Treatment-aware Diffusion Probabilistic Model for Longitudinal MRI Generation and Diffuse Glioma Growth Prediction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929683587661824 |
|---|---|
| author | Liu, Qinghui Fuster-Garcia, Elies Hovden, Ivar Thokle MacIntosh, Bradley J Grødem, Edvard Brandal, Petter Lopez-Mateu, Carles Sederevicius, Donatas Skogen, Karoline Schellhorn, Till Bjørnerud, Atle Emblem, Kyrre Eeg |
| author_facet | Liu, Qinghui Fuster-Garcia, Elies Hovden, Ivar Thokle MacIntosh, Bradley J Grødem, Edvard Brandal, Petter Lopez-Mateu, Carles Sederevicius, Donatas Skogen, Karoline Schellhorn, Till Bjørnerud, Atle Emblem, Kyrre Eeg |
| contents | Diffuse gliomas are malignant brain tumors that grow widespread through the brain. The complex interactions between neoplastic cells and normal tissue, as well as the treatment-induced changes often encountered, make glioma tumor growth modeling challenging. In this paper, we present a novel end-to-end network capable of future predictions of tumor masks and multi-parametric magnetic resonance images (MRI) of how the tumor will look at any future time points for different treatment plans. Our approach is based on cutting-edge diffusion probabilistic models and deep-segmentation neural networks. We included sequential multi-parametric MRI and treatment information as conditioning inputs to guide the generative diffusion process as well as a joint segmentation process. This allows for tumor growth estimates and realistic MRI generation at any given treatment and time point. We trained the model using real-world postoperative longitudinal MRI data with glioma tumor growth trajectories represented as tumor segmentation maps over time. The model demonstrates promising performance across various tasks, including generating high-quality multi-parametric MRI with tumor masks, performing time-series tumor segmentations, and providing uncertainty estimates. Combined with the treatment-aware generated MRI, the tumor growth predictions with uncertainty estimates can provide useful information for clinical decision-making. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_05406 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Treatment-aware Diffusion Probabilistic Model for Longitudinal MRI Generation and Diffuse Glioma Growth Prediction Liu, Qinghui Fuster-Garcia, Elies Hovden, Ivar Thokle MacIntosh, Bradley J Grødem, Edvard Brandal, Petter Lopez-Mateu, Carles Sederevicius, Donatas Skogen, Karoline Schellhorn, Till Bjørnerud, Atle Emblem, Kyrre Eeg Image and Video Processing Computer Vision and Pattern Recognition Diffuse gliomas are malignant brain tumors that grow widespread through the brain. The complex interactions between neoplastic cells and normal tissue, as well as the treatment-induced changes often encountered, make glioma tumor growth modeling challenging. In this paper, we present a novel end-to-end network capable of future predictions of tumor masks and multi-parametric magnetic resonance images (MRI) of how the tumor will look at any future time points for different treatment plans. Our approach is based on cutting-edge diffusion probabilistic models and deep-segmentation neural networks. We included sequential multi-parametric MRI and treatment information as conditioning inputs to guide the generative diffusion process as well as a joint segmentation process. This allows for tumor growth estimates and realistic MRI generation at any given treatment and time point. We trained the model using real-world postoperative longitudinal MRI data with glioma tumor growth trajectories represented as tumor segmentation maps over time. The model demonstrates promising performance across various tasks, including generating high-quality multi-parametric MRI with tumor masks, performing time-series tumor segmentations, and providing uncertainty estimates. Combined with the treatment-aware generated MRI, the tumor growth predictions with uncertainty estimates can provide useful information for clinical decision-making. |
| title | Treatment-aware Diffusion Probabilistic Model for Longitudinal MRI Generation and Diffuse Glioma Growth Prediction |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2309.05406 |