Probabilistic approach to longitudinal response prediction: application to radiomics from brain cancer imaging
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918018351628288 |
|---|---|
| author | Cama, Isabella Piana, Michele Campi, Cristina Garbarino, Sara |
| author_facet | Cama, Isabella Piana, Michele Campi, Cristina Garbarino, Sara |
| contents | Longitudinal imaging analysis tracks disease progression and treatment response over time, providing dynamic insights into treatment efficacy and disease evolution. Radiomic features extracted from medical imaging can support the study of disease progression and facilitate longitudinal prediction of clinical outcomes. This study presents a probabilistic model for longitudinal response prediction, integrating baseline features with intermediate follow-ups. The probabilistic nature of the model naturally allows to handle the instrinsic uncertainty of the longitudinal prediction of disease progression. We evaluate the proposed model against state-of-the-art disease progression models in both a synthetic scenario and using a brain cancer dataset. Results demonstrate that the approach is competitive against existing methods while uniquely accounting for uncertainty and controlling the growth of problem dimensionality, eliminating the need for data from intermediate follow-ups. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_07973 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Probabilistic approach to longitudinal response prediction: application to radiomics from brain cancer imaging Cama, Isabella Piana, Michele Campi, Cristina Garbarino, Sara Applications Artificial Intelligence 62P10 (Primary), 68T09, 92F05 (Secondary) Longitudinal imaging analysis tracks disease progression and treatment response over time, providing dynamic insights into treatment efficacy and disease evolution. Radiomic features extracted from medical imaging can support the study of disease progression and facilitate longitudinal prediction of clinical outcomes. This study presents a probabilistic model for longitudinal response prediction, integrating baseline features with intermediate follow-ups. The probabilistic nature of the model naturally allows to handle the instrinsic uncertainty of the longitudinal prediction of disease progression. We evaluate the proposed model against state-of-the-art disease progression models in both a synthetic scenario and using a brain cancer dataset. Results demonstrate that the approach is competitive against existing methods while uniquely accounting for uncertainty and controlling the growth of problem dimensionality, eliminating the need for data from intermediate follow-ups. |
| title | Probabilistic approach to longitudinal response prediction: application to radiomics from brain cancer imaging |
| topic | Applications Artificial Intelligence 62P10 (Primary), 68T09, 92F05 (Secondary) |
| url | https://arxiv.org/abs/2505.07973 |