Enlarged ventricles are a marker of several brain diseases; however, they are also associated with normal aging. Better understanding of the distribution of ventricular sizes in a large population would be of great clinical value to robustly define imaging markers that distinguish health and disease. The AGES-Reykjavik study includes magnetic resonance imaging scans of 4811 individuals from an elderly Icelandic population. Automated brain segmentation algorithms are necessary to analyze such a large data set but state-of-the-art algorithms often require long processing times or depend on large manually annotated data sets when based on deep learning approaches. In an effort to increase robustness, decrease processing time, and avoid tedious manual delineations, we selected 60 subjects with a large range of ventricle sizes and generated training labels using an automated whole brain segmentation algorithm designed for brains with ventriculomegaly. Lesion labels were added to the training labels, which were subsequently used to train a patch-based three-dimensional U-net Convolutional Neural Network for very fast and robust labeling of the remaining subjects. Comparisons with ground truth manual labels demonstrate that the proposed method yields robust segmentation and labeling of the four main sub-compartments of the ventricular system.
Lesions that appear hyperintense in both Fluid Attenuated Inversion Recovery (FLAIR) and T2-weighted magnetic resonance images (MRIs) of the human brain are common in the brains of the elderly population and may be caused by ischemia or demyelination. Lesions are biomarkers for various neurodegenerative diseases, making accurate quantification of them important for both disease diagnosis and progression. Automatic lesion detection using supervised learning requires manually annotated images, which can often be impractical to acquire. Unsupervised lesion detection, on the other hand, does not require any manual delineation; however, these methods can be challenging to construct due to the variability in lesion load, placement of lesions, and voxel intensities. Here we present a novel approach to address this problem using a convolutional autoencoder, which learns to segment brain lesions as well as the white matter, gray matter, and cerebrospinal fluid by reconstructing FLAIR images as conical combinations of softmax layer outputs generated from the corresponding T1, T2, and FLAIR images. Some of the advantages of this model are that it accurately learns to segment lesions regardless of lesion load, and it can be used to quickly and robustly segment new images that were not in the training set. Comparisons with state-of-the-art segmentation methods evaluated on ground truth manual labels indicate that the proposed method works well for generating accurate lesion segmentations without the need for manual annotations.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.