Artificial intelligence for classification of temporal lobe epilepsy with ROI-level MRI data: A worldwide ENIGMA-Epilepsy study

Gleichgerrcht, Ezequiel; Munsell, Brent C.; Alhusaini, Saud; Alvim, Marina K. M.; Bargalló, Núria; Bender, Benjamín; Bernasconi, Andrea; Bernasconi, Neda; Bernhardt, Boris C.; Blackmon, Karen; Caligiuri, Maria Eugenia; Cendes, Fernando; Concha, Luis; Desmond, Patricia; Devinsky, Orrin; Doherty, Colin; Domín, Martin; Duncan, John S.; Focke, Niels K.; Gambardella, Antonio; Gong, Bo; Guerrini, Renzo; Hatton, Sean N.; Kälviäinen, Reetta; Keller, Simon S.; Kochunov, Peter; Kotikalapudi, Raviteja; Kreilkamp, Barbara A.K.; Labate, Angelo; Langner, Soenke; Larivière, Sara; Lenge, Matteo; Lui, Elaine; Martin, Pascal; Mascalchi, Mario; Meletti, Stefano; O’Brien, Terence J.; Pardoe, Heath; Pariente, José; Rao, Jun; Richardson, Mark P.; Rodríguez‐Cruces, Raúl; Rüber, Theodor; Sinclair, Ben; Soltanian‐Zadeh, Hamid; Stein, Dan J.; Striano, Pasquale; Taylor, Peter Neal; Thomas, Rhys; Vaudano, Anna Elisabetta; Vivash, Lucy; Podewills, Felix von; Vos, Sjoerd B.; Weber, Bernd; Yao, Yi; Yasuda, Clarissa Lin; Zhang, Junsong; Thompson, Paul M.; Sisodiya, Sanjay M.; McDonald, Carrie R.; Bonilha, Leonardo

doi:10.1016/j.nicl.2021.102765

Cited by 33 publications

(42 citation statements)

References 66 publications

(68 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…3A ) that was introduced in a recent study using machine learning to study the classification of temporal lobe epilepsy using multicentric ROI-level MRI data. 18 More specifically, given a set

of input images where

is a 2D square resolution

image for participant

and

is the total number of participants, and a set

of labels that defines the corresponding group label (e.g. HC = 0 and TLE = 1) for each participant, the following steps were sequentially applied to identify the optimal modelling parameters:…”

Section: Methodsmentioning

confidence: 99%

Radiological identification of temporal lobe epilepsy using artificial intelligence: a feasibility study

Gleichgerrcht

Munsell

Keller

et al. 2021

Brain Communications

Self Cite

View full text Add to dashboard Cite

Temporal lobe epilepsy is associated with magnetic resonance imaging (MRI) findings reflecting underlying mesial temporal sclerosis. Identifying these MRI features is critical for the diagnosis and management of temporal lobe epilepsy. To date, this process relies on visual assessment by highly trained human experts (e.g. neuroradiologists, epileptologists). Artificial intelligence is increasingly recognized as a promising aid in the radiological evaluation of neurological diseases, yet its applications in temporal lobe epilepsy have been limited. Here, we applied a convolutional neural networks to assess the classification accuracy of temporal lobe epilepsy based on structural MRI. We demonstrate that convoluted neural networks can achieve high accuracy in the identification of unilateral temporal lobe epilepsy cases even when the MRI had been originally interpreted as normal by experts. We show that accuracy can be potentiated by employing smoothed gray matter maps and a direct acyclic graphs approach. We further discuss the foundations for the development of computer-aided tools to assist with the diagnosis of epilepsy.

show abstract

“…3A ) that was introduced in a recent study using machine learning to study the classification of temporal lobe epilepsy using multicentric ROI-level MRI data. 18 More specifically, given a set

of input images where

is a 2D square resolution

image for participant

and

is the total number of participants, and a set

of labels that defines the corresponding group label (e.g. HC = 0 and TLE = 1) for each participant, the following steps were sequentially applied to identify the optimal modelling parameters:…”

Section: Methodsmentioning

confidence: 99%

Radiological identification of temporal lobe epilepsy using artificial intelligence: a feasibility study

Gleichgerrcht

Munsell

Keller

et al. 2021

Brain Communications

Self Cite

View full text Add to dashboard Cite

show abstract

“…13 This study revealed that structural MRI and dMRI-based models had similar accuracy and that models for TLE-HS were more accurate than for MRInegative TLE. 13 While the ability of automatic quantification methods may not currently exceed visual inspection of MRIs by imaging experts in all situations, AI algorithms and tools provide important support tools and may become of great importance when such expertise is not available. Some AI tools have already been integrated into clinical care for epilepsy, 20 but it will remain important for clinicians and AI-experts to remain in close dialog for newer ML and DL approaches to be adapted for clinical use.…”

