Multi-task Learning Approach for Intracranial Hemorrhage Prognosis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913809186160640 |
|---|---|
| author | Cobo, Miriam del Barrio, Amaia Pérez Fernández-Miranda, Pablo Menéndez Bellón, Pablo Sanz Iglesias, Lara Lloret Silva, Wilson |
| author_facet | Cobo, Miriam del Barrio, Amaia Pérez Fernández-Miranda, Pablo Menéndez Bellón, Pablo Sanz Iglesias, Lara Lloret Silva, Wilson |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_08784 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-task Learning Approach for Intracranial Hemorrhage Prognosis Cobo, Miriam del Barrio, Amaia Pérez Fernández-Miranda, Pablo Menéndez Bellón, Pablo Sanz Iglesias, Lara Lloret Silva, Wilson Image and Video Processing Computer Vision and Pattern Recognition I.2 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. |
| title | Multi-task Learning Approach for Intracranial Hemorrhage Prognosis |
| topic | Image and Video Processing Computer Vision and Pattern Recognition I.2 |
| url | https://arxiv.org/abs/2408.08784 |