Automated ischemic stroke lesion segmentation from 3D MRI
This work addresses automated stroke lesion segmentation for medical imaging, but it is incremental as it applies existing methods to a new dataset.
The authors tackled the problem of segmenting ischemic stroke lesions from 3D MRI scans, achieving a top Dice score of 0.824 and second overall rank in the ISLES 2022 challenge.
Ischemic Stroke Lesion Segmentation challenge (ISLES 2022) offers a platform for researchers to compare their solutions to 3D segmentation of ischemic stroke regions from 3D MRIs. In this work, we describe our solution to ISLES 2022 segmentation task. We re-sample all images to a common resolution, use two input MRI modalities (DWI and ADC) and train SegResNet semantic segmentation network from MONAI. The final submission is an ensemble of 15 models (from 3 runs of 5-fold cross validation). Our solution (team name NVAUTO) achieves the top place in terms of Dice metric (0.824), and overall rank 2 (based on the combined metric ranking).