Section: Artificial Intelligence Applications For Epilepsy Diagnosis ...mentioning

confidence: 64%

“…18,19 A recent ENIGMA-Epilepsy study investigated the performance of ML and DL algorithms using structural MRI and diffusion MRI (dMRI) to classify controls vs patients with TLE with HS and MRI-negative TLE. 13 This study revealed that structural MRI and dMRI-based models had similar accuracy and that models for TLE-HS were more accurate than for MRInegative TLE. 13 While the ability of automatic quantification methods may not currently exceed visual inspection of MRIs by imaging experts in all situations, AI algorithms and tools provide important support tools and may become of great importance when such expertise is not available.…”

Section: Artificial Intelligence Applications For Epilepsy Diagnosis ...mentioning

confidence: 64%

“… 12 One successful example is the Enhancing Neuroimaging Genetics through Meta-analysis (ENIGMA) brain imaging consortium that has revealed associations between brain imaging, genetic variations, and cognition in both healthy subjects and different diseases, including epilepsy. 13 – 16 Another is the multicenter epilepsy lesion detection (MELD) project. 17 These datasets include hundreds to thousands of MRI and clinical data in patients with epilepsy and are ripe for AI applications.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence Applications in the Imaging of Epilepsy and Its Comorbidities: Present and Future

Cendes

McDonald

2022

Epilepsy Curr

Self Cite

View full text Add to dashboard Cite

Artificial intelligence (AI) is increasingly used in medical image analysis and has accelerated scientific discoveries across fields of medicine. In this review, we highlight how AI has been applied to neuroimaging in patients with epilepsy to enhance classification of clinical diagnosis, prediction of treatment outcomes, and the understanding of cognitive comorbidities. We outline the strengths and shortcomings of current AI research and the need for future studies using large datasets that test the reproducibility and generalizability of current findings, as well as studies that test the clinical utility of AI approaches.

show abstract

“…In the presently highlighted study, Gleichgerrecht and colleagues leveraged ENIGMA-Epilepsy structural and diffusion-weighted MRI data using a machine learning approach to evaluate epilepsy patient and control subgroups. 4 For structural T1-weighted MRI analysis, data were collected from 16 centers and included 336 unilateral adult TLE patients and 631 matched control subjects, while diffusion data originated from 21 sites and included 863 individuals with TLE and 976 controls. Approximately 56% of TLE patients were diagnosed with left sided seizure onset, and structural T1 data were only available for patients with MTS, although diffusion data were obtained for patients with MTS and non-lesional TLE.…”

Section: Commentarymentioning

confidence: 99%

Machine Learning to Address the Enigma of Temporal Lobe Epilepsy Lateralization

Englot¹

2021

Epilepsy Curr

View full text Add to dashboard Cite

Artificial intelligence has recently gained popularity across different medical fields to aid in the detection of diseases based on pathology samples or medical imaging findings. Brain magnetic resonance imaging (MRI) is a key assessment tool for patients with temporal lobe epilepsy (TLE). The role of machine learning and artificial intelligence to increase detection of brain abnormalities in TLE remains inconclusive. We used support vector machine (SV) and deep learning (DL) models based on region of interest (ROI-based) structural (n = 336) and diffusion (n = 863) brain MRI data from patients with TLE with ("lesional") and without ("non-lesional") radiographic features suggestive of underlying hippocampal sclerosis from the multinational (multi-center) ENIGMA-Epilepsy consortium. Our data showed that models to identify TLE performed better or similar (68-75%) compared to models to lateralize the side of TLE (56-73%, except structural-based) based on diffusion data with the opposite pattern seen for structural data (67-75% to diagnose vs 83% to lateralize). In other aspects, structural and diffusion-based models showed similar classification accuracies. Our classification models for patients with hippocampal sclerosis were more accurate (68-76%) than models that stratified non-lesional patients (53-62%). Overall, SV and DL models performed similarly with several instances in which SV mildly outperformed DL. We discuss the relative performance of these models with ROI-level data and the implications for future applications of machine learning and artificial intelligence in epilepsy care.

show abstract

Artificial intelligence for classification of temporal lobe epilepsy with ROI-level MRI data: A worldwide ENIGMA-Epilepsy study

Cited by 33 publications

References 66 publications

Radiological identification of temporal lobe epilepsy using artificial intelligence: a feasibility study

Radiological identification of temporal lobe epilepsy using artificial intelligence: a feasibility study

Artificial Intelligence Applications in the Imaging of Epilepsy and Its Comorbidities: Present and Future

Machine Learning to Address the Enigma of Temporal Lobe Epilepsy Lateralization

Contact Info

Product

Resources

About