iiinova — where your digital self keeps evolving

Mathilde Ripart

@mathrip.bsky.social

Postdoctoral Researcher | Neurosciences | Machine learning | Epilepsy | MELD project

Mathilde Ripart @mathrip.bsky.social · 25/02/2025

5️⃣Finally, MELD Graph was a huge team effort with @konradwagstyl.bsky.social, @sophieadlerwagstyl.bsky.social, @hannahspitzer. and our MELD consortium (@drfelicedarco.bsky.social @nathantcohen.bsky.social @metricsemma.bsky.social @kirstiejane.bsky.social @lzjwilliams.bsky.social + many others!)

052

Mathilde Ripart @mathrip.bsky.social · 25/02/2025

3️⃣ Notably, MELD Graph detected 64% of lesions previously missed by radiologists. The MELD reports below show two independent test patients with FCD that were missed by 5/5 expert radiologists.

110

Mathilde Ripart @mathrip.bsky.social · 25/02/2025

2️⃣ Incorporating whole brain context significantly boosted model specificity – fewer false positives mean the positive predictive is significantly lower than a baseline Multilayer Perceptron (MLP). Also, the predictions generally look much nicer!

110

Mathilde Ripart @mathrip.bsky.social · 25/02/2025

1️⃣MELD Graph uses a graph convolutional neural network to segment FCD lesions on the cortical surface. We trained it using the Multicentre Epilepsy Lesion Detection project’s FCD cohort, with 703 epilepsy patients and 482 controls from 23 hospitals around the world.

110