Dataset Information

Radiomics features of hippocampal regions in magnetic resonance imaging can differentiate medial temporal lobe epilepsy patients from healthy controls.

ABSTRACT: To investigative whether radiomics features in bilateral hippocampi from MRI can identify temporal lobe epilepsy (TLE). A total of 131 subjects with MRI (66 TLE patients [35 right and 31 left TLE] and 65 healthy controls [HC]) were allocated to training (n?=?90) and test (n?=?41) sets. Radiomics features (n?=?186) from the bilateral hippocampi were extracted from T1-weighted images. After feature selection, machine learning models were trained. The performance of the classifier was validated in the test set to differentiate TLE from HC and ipsilateral TLE from HC. Identical processes were performed to differentiate right TLE from HC (training set, n?=?69; test set; n?=?31) and left TLE from HC (training set, n?=?66; test set, n?=?30). The best-performing model for identifying TLE showed an AUC, accuracy, sensitivity, and specificity of 0.848, 84.8%, 76.2%, and 75.0% in the test set, respectively. The best-performing radiomics models for identifying right TLE and left TLE subgroups showed AUCs of 0.845 and 0.840 in the test set, respectively. In addition, multiple radiomics features significantly correlated with neuropsychological test scores (false discovery rate-corrected p-values?

SUBMITTER: Park YW

PROVIDER: S-EPMC7658973 | biostudies-literature | 2020 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Radiomics features of hippocampal regions in magnetic resonance imaging can differentiate medial temporal lobe epilepsy patients from healthy controls.

Park Yae Won YW Choi Yun Seo YS Kim Song E SE Choi Dongmin D Han Kyunghwa K Kim Hwiyoung H Ahn Sung Soo SS Kim Sol-Ah SA Kim Hyeon Jin HJ Lee Seung-Koo SK Lee Hyang Woon HW

Scientific reports 20201111 1

To investigative whether radiomics features in bilateral hippocampi from MRI can identify temporal lobe epilepsy (TLE). A total of 131 subjects with MRI (66 TLE patients [35 right and 31 left TLE] and 65 healthy controls [HC]) were allocated to training (n = 90) and test (n = 41) sets. Radiomics features (n = 186) from the bilateral hippocampi were extracted from T1-weighted images. After feature selection, machine learning models were trained. The performance of the classifier was validated in ...[more]

PMID: 33177624

Similar Datasets

Project description:Mesial temporal lobe epilepsy (MTLE), one of the most common types of refractory focal epilepsy, has shown white matter abnormalities both within and beyond the temporal lobe. In particular, the white matter abnormalities in the ipsilateral hemisphere are more obvious than those in the contralateral hemisphere in MTLE, that is, the abnormalities present asymmetrical characteristics. However, very few studies have characterized the white matter microstructure asymmetry in MTLE patients specifically. Thus, we performed diffusion tensor imaging (DTI) to investigate the white matter microstructure asymmetries of patients with MTLE with unilateral hippocampal sclerosis (MTLE-HS). We enrolled 25 MTLE-HS (left MTLE-HS group, n = 13; right MTLE-HS group, n = 12) and 26 healthy controls (HC). DTI data were analyzed by tract-based spatial statistics (TBSS) to test the hemispheric differences across the entire white matter skeleton. We also conducted a two-sample paired t-test for 21 paired region of interests (ROIs) parceled on the basis of the ICBM-DTI-81 white-matter label atlas of bilateral hemispheres to test the hemispheric differences. An asymmetry index (AI) was calculated to further quantify the differences between the left and right paired-ROIs. It was found that the asymmetries of white matter skeletons were significantly lower in the MTLE-HS groups than in the HC group. In particular, the asymmetry traits were moderately reduced in the RMTLE-HS group and obviously reduced in the LMTLE-HS group. In addition, AI was significantly different in the RMTLE-HS group from the LMTLE-HS or HC group in the limbic system and superior longitudinal fasciculus (SLF). The current study found that the interhemispheric white matter asymmetries were significantly reduced in the MTLE-HS groups than in the HC group. The interhemispheric white matter asymmetries are distinctly affected in left and right MTLE-HS groups. The differences in AI among RMTLE-HS, LMTLE-HS, and HC involved the limbic system and SLF, which may have some pragmatic implications for the diagnosis of MTLE and differentiating LMTLE-HS from RMTLE-HS.

