Epilepsia. 2022 Mar 17. doi: 10.1111/epi.17227. Online ahead of print.
ABSTRACT
OBJECTIVE: One of the clinical hallmarks of tuberous sclerosis complex is radiologically-identified cortical tubers present in most patients. Intractable epilepsy may require surgery, often involving invasive diagnostic procedures such as intracranial EEG. Identifying the location of the dominant tuber responsible for generating epileptic activities, is a critical issue. However, the link between cortical tubers and epileptogenesis is poorly understood. Given this, we hypothesized that tuber voxel intensity may be an indicator of the dominant epileptogenic tuber. Also, via tuber segmentation based on deep learning, we explore whether an automatic quantification of the tuber burden is feasible.
METHODS: We annotated tubers from structural MRIs across 29 TSC subjects, summarized tuber statistics in eight brain lobes, and determined suspected epileptogenic lobes from the same group using EEG monitoring data. Then logistic regression analyses are performed to demonstrate the linkage between the statistics of cortical tuber and the epileptogenic zones. Furthermore, we test the ability of a neural network to identify and quantify tuber burden.
RESULTS: Logistic regression analyses show that the volume and count of tubers per lobe, not the mean or variance of tuber voxel intensity, are positively correlated with electrophysiological data. In 47.6% of subjects, the lobe with the largest tuber volume concurred with the epileptic brain activity. A neural network model on the test dataset shows a sensitivity of 0.83 for localizing individual tubers. The predicted masks from the model highly correlated with the neurologist labels, thus may be a useful tool for determining tuber burden and searching for epileptogenic zone.
SIGNIFICANCE: we prove the feasibility of an automatic segmentation of tubers and a derivation of tuber burden across brain lobes. Our method may provide crucial insights in the treatment and outcome of TSC patients.
PMID:35301716 | DOI:10.1111/epi.17227
