Interpretable surface-based detection of focal cortical dysplasias: a Multi-centre Epilepsy Lesion Detection study.

2022-11-21

Spitzer, Hannah

Ripart, Mathilde

Whitaker, Kirstie

D'Arco, Felice

Mankad, Kshitij

Chen, Andrew A

Napolitano, Antonio

De Palma, Luca

De Benedictis, Alessandro

Foldes, Stephen

Humphreys, Zachary

Zhang, Kai

Hu, Wenhan

Mo, Jiajie

Likeman, Marcus

Davies, Shirin

Güttler, Christopher

Lenge, Matteo

Cohen, Nathan T

Tang, Yingying

Wang, Shan

Chari, Aswin

Tisdall, Martin

Bargallo, Nuria

Conde-Blanco, Estefanía

Pariente, Jose Carlos

Pascual-Diaz, Saül

Delgado-Martínez, Ignacio

Pérez-Enríquez, Carmen

Lagorio, Ilaria

Abela, Eugenio

Mullatti, Nandini

O'Muircheartaigh, Jonathan

Vecchiato, Katy

Liu, Yawu

Caligiuri, Maria Eugenia

Sinclair, Ben

Vivash, Lucy

Willard, Anna

Kandasamy, Jothy

McLellan, Ailsa

Sokol, Drahoslav

Semmelroch, Mira K H G

Kloster, Ane G

Opheim, Giske

Ribeiro, Letícia

Yasuda, Clarissa

Rossi-Espagnet, Camilla

Hamandi, Khalid

Tietze, Anna

Barba, Carmen

Guerrini, Renzo

Gaillard, William Davis

You, Xiaozhen

Wang, Irene

González-Ortiz, Sofía

Severino, Mariasavina

Striano, Pasquale

Tortora, Domenico

Kälviäinen, Reetta

Gambardella, Antonio

Labate, Angelo

Desmond, Patricia

Lui, Elaine

O'Brien, Terence

Shetty, Jay

Jackson, Graeme D

Duncan, John S

Winston, Gavin P

Pinborg, Lars H

Cendes, Fernando

Theis, Fabian J

Shinohara, Russell T

Cross, J Helen

Baldeweg, Torsten

Adler, Sophie

Wagstyl, Konrad

epilepsy

focal cortical dysplasia

machine learning

structural MRI

Journal Article

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

0000-0003-2848-621X

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

0000-0003-0053-147X

0000-0001-8880-8386

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

0000-0002-9356-1450

#PLACEHOLDER_PARENT_METADATA_VALUE#

0000-0002-8033-6959

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

0000-0001-5445-5842

0000-0002-7272-7079

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

0000-0003-4730-5322

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

0000-0001-7384-3074

0000-0002-8827-7324

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

0000-0002-1373-0681

0000-0001-9395-1478

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

#PLACEHOLDER_PARENT_METADATA_VALUE#

0000-0003-3439-5808

10.1093/brain/awac224

One outstanding challenge for machine learning in diagnostic biomedical imaging is algorithm interpretability. A key application is the identification of subtle epileptogenic focal cortical dysplasias (FCDs) from structural MRI. FCDs are difficult to visualize on structural MRI but are often amenable to surgical resection. We aimed to develop an open-source, interpretable, surface-based machine-learning algorithm to automatically identify FCDs on heterogeneous structural MRI data from epilepsy surgery centres worldwide. The Multi-centre Epilepsy Lesion Detection (MELD) Project collated and harmonized a retrospective MRI cohort of 1015 participants, 618 patients with focal FCD-related epilepsy and 397 controls, from 22 epilepsy centres worldwide. We created a neural network for FCD detection based on 33 surface-based features. The network was trained and cross-validated on 50% of the total cohort and tested on the remaining 50% as well as on 2 independent test sites. Multidimensional feature analysis and integrated gradient saliencies were used to interrogate network performance. Our pipeline outputs individual patient reports, which identify the location of predicted lesions, alongside their imaging features and relative saliency to the classifier. On a restricted 'gold-standard' subcohort of seizure-free patients with FCD type IIB who had T1 and fluid-attenuated inversion recovery MRI data, the MELD FCD surface-based algorithm had a sensitivity of 85%. Across the entire withheld test cohort the sensitivity was 59% and specificity was 54%. After including a border zone around lesions, to account for uncertainty around the borders of manually delineated lesion masks, the sensitivity was 67%. This multicentre, multinational study with open access protocols and code has developed a robust and interpretable machine-learning algorithm for automated detection of focal cortical dysplasias, giving physicians greater confidence in the identification of subtle MRI lesions in individuals with epilepsy.

link

Brain 2022

Brain

1460-2156