{"ID":2855497,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.13886","arxiv_id":"2510.13886","title":"Physics-Informed autoencoder for DSC-MRI Perfusion post-processing: application to glioma grading","abstract":"DSC-MRI perfusion is a medical imaging technique for diagnosing and prognosing brain tumors and strokes. Its analysis relies on mathematical deconvolution, but noise or motion artifacts in a clinical environment can disrupt this process, leading to incorrect estimate of perfusion parameters. Although deep learning approaches have shown promising results, their calibration typically rely on third-party deconvolution algorithms to generate reference outputs and are bound to reproduce their limitations. To adress this problem, we propose a physics-informed autoencoder that leverages an analytical model to decode the perfusion parameters and guide the learning of the encoding network. This autoencoder is trained in a self-supervised fashion without any third-party software and its performance is evaluated on a database with glioma patients. Our method shows reliable results for glioma grading in accordance with other well-known deconvolution algorithms despite a lower computation time. It also achieved competitive performance even in the presence of high noise which is critical in a medical environment.","short_abstract":"DSC-MRI perfusion is a medical imaging technique for diagnosing and prognosing brain tumors and strokes. Its analysis relies on mathematical deconvolution, but noise or motion artifacts in a clinical environment can disrupt this process, leading to incorrect estimate of perfusion parameters. Although deep learning appr...","url_abs":"https://arxiv.org/abs/2510.13886","url_pdf":"https://arxiv.org/pdf/2510.13886v1","authors":"[\"Pierre Fayolle\",\"Alexandre Bône\",\"Noëlie Debs\",\"Mathieu Naudin\",\"Pascal Bourdon\",\"Remy Guillevin\",\"David Helbert\"]","published":"2025-10-14T02:39:55Z","proceeding":"q-bio.QM","tasks":"[\"q-bio.QM\",\"cs.AI\",\"eess.IV\",\"eess.SP\"]","methods":"[]","has_code":false}