Number of Tables: 2
Highlights:
- Multiscale image filters provide a good representation of local cortical appearance
- Normative modeling can be used to describe normal cortical variability
- Most FCD lesions and some normal cortical regions appear as outliers in our model
- FCDs appear similar to paralimbic and primary sensorimotor cortical regions in our model
- Our constrained outlier detection approach allows for automated FCD detection
Introduction
Focal cortical dysplasia (FCD) is a relatively common cause of drug-resistant focal epilepsy, and particularly of MRI negative (MRI-) epilepsy. Approximately 15-25% of patients being evaluated for epilepsy surgery have apparently normal MRIs; FCD is diagnosed pathologically in 25-50% of these patients \cite{Blumcke2017,Lerner2009,Bien2009}. Because post-operative seizure outcomes are significantly worse in MRI- compared to MRI positive (MRI+) patients \cite{Téllez-Zenteno2010}, improved identification of subtle FCDs is of great clinical importance as it may lead to better surgical outcomes.
FCDs are variable in their histopathological and radiographic appearances. Pathological abnormalities range from cortical dyslamination in type I, to the presence of large dysmorphic neurons in type IIa (FCDIIa), and balloon cells and more prominent dysmyelination in type IIb (FCDIIb) \cite{Blümcke2011}. FCD type I lesions are typically difficult to identify radiologically, most often consisting of cortical thinning and lobar hypoplasia, at times with blurring of the gray-white junction and changes in T1- or T2-weighted image intensity. FCD type II lesions are more easily identified on MRI, with typical findings consisting of increased cortical thickness, blurring of the gray-white junction, FLAIR/T2 hyperintensity (including the transmantle sign in FCD type IIb), and alterations in gyrification patterns \cite{Adler2017a,Kini2016}. These findings, however, appear inconsistently within and across lesions \cite{Hong2017} and are often subtle, with up to 80% of small bottom-of-sulcus dysplasias being missed on routine visual inspection \cite{Besson2008}.
To aid with detection of subtle FCD lesions, a number of post-processing methods have been developed. These range from creation of synthetic contrasts to highlight areas of interest (such as the Morphometric Analysis Program (MAP) \cite{Huppertz2005}), to machine-learning based fully automated detection methods (such as those described by \cite{Adler2017,Ahmed2015,Hong2014}). Across these methods, two key challenges have been 1) selection of optimal features to describe FCD lesions, and 2) accounting for variability within and across FCD lesions, as well as in normal cortex. While a wide variety of features have been investigated, most methods have used features derived from either voxel-based morphometry \cite{Huppertz2005,Martin2017} or surface-based morphometry (SBM) (see review in \cite{Kini2016}). Higher-order textural features or local statistics used to describe the local characteristics of patches within an image, are well-described in computer vision applications \cite{Portilla2003}, but have only occasionally been applied in biomedical imaging (for examples, see \cite{Joyseeree2018,Wang2018,Zacharaki2009}), and even less often for FCD detection \cite{Antel2003}.
In this work, we describe a novel approach for describing the normal variability observed along the cortical sheet in healthy volunteers. This normative model is then used to identify outliers, first in healthy volunteers to identify atypical normal cortical regions, and then in patients to identify focal cortical dysplasias. Our model is based on an implementation of 3D multiscale rotationally-invariant local image features across multiple MR contrasts, similar to those that have been previously shown to efficiently represent the local statistics of natural images \cite{Simoncelli2001}. We use these features to create a latent representation of this normative data that allows for straightforward outlier detection in our multivariate feature space. We identify several cortical regions as outliers in healthy volunteers, corresponding to regions known to have atypical underlying cytoarchitecture and myelination patterns. In patients, most FCD lesions also appear as outliers, but are similar in their underlying features to some normally atypical regions. Local normalization corrects for the expected appearance at any given cortical location, and allows for automated detection of FCDs.
Materials and Methods
Study Participants
From our surgical epilepsy imaging database, we retrospectively identified 15 consecutive patients undergoing presurgical evaluation for drug-resistant focal epilepsy from 2014-2019 with: 1) radiologically apparent (MRI+) or histologically proven (MRI+ or MRI-) FCDs; and 2) our standard 3T MRI epilepsy structural imaging protocol. Patients were excluded if they underwent other MR imaging protocols or had low image quality on visual inspection. The control group consisted of 30 healthy volunteers (HVs) scanned using the same imaging protocol with no previous history of neurologic, psychiatric, or other significant medical illnesses that may affect the central nervous system. Data were collected at the National Institutes of Health (NIH) Clinical Center (Bethesda, MD). All participants were enrolled in an Institutional Review Board-approved research protocol; informed consent was obtained from all participants.
Lesion Labels
For MRI+ patients, lesions were traced in the volume using the Analysis of Functional NeuroImages (AFNI) software package \cite{Cox1996a} by an experienced neurologist using the T1 weighted image, informed by the T2 and FLAIR images when necessary. For MRI- patients, the postoperative T1 was registered to the preoperative T1 in the same manner as described below for T2 and FLAIR images; the resected region was manually traced using AFNI. Lesion masks were mapped onto the smoothed white matter surface using AFNI's 3dVol2Surf function.
MRI Acquisition Protocol
All participants were scanned on a Philips Achieva 3T MRI scanner in the NIH Clinical Center Radiology Department as follows: 1) 3D T1 weighted MPRAGE (T1): TR = 6.8–7.2, TE = 3.2 ms, TI = 900ms, flip angle = 90, voxel size = 0.75 x 0.75 x 0.8, acceleration factor 2 in slice direction, acquisition time = 7:02 min; 2) 3D T2 weighted FSE (T2): TR = 2500, TE = 225–245, voxel size = 1 x 1 x 2 or 1 x 1 x 1, acceleration factor 2 in slice and phase directions, acquisition time = 5:03 min; and 3) 3D FLAIR: TR = 4800, TE = 271–415, TI = 1600, voxel size = 0.9 x 0.9 x 1, acceleration factor 2 in slice direction, 2.6 in phase direction, acquisition time = 6:10 min. All scans were acquired sagittally.
Image Preprocessing
For each individual subject, T
2 and FLAIR images were co-registered to the T
1 with an affine transformation using a normalized mutual information cost function and resampled to the T
1 grid using AFNI. Registered images were visually assessed for alignment. Cortical reconstruction was performed using T
1 and T
2 images as input to FreeSurfer's standard processing pipeline with
FreeSurfer v6.0.0 \cite{Dale1999,Fischl1999}. Results were visually inspected and manually corrected as needed. Cortical surfaces were resampled to a standard mesh using the AFNI SUMA package
\cite{Cox1996a} to allow comparison of corresponding vertices across individuals.