Gonzalez, Camila ; Gotkowski, Karol ; Bucher, Andreas ; Fischbach, Ricarda ; Kaltenborn, Isabel ; Mukhopadhyay, Anirban (2021)
Detecting When Pre-trained nnU-Net Models Fail Silently for Covid-19 Lung Lesion Segmentation.
24th International Conference on Medical Image Computing and Computer-Assisted Intervention. Strasbourg, France (27.09.2021-01.10.2021)
doi: 10.1007/978-3-030-87234-2_29
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Automatic segmentation of lung lesions in computer tomography has the potential to ease the burden of clinicians during the Covid-19 pandemic. Yet predictive deep learning models are not trusted in the clinical routine due to failing silently in out-of-distribution (OOD) data. We propose a lightweight OOD detection method that exploits the Mahalanobis distance in the feature space. The proposed approach can be seamlessly integrated into state-of-the-art segmentation pipelines without requiring changes in model architecture or training procedure, and can therefore be used to assess the suitability of pre-trained models to new data. We validate our method with a patch-based nnU-Net architecture trained with a multi-institutional dataset and find that it effectively detects samples that the model segments incorrectly.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2021 |
| Autor(en): | Gonzalez, Camila ; Gotkowski, Karol ; Bucher, Andreas ; Fischbach, Ricarda ; Kaltenborn, Isabel ; Mukhopadhyay, Anirban |
| Art des Eintrags: | Bibliographie |
| Titel: | Detecting When Pre-trained nnU-Net Models Fail Silently for Covid-19 Lung Lesion Segmentation |
| Sprache: | Englisch |
| Publikationsjahr: | 2021 |
| Verlag: | Springer |
| Buchtitel: | Medical Image Computing and Computer Assisted Intervention - MICCAI 2021 |
| Reihe: | Lecture Notes in Computer Science |
| Band einer Reihe: | 12907 |
| Veranstaltungstitel: | 24th International Conference on Medical Image Computing and Computer-Assisted Intervention |
| Veranstaltungsort: | Strasbourg, France |
| Veranstaltungsdatum: | 27.09.2021-01.10.2021 |
| DOI: | 10.1007/978-3-030-87234-2_29 |
| Kurzbeschreibung (Abstract): | Automatic segmentation of lung lesions in computer tomography has the potential to ease the burden of clinicians during the Covid-19 pandemic. Yet predictive deep learning models are not trusted in the clinical routine due to failing silently in out-of-distribution (OOD) data. We propose a lightweight OOD detection method that exploits the Mahalanobis distance in the feature space. The proposed approach can be seamlessly integrated into state-of-the-art segmentation pipelines without requiring changes in model architecture or training procedure, and can therefore be used to assess the suitability of pre-trained models to new data. We validate our method with a patch-based nnU-Net architecture trained with a multi-institutional dataset and find that it effectively detects samples that the model segments incorrectly. |
| Zusätzliche Informationen: | Proceedings, Part VII |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Graphisch-Interaktive Systeme |
| Hinterlegungsdatum: | 16 Feb 2022 08:25 |
| Letzte Änderung: | 16 Feb 2022 08:25 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum