Prognosis after intracranial hemorrhage (ICH) is influenced by a complex interplay between imaging and tabular data. Rapid and reliable prognosis are crucial for effective patient stratification and informed treatment decision-making. In this study, we aim to enhance image-based prognosis by learning a robust feature representation shared between prognosis and the clinical and demographic variables most highly correlated with it. Our approach mimics clinical decision-making by reinforcing the model to learn valuable prognostic data embedded in the image. We propose a 3D multi-task image model to predict prognosis, Glasgow Coma Scale and age, improving accuracy and interpretability. Our method outperforms current state-of-the-art baseline image models, and demonstrates superior performance in ICH prognosis compared to four board-certified neuroradiologists using only CT scans as input. We further validate our model with interpretability saliency maps. Code is available at https://github.com/MiriamCobo/MultitaskLearning_ICH_Prognosis.git.
@article{arxiv.2408.08784,
title = {Multi-task Learning Approach for Intracranial Hemorrhage Prognosis},
author = {Miriam Cobo and Amaia Pérez del Barrio and Pablo Menéndez Fernández-Miranda and Pablo Sanz Bellón and Lara Lloret Iglesias and Wilson Silva},
journal= {arXiv preprint arXiv:2408.08784},
year = {2025}
}
Comments
16 pages. Accepted at Machine Learning in Medical Imaging Workshop @ MICCAI 2024 (MLMI2024). This is the submitted manuscript with added link to github repo, funding acknowledgements and authors' names and affiliations. No further post submission improvements or corrections were integrated. Final version not published yet