Abstract #4121

Can neural networks support identification of epileptogenic foci in children with suspected focal cortical dysplasia (FCD)?

Enrico De Vita^1,2, Mathilde Ripart³, Kiran K Senaurine^2,4, Annemarie Knill¹, Yi Jie Li², Suresh Pujar⁵, Helen Cross⁶, M Zubair Tahir⁴, Friederike Moeller⁷, Sniya Sudhakar⁸, Pritika Gaur⁸, Kshitij Mankad⁸, Asthik Biswas⁸, Ulrike Loebel⁸, Aswin Chari⁶, Martin T Tisdall⁴, Konrad Wagstyl^6,9, Sophie Adler⁶, and Felice D'Arco⁸

¹MR Physics Group. Radiology, Great Ormond Street Hospital for Children NHS Foundation Trust, London, United Kingdom, ²Developmental Imaging and Biophysics Section, Developmental Neurosciences, UCL Great Ormond Street Institute of Child Health, University College London, London, United Kingdom, ³Developmental Neurosciences, UCL Great Ormond Street Institute of Child Health, University College London, London, United Kingdom, ⁴Neurosurgery, Great Ormond Street Hospital for Children NHS Foundation Trust, London, United Kingdom, ⁵Neurology, Great Ormond Street Hospital for Children NHS Foundation Trust, London, United Kingdom, ⁶UCL Great Ormond Street Institute of Child Health, University College London, London, United Kingdom, ⁷Neurophysiology, Great Ormond Street Hospital for Children NHS Foundation Trust, London, United Kingdom, ⁸Radiology, Great Ormond Street Hospital for Children NHS Foundation Trust, London, United Kingdom, ⁹Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom

Synopsis

Keywords: Epilepsy, Epilepsy, FCD

Motivation: Success of surgical resection in focal epilepsy is highly dependent on identification of epileptogenic foci. Machine learning algorithms are proving useful in supporting detection of pediatric focal cortical dysplasia (FCD) lesions.

Goal(s): Evaluating 2 algorithms predicting FCD lesions, developed by the multi-centre epilepsy lesion-detection project (MELD): the multi-layer-perceptron-based classifier [MELD_MLP] and the newer graph-neural-network based algorithm [MELD_GRAPH] aiming to increase specificity/accuracy. Is the new model better for routine clinical integration?

Approach: Comparison of true and false-positive rates for MELD_Graph vs MELD_MLP on 17 children

Results: MELD_MLP detects more lesions than MELD_Graph. However MELD_Graph produces less false positives, resulting in better positive predictive value

Impact: Clinical validation is essential for AI-based Focal Cortical Dysplasia lesion-detection algorithms. A local trade-off between sensitivity and specificity is necessary when selecting an appropriate decision support AI/machine-learning tool.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.