ISLES’24: Final Infarct Prediction with Multimodal Imaging and Clinical Data. Where Do We Stand?

Accurate estimation of brain infarction (i.e., irreversibly damaged tissue) is critical for guiding treatment decisions in acute ischemic stroke. This work introduces the ISLES’24 challenge, which focuses on the prediction of final infarct volumes from pre-interventional acute stroke imaging and clinical data. The challenge provides a comprehensive multimodal dataset—including full acute CT imaging, follow-up MRI, and structured clinical information—for 150 training and 98 test cases. On the hidden test set, the top-performing multimodal nnU-Net–based model achieved a Dice score of 0.285 ± 0.213 and an absolute volume difference of 21.2 ± 37.2 mL, underlining the difficulty of the task and the need for further advances. ISLES’24 establishes a standardized benchmark for post-treatment infarct prediction and highlights current methodological limitations, offering guidance for the development of next-generation multimodal models.