SEGMENTATION OF THE COMPLETE SUPERIOR CEREBELLAR PEDUNCLES USING A MULTI-OBJECT GEOMETRIC DEFORMABLE MODEL

Neuroradiological findings in GAA-FGF14 ataxia (SCA27B): more than cerebellar atrophy

Background

GAA-FGF14 ataxia (SCA27B) is a recently reported late-onset ataxia caused by a GAA repeat expansion in intron 1 of the FGF14 gene. Initial studies revealed cerebellar atrophy in 74-97% of patients. A more detailed brain imaging characterization of GAA-FGF14 ataxia is now needed to provide supportive diagnostic features and earlier disease recognition.

Methods

We performed a retrospective review of the brain MRIs of 35 patients (median age at MRI 63 years; range 28-88 years) from Quebec (n=27), Nancy (n=3), Perth (n=3) and Bengaluru (n=2) to assess the presence of atrophy in vermis, cerebellar hemispheres, brainstem, cerebral hemispheres, and corpus callosum, as well as white matter involvement. Following the identification of the superior cerebellar peduncles (SCPs) involvement, we verified its presence in 54 GAA-FGF14 ataxia patients from four independent cohorts (Tübingen n=29; Donostia n=12; Innsbruck n=7; Cantabria n=6). To assess lobular atrophy, we performed quantitative cerebellar segmentation in 5 affected subjects with available 3D T1-weighted images and matched controls.

Results

Cerebellar atrophy was documented in 33 subjects (94.3%). We observed SCP involvement in 22 subjects (62.8%) and confirmed this finding in 30/54 (55.6%) subjects from the validation cohorts. Cerebellar segmentation showed reduced mean volumes of lobules X and IV in the 5 affected individuals.

Conclusions

Cerebellar atrophy is a key feature of GAA-FGF14 ataxia. The frequent SCP involvement observed in different cohorts may facilitate the diagnosis. The predominant involvement of lobule X correlates with the frequently observed downbeat nystagmus.

Quality Assurance using Outlier Detection on an Automatic Segmentation Method for the Cerebellar Peduncles

Cerebellar peduncles (CPs) are white matter tracts connecting the cerebellum to other brain regions. Automatic segmentation methods of the CPs have been proposed for studying their structure and function. Usually the performance of these methods is evaluated by comparing segmentation results with manual delineations (ground truth). However, when a segmentation method is run on new data (for which no ground truth exists) it is highly desirable to efficiently detect and assess algorithm failures so that these cases can be excluded from scientific analysis. In this work, two outlier detection methods aimed to assess the performance of an automatic CP segmentation algorithm are presented. The first one is a univariate non-parametric method using a box-whisker plot. We first categorize automatic segmentation results of a dataset of diffusion tensor imaging (DTI) scans from 48 subjects as either a success or a failure. We then design three groups of features from the image data of nine categorized failures for failure detection. Results show that most of these features can efficiently detect the true failures. The second method-supervised classification-was employed on a larger DTI dataset of 249 manually categorized subjects. Four classifiers-linear discriminant analysis (LDA), logistic regression (LR), support vector machine (SVM), and random forest classification (RFC)-were trained using the designed features and evaluated using a leave-one-out cross validation. Results show that the LR performs worst among the four classifiers and the other three perform comparably, which demonstrates the feasibility of automatically detecting segmentation failures using classification methods.

Segmentation of the Cerebellar Peduncles Using a Random Forest Classifier and a Multi-object Geometric Deformable Model: Application to Spinocerebellar Ataxia Type 6

The cerebellar peduncles, comprising the superior cerebellar peduncles (SCPs), the middle cerebellar peduncle (MCP), and the inferior cerebellar peduncles (ICPs), are white matter tracts that connect the cerebellum to other parts of the central nervous system. Methods for automatic segmentation and quantification of the cerebellar peduncles are needed for objectively and efficiently studying their structure and function. Diffusion tensor imaging (DTI) provides key information to support this goal, but it remains challenging because the tensors change dramatically in the decussation of the SCPs (dSCP), the region where the SCPs cross. This paper presents an automatic method for segmenting the cerebellar peduncles, including the dSCP. The method uses volumetric segmentation concepts based on extracted DTI features. The dSCP and noncrossing portions of the peduncles are modeled as separate objects, and are initially classified using a random forest classifier together with the DTI features. To obtain geometrically correct results, a multi-object geometric deformable model is used to refine the random forest classification. The method was evaluated using a leave-one-out cross-validation on five control subjects and four patients with spinocerebellar ataxia type 6 (SCA6). It was then used to evaluate group differences in the peduncles in a population of 32 controls and 11 SCA6 patients. In the SCA6 group, we have observed significant decreases in the volumes of the dSCP and the ICPs and significant increases in the mean diffusivity in the noncrossing SCPs, the MCP, and the ICPs. These results are consistent with a degeneration of the cerebellar peduncles in SCA6 patients.