Interpretable surface-based detection of focal cortical dysplasias: a Multi-centre Epilepsy Lesion Detection study-Reference-Cited by-同舟云学术

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

Published:2022-08-10 Issue:11 Volume:145 Page:3859-3871
ISSN:0006-8950
Container-title:Brain
language:en
Short-container-title:

Author:

Spitzer Hannah¹,Ripart Mathilde²,Whitaker Kirstie³,D’Arco Felice⁴,Mankad Kshitij⁴,Chen Andrew A⁵⁶,Napolitano Antonio⁷,De Palma Luca⁸,De Benedictis Alessandro⁹,Foldes Stephen¹⁰,Humphreys Zachary¹⁰,Zhang Kai¹¹,Hu Wenhan¹¹,Mo Jiajie¹¹,Likeman Marcus¹²,Davies Shirin¹³¹⁴,Güttler Christopher¹⁵,Lenge Matteo¹⁶^ORCID,Cohen Nathan T¹⁷,Tang Yingying¹⁸¹⁹,Wang Shan¹⁹²⁰,Chari Aswin²⁴^ORCID,Tisdall Martin²⁴^ORCID,Bargallo Nuria²¹²²,Conde-Blanco Estefanía²³,Pariente Jose Carlos²³,Pascual-Diaz Saül²³,Delgado-Martínez Ignacio²⁴,Pérez-Enríquez Carmen²⁵,Lagorio Ilaria²⁶,Abela Eugenio²⁷^ORCID,Mullatti Nandini²⁸,O’Muircheartaigh Jonathan²⁸²⁹^ORCID,Vecchiato Katy²⁹³⁰,Liu Yawu³¹,Caligiuri Maria Eugenia³²,Sinclair Ben³³,Vivash Lucy³³³⁴,Willard Anna³³,Kandasamy Jothy³⁵,McLellan Ailsa³⁵,Sokol Drahoslav³⁵,Semmelroch Mira³⁶,Kloster Ane G³⁷,Opheim Giske³⁷³⁸,Ribeiro Letícia³⁹⁴⁰,Yasuda Clarissa³⁹⁴⁰,Rossi-Espagnet Camilla⁴¹,Hamandi Khalid¹³⁴²,Tietze Anna¹⁵,Barba Carmen¹⁶^ORCID,Guerrini Renzo¹⁶^ORCID,Gaillard William Davis¹⁷,You Xiaozhen¹⁷,Wang Irene¹⁹,González-Ortiz Sofía⁴³⁴⁴,Severino Mariasavina²⁶^ORCID,Striano Pasquale²⁶⁴⁵,Tortora Domenico²⁶,Kälviäinen Reetta³¹⁴⁶,Gambardella Antonio⁴⁷^ORCID,Labate Angelo⁴⁸^ORCID,Desmond Patricia⁴⁹,Lui Elaine⁴⁹,O’Brien Terence³³⁵⁰,Shetty Jay³⁵,Jackson Graeme⁵¹⁵²,Duncan John S⁵³^ORCID,Winston Gavin P⁵³⁵⁴^ORCID,Pinborg Lars H³⁷⁵⁵,Cendes Fernando³⁹⁴⁰,Theis Fabian J¹⁵⁶,Shinohara Russell T⁵⁷,Cross J Helen²⁵⁸,Baldeweg Torsten²⁴,Adler Sophie²,Wagstyl Konrad²⁵⁹^ORCID

Affiliation:

1. Institute of Computational Biology, Helmholtz Center Munich , Munich 85764 , Germany

2. Department of Developmental Neuroscience, UCL Great Ormond Street Institute for Child Health , London WC1N 1EH , UK

3. The Alan Turing Institute , London NW1 2DB , UK

4. Great Ormond Street Hospital NHS Foundation Trust , London WC1N 3JH , UK

5. Penn Statistics in Imaging and Visualization Center, Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania , Philadelphia, PA 19104 , USA

6. Center for Biomedical Image Computing and Analytics, University of Pennsylvania , Philadelphia, PA 19104 , USA

7. Medical Physics Department, Bambino Gesù Children’s Hospital , Rome 00165 , Italy

8. Rare and Complex Epilepsies, Department of Neurosciences, Bambino Gesù Children’s Hospital, IRCCS , Rome 00165 , Italy

9. Neurosurgery Unit, Department of Neurosciences, Bambino Gesù Children’s Hospital, IRCCS , Rome 00165 , Italy

10. Barrow Neurological Institute at Phoenix Children’s Hospital , Phoenix, AZ 85016 , USA

11. Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University , Beijing 100054 , China

12. Bristol Royal Hospital for Children , Bristol BS2 8BJ , UK

13. School of Psychology, Cardiff University Brain Research Imaging Centre , Cardiff CF24 4HQ , UK

14. The Welsh Epilepsy Unit, Cardiff and Vale University Health Board, University Hospital of Wales , Cardiff CF14 4XW , UK

