Search

Presurgical evaluation that can precisely delineate the epileptogenic zone (EZ) is one important step for successful surgical resection treatment of refractory epilepsy patients. The noninvasive EEG-fMRI recording technique combined with general linear model (GLM) analysis is considered an important tool for estimating the EZ. However, the manual marking of interictal epileptic discharges (IEDs) needed in this analysis is challenging and time-consuming because the quality of the EEG recorded inside the scanner is greatly deteriorated compared to the usual EEG obtained outside the scanner. This is one of main impediments to the widespread use of EEG-fMRI in epilepsy. We propose a deep learning based semi-automatic IED detector that can find the candidate IEDs in the EEG recorded inside the scanner which resemble sample IEDs marked in the EEG recorded outside the scanner. The manual marking burden is greatly reduced as the expert need only edit candidate IEDs. The model is trained on data from 30 patients. Validation of IEDs detection accuracy on another 37 consecutive patients shows our method can improve the median sensitivity from 50.0% for the previously proposed template-based method to 84.2%, with false positive rate as 5 events/min. Reproducibility validation on 15 patients is applied to evaluate if our method can produce similar hemodynamic response maps compared with the manual marking ground truth results. We explore the concordance between the maximum hemodynamic response and the intracerebral EEG defined EZ and find that both methods produce similar percentage of concordance (76.9%, 10 out of 13 patients, electrode was absent in the maximum hemodynamic response in two patients). This tool will make EEG-fMRI analysis more practical for clinical usage., Highlights • A deep learning based epileptic discharge detector for EEG-fMRI is proposed. • The burden of manually marking epileptic discharges is greatly reduced. • Our method can produce similar EEG-fMRI results compared with traditional method.

Purpose Recent studies have applied the new magnetic resonance encephalography (MREG) sequence to the study of interictal epileptic discharges (IEDs) in the electroencephalogram (EEG) of epileptic patients. However, there are no criteria to quantitatively evaluate different processing methods, to properly use the new sequence. Methods We evaluated different processing steps of this new sequence under the common generalized linear model (GLM) framework by assessing the reliability of results. A bootstrap sampling technique was first used to generate multiple replicated data sets; a GLM with different processing steps was then applied to obtain activation maps, and the reliability of these maps was assessed. Results We applied our analysis in an event-related GLM related to IEDs. A higher reliability was achieved by using a GLM with head motion confound regressor with 24 components rather than the usual 6, with an autoregressive model of order 5 and with a canonical hemodynamic response function (HRF) rather than variable latency or patient-specific HRFs. Comparison of activation with IED field also favored the canonical HRF, consistent with the reliability analysis. Conclusion The reliability analysis helps to optimize the processing methods for this fast fMRI sequence, in a context in which we do not know the ground truth of activation areas. Magn Reson Med 78:370–382, 2017. © 2016 International Society for Magnetic Resonance in Medicine

Automatic and reliable segmentation of subcortical structures is an important but difficult task in quantitative brain image analysis. Multi-atlas based segmentation methods have attracted great interest due to their promising performance. Under the multi-atlas based segmentation framework, using deformation fields generated for registering atlas images onto a target image to be segmented, labels of the atlases are first propagated to the target image space and then fused to get the target image segmentation based on a label fusion strategy. While many label fusion strategies have been developed, most of these methods adopt predefined weighting models that are not necessarily optimal. In this study, we propose a novel local label learning strategy to estimate the target image's segmentation label using statistical machine learning techniques. In particular, we use a L1-regularized support vector machine (SVM) with a k nearest neighbor (kNN) based training sample selection strategy to learn a classifier for each of the target image voxel from its neighboring voxels in the atlases based on both image intensity and texture features. Our method has produced segmentation results consistently better than state-of-the-art label fusion methods in validation experiments on hippocampal segmentation of over 100 MR images obtained from publicly available and in-house datasets. Volumetric analysis has also demonstrated the capability of our method in detecting hippocampal volume changes due to Alzheimer's disease. Hum Brain Mapp 35:2674-2697, 2014. (c) 2013 Wiley Periodicals, Inc.

For medical image segmentation, multi-atlas based segmentation methods have attracted great attention recently. Within the multi-atlas segmentation framework, labels of all atlases are propagated to the target image by means of image registration and then fused to achieve segmentation of the target image. While most multi-atlas based segmentation methods focus on developing effective label fusion strategies, few of them make an effort to improve the accuracy of image registration between atlas and target images. Inspired by the idea that the estimated segmentation of the target image can be used to refine the pairwise registration performance, we propose an iterative strategy to improve registration accuracy between the atlas and target images using a multi-channel registration approach. In addition, an overfitting-resistant discriminative learning procedure, referred to as Jackknife Context Model (JCM), is adopted at each iteration to improve accuracy and robustness of label fusion results. Validation experiments on hippocampal segmentation have demonstrated that our method can statistically significantly improve the performance of the state-of-art multi-atlas based methods.

For subcortical structure segmentation, multi-atlas based segmentation methods have attracted great interest due to their competitive performance. Under this framework, using deformation fields generated for registering atlas images to the target image, labels of the atlases are first propagated to the target image space and further fused somehow to get the target segmentation. Many label fusion strategies have been proposed and most of them adopt predefined weighting models which are not necessarily optimal. In this paper, we propose a local label learning (L3) strategy to estimate the target image's label using statistical machine learning techniques. Specifically, we use Support Vector Machine (SVM) to learn a classifier for each of the target image voxels using its neighboring voxels in the atlases as a training dataset. Each training sample has dozens of image features extracted around its neighborhood and these features are optimally combined by the SVM learning method to classify the target voxel. The key contribution of this method is the development of a locally specific classifier for each target voxel based on informative texture features. The validation experiment on 57 MR images has demonstrated that our method generates segmentation results of hippocampal with a dice overlap of 0.908±0.023 to manual segmentations, statistically significantly better than state-of-the-art segmentation algorithms.

Multi-atlas based segmentation methods have recently attracted much attention in medical image segmentation. The multi-atlas based segmentation methods typically consist of three steps, including image registration, label propagation, and label fusion. Most of the recent studies devote to improving the label fusion step and adopt a typical image registration method for registering atlases to the target image. However, the existing registration methods may become unstable when poor image quality or high anatomical variance between registered image pairs involved. In this paper, we propose an iterative image segmentation and registration procedure to simultaneously improve the registration and segmentation performance in the multi-atlas based segmentation framework. Particularly, a two-channel registration method is adopted with one channel driven by appearance similarity between the atlas image and the target image and the other channel optimized by similarity between atlas label and the segmentation of the target image. The image segmentation is performed by fusing labels of multiple atlases. The validation of our method on hippocampus segmentation of 30 subjects containing MR images with both 1.5T and 3.0T field strength has demonstrated that our method can significantly improve the segmentation performance with different fusion strategies and obtain segmentation results with Dice overlap of 0.892±0.024 for 1.5T images and 0.902±0.022 for 3.0T images to manual segmentations.