3T MRI Quantification of Hippocampal Volume and Signal in Mesial Temporal Lobe Epilepsy Improves Detection of Hippocampal Sclerosis

Coan, Ana Carolina; Kubota, Bruno Y.; Bergo, Felipe P. G.; Campos, Brunno M.; Cendes, Fernando

doi:10.3174/ajnr.a3640

Cited by 141 publications

(139 citation statements)

References 33 publications

Supporting

Mentioning

123

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, as we only utilized T1 MRI data and did not incorporate signal variation from T2/FLAIR scans (Coan et al, 2014, Cantor-Rivera et al, 2015 or alterations found in PET (Kerr et al, 2013) or DTI data (Cantor-Rivera et al, 2015), it is clear that there is still much room for improving classifier performance. Thus, in the future, an even more comprehensive model that identifies subgroups, incorporates other imaging modalities in addition to clinical and neuropsychological data, would likely be superior in regards to both diagnosis and predicting treatment outcomes, thus achieving clinical utility.…”

Section: Discussionmentioning

confidence: 99%

“…Using a linear discriminant analysis McDonald et al (2008) showed that lateral temporal cortical thickness could significantly discriminate TLE patients from controls with 74% accuracy. By focusing solely on quantification of hippocampal volume and T2 signal changes, computer-aided methods were shown to improve detection of MTS by 28% compared to visual analysis alone (Coan et al, 2014). Using a voxel-based approach for white and gray matter segmentation as well as voxel based DTI measures, Focke et al (2012) were able to distinguish TLE with MTS from controls with greater than 88% accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning classification of mesial temporal sclerosis in epilepsy patients

Rudie¹,

Colby²,

Salamon

2015

Epilepsy Research

View full text Add to dashboard Cite

a b s t r a c tBackground and purpose: Novel approaches applying machine-learning methods to neuroimaging data seek to develop individualized measures that will aid in the diagnosis and treatment of brain-based disorders such as temporal lobe epilepsy (TLE). Using a large cohort of epilepsy patients with and without mesial temporal sclerosis (MTS), we sought to automatically classify MTS using measures of cortical morphology, and to further relate classification probabilities to measures of disease burden. Materials and methods: Our sample consisted of high-resolution T1 structural scans of 169 adults with epilepsy collected across five different 1.5 T and four different 3 T scanners at UCLA. We applied a multiple support vector machine recursive feature elimination algorithm to morphological measures generated from FreeSurfer's automated segmentation and parcellation in order to classify Epilepsy patients with MTS (n = 85) from those without MTS (N = 84). Results: In addition to hippocampal volume, we found that alterations in cortical thickness, surface area, volume and curvature in inferior frontal and anterior and inferior temporal regions contributed to a classification accuracy of up to 81% (p = 1.3 × 10 −17 ) in identifying MTS. We also found that MTS classification probabilities were associated with a longer duration of disease for epilepsy patients both with and without MTS. Conclusions: In addition to implicating extra-hippocampal involvement of MTS, these findings shed further light on the pathogenesis of TLE and may ultimately assist in the development of automated tools that incorporate multiple neuroimaging measures to assist clinicians in detecting more subtle cases of TLE and MTS.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine learning classification of mesial temporal sclerosis in epilepsy patients

Rudie¹,

Colby²,

Salamon

2015

Epilepsy Research

View full text Add to dashboard Cite

show abstract

“…Furthermore, a study that tested the ability of conventional manual segmentation and two automatic segmentation methods for measuring hippocampal volume found that the manual method was more sensitive than both automated methods, and suggested that manual segmentation should still be used as the standard technique for volume measurements. [42] Furthermore, most of the automatic techniques are not completely automated and require manual intervention to outline the callosal boundaries. [43] The disadvantages of the manual method are: (i) results can be influenced by factors such as anatomical protocols, tracer experience, scan acquisition parameters and image quality; (ii) some authors consider that manual tracings are time consuming, but we think that this depends on the examined structure's complexity, and the CC is not a complex structure for tracing.…”

