MELD-PostOp: an automated segmentation tool for post-surgical resection cavities on T1w MRI in focal epilepsy

Read full text
Authors: Jieun Seo, Mathilde Ripart, Konrad Wagstyl, Sophie Adler
Cited by: 0

Abstract

MELD-PostOp is an automated segmentation tool based on the nnU-Net, designed to identify resection cavities on postoperative T1w MRI in patients with focal epilepsy. MELD-PostOP was trained on 965 postoperative scans collected from 25 MELD focal epilepsy (FE) sites and EPISURG dataset. The repository provides a pretrained nnU-Net weight (MELDPostOp_v1.0.0) for inference only. nnU-Net ver 2 is required. For detailed information on prerequisites, installation, and usage, please refer to the MELD Project Github repository.

Fields of Study & Subjects

Medical Image Segmentation Techniques Brain Tumor Detection and Classification Medical Imaging and Analysis

Publication details

Journal / source
Figshare
Publication date
5 March 2026
Language
EN