15. Charité University Hospital , Berlin 10117 , Germany

16. Neuroscience Department, Children’s Hospital Meyer-University of Florence , Florence 50139 , Italy

17. Center for Neuroscience, Children’s National Hospital , Washington, DC 20012 , USA

18. Department of Neurology, West China Hospital of Sichuan University , Chengdu 610093 , China

19. Epilepsy Center, Cleveland Clinic , Cleveland, OH 44106 , USA

20. Department of Neurology, Epilepsy Center, Second Affiliated Hospital, School of Medicine, Zhejiang University , Hangzhou 310058 , China

21. Department of Neuroradiology, Hospital Clinic Barcelona and Magnetic Resonance Imaging, Core Facility, IDIBAPS , Barcelona 08036 , Spain

22. Centro de Investigación Biomédica en Red de Salud Mental, CIBERSAM , Madrid 28029 , Spain

23. Magnetic Resonance Imaging, Core Facility, IDIBAPS , Barcelona 08036 , Spain

24. Department of Neurosurgery, Hospital del Mar , Barcelona 08003 , Spain

25. Department of Neurology, Hospital del Mar , Barcelona 08003 , Spain

26. IRCCS Istituto Giannina Gaslini , Genova 16147 , Italy

27. Center for Neuropsychiatry and Intellectual Disability, Psychiatrische Dienste Aargau AG , Windisch 5120 , Switzerland

28. Institute of Psychiatry, Psychology and Neuroscience, King’s College , London SE5 8AF , UK

29. Department of Perinatal Imaging and Health, St. Thomas’ Hospital, King’s College London , London SE1 7EH , UK

30. Department of Forensic and Neurodevelopmental Sciences, Institute of Psychiatry, Psychology and Neuroscience, King’s College , London SE5 8AF , UK

31. Department of Neurology, University of Eastern Finland , Kuopio 70210 , Finland

32. Department of Medical and Surgical Sciences, Magna Graecia University of Catanzaro , Catanzaro 88100 , Italy

33. Department of Neuroscience, Central Clinical School, Monash University , Melbourne, VIC 3004 , Australia

34. Department of Neurology, Monash University , Melbourne, VIC 3004 , Australia

35. Royal Hospital for Children and Young People , Edinburgh EH16 4TJ , UK

36. The Florey Institute of Neuroscience and Mental Health, University of Melbourne , Parkville, VIC 3052 , Australia

37. Neurobiology Research Unit, Copenhagen University Hospital—Rigshospitalet , Copenhagen 2100 , Denmark

38. Department of Neuroradiology, Copenhagen University Hospital—Rigshospitalet , Copenhagen 2100 , Denmark

39. Department of Neurology, University of Campinas , Campinas 13083-888 , Brazil

40. Brazilian Institute of Neuroscience and Neurotechnology (BRAINN), University of Campinas , Campinas 13083-888 , Brazil

41. Neuroradiology Unit, IRCCS Bambino Gesù Children’s Hospital , Rome 00165 , Italy

42. The Welsh Epilepsy Unit, University Hospital of Wales , Cardiff CF14 4XW , UK

43. Department of Neuroradiology, Hospital del Mar , Barcelona 08003 , Spain

44. Magnetic Resonance Imaging Core Facility, Institut d’Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS) , Barcelona 08036 , Spain

45. Department of Neurosciences, Rehabilitation, Ophthalmology, Genetics, Maternal and Child Health, University of Genova , Genova , Italy

46. Kuopio Epilepsy Center, Neurocenter, Kuopio University Hospital , Kuopio 70210 , Finland

47. Institute of Neurology, Department of Medical and Surgical Sciences, Magna Graecia University , Catanzaro 88100 , Italy

48. Neurology Unit, Department of BIOMORF, University of Messina , Messina 98168 , Italy

49. Department of Radiology, The Royal Melbourne Hospital, University of Melbourne , Parkville, VIC 3050 , Australia

50. Department of Medicine, The Royal Melbourne Hospital , Parkville, VIC, 3052 , Australia

51. The Florey Institute of Neuroscience and Mental Health , Austin Campus, Heidelberg, VIC 3071 , Australia

52. Department of Neurology, Austin Health , Heidelberg, VIC 3084 , Australia

53. UCL Queen Square Institute of Neurology , London WC1N 3BG , UK

54. Department of Medicine, Division of Neurology, Queen’s University , Kingston, ON , Canada K7L 3N6

55. Epilepsy Clinic, Department of Neurology, Copenhagen University Hospital—Rigshopsitalet , Copenhagen 2100 , Denmark

56. Department of Mathematics, Technical University of Munich , Garching 85748 , Germany

57. Penn Statistics in Imaging and Visualization Center, Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania , Philadelphia, PA 19104 , USA

58. Young Epilepsy , Lingfield, Surrey RH7 6PW , UK

59. Wellcome Centre for Human Neuroimaging, University College London , London WC1N 3AR , UK

Abstract

Abstract 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.

Funder

Rosetrees Trust

NIHR GOSH BRC

Wellcome Trust

CNF/PERF Shields Award

CNRI Chief Research Officer Award

Hess Foundation and Children’s National IDDRC

São Paulo Research Foundation

Sir Henry Dale Fellowship

Wellcome Trust and the Royal Society

Medical Research Council Centre

King’s College London