Section: Discussionmentioning

confidence: 99%

Magnetic resonance imaging study of corpus callosum abnormalities in patients with different subtypes of schizophrenia

et al. 2014

View full text Add to dashboard Cite

“…(d) [20,21] In these cases, advanced techniques of imaging including magnetic resonance spectroscopy (MRS), interictal FDG-PET, ictal SPECT (Figure 9), quantitative analysis of hippocampus formation such as volumetry and relaxometry, [22][23][24][25] can be useful tools for diagnostic and lateralization of seizure onset ( Figure 6). …”

Section: Mtle With Normal Mrimentioning

confidence: 99%

Neuroimaging in Focal Epilepsies: An Update

Cendes¹

2016

Epilepsi

View full text Add to dashboard Cite

SummaryEpilepsy is a common neurologic disorder with diverse etiologies. Appropriate MRI investigation has an important role in the assessment of epilepsy. Specific protocols are required for recognition of epileptogenic lesions, particularly for recognition of subtle lesions. In patients with refractory epilepsy and "normal MRI, " multimodal imaging techniques are crucial in the definition of epilepsy etiology, including those that combine metabolic and functional investigation, such as fluorodeoxyglucose positron emission tomography (FDG-PET), single-photonemission computed tomography (SPECT), diffusion MRI and magnetic resonance spectroscopy (MRS). Familiarity with various protocols of imaging studies is required for optimized investigation of seizure etiology. Main features found in MRIs of patients with focal epilepsies are discussed in the present review, as are alternative protocols and techniques of imaging that may optimize neuroimaging investigation in patients with epilepsy. The findings described have a direct impact on treatment and prognosis counseling of patients with focal epilepsies.Keywords: Focal epilepsies; neuroimaging. ÖzetEpilepsi, çeşitli etiyolojileri olan yaygın bir nörolojik rahatsızlıktır. Epilepsi değerlendirmesinde uygun manyetik rezonans görüntüleme (MRG) incelemeleri önemli bir role sahiptir. Epileptojenik lezyonların, özellikle güç alıgılanılan lezyonların teşhisi için spesifik protokollere ihtiyaç vardır. Dirençli epilepsisi olan ve "normal MRG" sonuçlarına sahip hastalarda florodeoksiglikoz-pozitron emsiyon tomografisi (FG-PET), tek föton emisyon bilgisayarlı tomografi (SPECT), difüzyon MRG ve manyetik rezonans spektroskopisi (MRS) gibi metabolik ve fonksiyonel incelemeleri de birleştiren multimodal görüntüleme yöntemleri epilepsi etiyolojisini tanımlamada önem taşımaktadır. Görüntüleme yöntemlerinin farklı protokollerine aşina olmak nöbet etiyolojisinin optimize incelemesi açısından gereklidir. Biz bu çalışmada, fokal epilepsisi olan hastaların MRG incelemesinde bulunan başlıca özellikleri tartışacağız. Ayrıca, epilepsisi olan hastaların nörolojik görüntüleme ile yapılan incelemelerini en uygun hale getirebilecek farklı görüntüleme yöntemleri ve alternatif protokolleri de tartışacağız. Burada tanımlanan bulguların, fokal epilepsisi olan hastaların tedavisi ve prognoz danışmanlığı üzerine doğrudan bir etkisi olacaktır.Anahtar sözcükler: Fokal epilepsi; nörolojik görüntüleme.

show abstract

3T MRI Quantification of Hippocampal Volume and Signal in Mesial Temporal Lobe Epilepsy Improves Detection of Hippocampal Sclerosis

Cited by 141 publications

References 33 publications

Machine learning classification of mesial temporal sclerosis in epilepsy patients

Machine learning classification of mesial temporal sclerosis in epilepsy patients

Magnetic resonance imaging study of corpus callosum abnormalities in patients with different subtypes of schizophrenia

Neuroimaging in Focal Epilepsies: An Update

Contact Info

Product

Resources

About