Project description:Mesial temporal lobe epilepsy (mTLE) is a chronic disorder with spontaneous seizures recurring for years, or even decades. Many structural and functional changes have been detected in both the seizure focus and distal regions throughout the brain over this duration that may reflect the development of epileptogenic networks. Resting state functional magnetic resonance imaging (fMRI) connectivity mapping has the potential to elucidate and quantify these networks. The network between the left and right hippocampus may very likely be one of the most susceptible to changes due to long-term seizure propagation effects. Therefore, the objective of this study was to quantify cross hippocampal influence in mTLE using high temporal resolution fMRI, and to determine its relationship with disease duration.fMRI images were acquired in the resting (interictal) state with 500 ms temporal resolution across the temporal lobes of 19 mTLE patients (13 left, 6 right). The left and right hippocampi were identified on each subject's images using both structurally defined and functionally defined boundaries. The cross hippocampal influence was quantified in two ways for each pair of regions: (1) the nondirectional hippocampal functional connectivity calculated as the Pearson's correlation between the average time series in the left and the right hippocampus regions, and (2) the Granger causality (GC) laterality measure, which implies directional influence by determining temporal precedence. Each of these measures was correlated with age, age of onset, and disease duration across subjects to investigate relationship to disease progression.The hippocampal connectivity was not significantly different between patients with left and right mTLE using either the structurally or the functionally defined regions. Across all patients, hippocampal connectivity was not correlated significantly with age of onset or duration of disease. However, as duration of disease increased after 10 years (nine patients), the hippocampal connectivity increased linearly. Using the functionally defined regions, the GC laterality was increased in the right mTLE over the left mTLE, indicating that the left hippocampus was influencing the right hippocampus more than the right influencing left. This was also positively correlated with age of onset. Furthermore, like hippocampal connectivity, the relationship between GC laterality and duration of disease changes after 10 years duration of disease. After this duration, the GC laterality was positive in the three of three patients with right mTLE (left influencing right), whereas the GC laterality was negative in five of six patients with left mTLE (right influencing left).This study reveals a relationship between fMRI functional connectivity and causal influence of the left and right hippocampi and duration of disease in mTLE. During the interictal state, the interhemispheric hippocampal connectivity initially is disrupted and then linearly increases as the epilepsy progresses longer than 10 years. This increase in connectivity appears to be due to the hippocampus contralateral to the epileptogenic focus exerting more influence over the ipsilateral hippocampus. These findings may have implications in understanding the functional development of epileptic networks and possibly prediction of surgical outcome of mTLE.

Project description:BackgroundMedial temporal lobe epilepsy (MTLE) is associated with limbic atrophy involving the hippocampus, peri-hippocampal and extra-temporal structures. While MTLE is related to static structural limbic compromise, it is unknown whether the limbic system undergoes dynamic regional perfusion network alterations during seizures. In this study, we aimed to investigate state specific (i.e. ictal versus interictal) perfusional limbic networks in patients with MTLE.MethodsWe studied clinical information and single photon emission computed tomography (SPECT) images obtained with intravenous infusion of the radioactive tracer Technetium- Tc 99 m Hexamethylpropyleneamine Oxime (Tc-99 m HMPAO) during ictal and interictal state confirmed by video-electroencephalography (VEEG) in 20 patients with unilateral MTLE (12 left and 8 right MTLE). Pair-wise voxel-based analyses were used to define global changes in tracer between states. Regional tracer uptake was calculated and state specific adjacency matrices were constructed based on regional correlation of uptake across subjects. Graph theoretical measures were applied to investigate global and regional state specific network reconfigurations.ResultsA significant increase in tracer uptake was observed during the ictal state in the medial temporal region, cerebellum, thalamus, insula and putamen. From network analyses, we observed a relative decreased correlation between the epileptogenic temporal region and remaining cortex during the interictal state, followed by a surge of cross-correlated perfusion in epileptogenic temporal-limbic structures during a seizure, corresponding to local network integration.ConclusionsThese results suggest that MTLE is associated with a state specific perfusion and possibly functional organization consisting of a surge of limbic cross-correlated tracer uptake during a seizure, with a relative disconnection of the epileptogenic temporal lobe in the interictal period. This pattern of state specific shift in metabolic networks in MTLE may improve the understanding of epileptogenesis and neuropsychological impairments associated with MTLE.

Dataset Information

Radiomics features of hippocampal regions in magnetic resonance imaging can differentiate medial temporal lobe epilepsy patients from healthy controls.

Publications

Radiomics features of hippocampal regions in magnetic resonance imaging can differentiate medial temporal lobe epilepsy patients from healthy controls.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets