Bayesian segmentation of brainstem structures in MRI

Abstract

In this paper we present a method to segment four brainstem structures (midbrain, pons, medulla oblongata and superior cerebellar peduncle) from 3D brain MRI scans. The segmentation method relies on a probabilistic atlas of the brainstem and its neighboring brain structures. To build the atlas, we combined a dataset of 39 scans with already existing manual delineations of the whole brainstem and a dataset of 10 scans in which the brainstem structures were manually labeled with a protocol that was specifically designed for this study. The resulting atlas can be used in a Bayesian framework to segment the brainstem structures in novel scans. Thanks to the generative nature of the scheme, the segmentation method is robust to changes in MRI contrast or acquisition hardware. Using cross validation, we show that the algorithm can segment the structures in previously unseen T1 and FLAIR scans with great accuracy (mean error under 1 mm) and robustness (no failures in 383 scans including 168 AD cases). We also indirectly evaluate the algorithm with a experiment in which we study the atrophy of the brainstem in aging. The results show that, when used simultaneously, the volumes of the midbrain, pons and medulla are significantly more predictive of age than the volume of the entire brainstem, estimated as their sum. The results also demonstrate that that the method can detect atrophy patterns in the brainstem structures that have been previously described in the literature. Finally, we demonstrate that the proposed algorithm is able to detect differential effects of AD on the brainstem structures. The method will be implemented as part of the popular neuroimaging package FreeSurfer.

Structural alterations of the brainstem in migraine

“…The FreeSurfer 6.0 version, which allows for automatic calculation of medulla, pons, midbrain and superior cerebellar peduncle volumes, is based on a probabilistic atlas and a Bayesian segmentation (Iglesias et al, 2015). In order to avoid data irregularities stemming from the use of multiple workstations, all subjects were post-processed on a single Macintosh computer (osX: 10.10.5, Model: MacPro 6.1, Processor: 3.7 Quad-Core Intel Xeon E5, and RAM: 16GB 1866 MHz DDR3 ECC) in accordance with the manual guidelines used by FreeSurfer.…”

“…Until recently, parcelletion of brainstem sub-structures could not be achieved using automated brain parcellation algorithms, leaving changes in the structural anatomy of individual brainstem structures in migraine relatively unexplored. The most recent structural pipeline of FreeSurfer 6.0 includes the capability to segment brainstem regions, and shows good performance relative to manual labeling techniques, which are time-consuming and operator-dependent (Iglesias et al, 2015). …”

Brainstem enlargement in preschool children with autism: Results from an intermethod agreement study of segmentation algorithms

“…The atlas consists in a data set of 49 manually labeled with a protocol that was specifically designed for the study and fully described in (Iglesias et al, 2015). This segmentation method relies on a probabilistic atlas of the brainstem and its neighboring brain structures.…”

Radiological biomarkers for diagnosis in PSP: Where are we and where do we need to be?

“…However, another multicenter study showed high sensitivity/specificity for the MRPI in differentiating PSP‐RS and PD and showed that an automated MRPI measurement that does not rely on rater reliability performs as well as a manual MRPI measurement . Automated methods for measuring midbrain volume are also now available and may improve standardization.…”