360
PMID: 34873358
Abstract
Longitudinal information is important for monitoring the progression of neurodegenerative diseases, such as Huntington's disease (HD). Specifically, longitudinal magnetic resonance imaging (MRI) studies may allow the discovery of subtle intra-subject changes over time that may otherwise go undetected because of inter-subject variability. For HD patients, the primary imaging-based marker of disease progression is the atrophy of subcortical structures, mainly the caudate and putamen. To better understand the course of subcortical atrophy in HD and its correlation with clinical outcome measures, highly accurate segmentation is important. In recent years, subcortical segmentation methods have moved towards deep learning, given the state-of-the-art accuracy and computational efficiency provided by these models. However, these methods are not designed for longitudinal analysis, but rather treat each time point as an independent sample, discarding the longitudinal structure of the data. In this paper, we propose a deep learning based subcortical segmentation method that takes into account this longitudinal information. Our method takes a longitudinal pair of 3D MRIs as input, and jointly computes the corresponding segmentations. We use bi-directional convolutional long short-term memory (C-LSTM) blocks in our model to leverage the longitudinal information between scans. We test our method on the PREDICT-HD dataset and use the Dice coefficient, average surface distance and 95-percent Hausdorff distance as our evaluation metrics. Compared to cross-sectional segmentation, we improve the overall accuracy of segmentation, and our method has more consistent performance across time points. Furthermore, our method identifies a stronger correlation between subcortical volume loss and decline in the total motor score, an important clinical outcome measure for HD.
Details
- Title: Subtitle
- Longitudinal subcortical segmentation with deep learning
- Creators
- Hao Li - Vanderbilt UniversityHuahong Zhang - Vanderbilt UniversityHans Johnson - University of IowaJeffrey D Long - University of IowaJane S Paulsen - University of Wisconsin–MadisonIpek Oguz - Vanderbilt University
- Contributors
- B A Landman (Editor)
- Resource Type
- Conference proceeding
- Publication Details
- MEDICAL IMAGING 2021: IMAGE PROCESSING, Vol.11596
- DOI
- 10.1117/12.2582340
- PMID
- 34873358
- PMCID
- PMC8643360
- Language
- English
- Date published
- 2021
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Psychiatry; Psychological and Brain Sciences; Biostatistics; The Iowa Institute for Biomedical Imaging; The Iowa Initiative for Artificial Intelligence; Iowa Informatics Initiative
- Record Identifier
- 9984231911802771
Metrics
65 Record Views