González, Camila ; Mukhopadhyay, Anirban (2021)
Self-supervised Out-of-distribution Detection for Cardiac CMR Segmentation.
In: Proceedings of Machine Learning Research, 143
Artikel, Bibliographie
Kurzbeschreibung (Abstract)
The segmentation of cardiac structures in Cine Magnetic Resonance imaging (CMR) plays an important role in monitoring ventricular function, and many deep learning solutions have been introduced that successfully automate this task. Yet due to variabilities in the CMR acquisition process, images from different centers or acquisition protocols differ considerably. This causes deep learning models to fail silently. It is therefore crucial to identify out-of-distribution (OOD) samples for which the trained model is unsuitable. For models with a self-supervised proxy task, we propose a simple method to identify OOD samples that does not require adapting the model architecture or access to a separate OOD dataset during training. As the performance of self-supervised tasks can be assessed without ground truth information, it indicates during test time when a sample differs from the training distribution. The proposed method combines a voxel-wise uncertainty estimate with the self-supervision information. Our approach is validated across three CMR datasets and two different proxy tasks. We find that it is more effective at detecting OOD samples than state-of-the-art post-hoc OOD detection and uncertainty estimation approaches.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2021 |
| Autor(en): | González, Camila ; Mukhopadhyay, Anirban |
| Art des Eintrags: | Bibliographie |
| Titel: | Self-supervised Out-of-distribution Detection for Cardiac CMR Segmentation |
| Sprache: | Englisch |
| Publikationsjahr: | 2021 |
| Verlag: | MLResearch Press |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Proceedings of Machine Learning Research |
| Jahrgang/Volume einer Zeitschrift: | 143 |
| URL / URN: | https://proceedings.mlr.press/v143/gonzalez21a.html |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | The segmentation of cardiac structures in Cine Magnetic Resonance imaging (CMR) plays an important role in monitoring ventricular function, and many deep learning solutions have been introduced that successfully automate this task. Yet due to variabilities in the CMR acquisition process, images from different centers or acquisition protocols differ considerably. This causes deep learning models to fail silently. It is therefore crucial to identify out-of-distribution (OOD) samples for which the trained model is unsuitable. For models with a self-supervised proxy task, we propose a simple method to identify OOD samples that does not require adapting the model architecture or access to a separate OOD dataset during training. As the performance of self-supervised tasks can be assessed without ground truth information, it indicates during test time when a sample differs from the training distribution. The proposed method combines a voxel-wise uncertainty estimate with the self-supervision information. Our approach is validated across three CMR datasets and two different proxy tasks. We find that it is more effective at detecting OOD samples than state-of-the-art post-hoc OOD detection and uncertainty estimation approaches. |
| Zusätzliche Informationen: | Proceedings of the 4th Conference on Medical Imaging with Deep Learning, 07.-09.07.2021, Lübeck,Germany ; until 2017 Journal of machine learning research - Workshop and conference proceedings JMLR W&CP (rebranding to PMLR) |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Graphisch-Interaktive Systeme |
| Hinterlegungsdatum: | 21 Feb 2022 12:07 |
| Letzte Änderung: | 21 Feb 2022 12:07 |
| PPN: | |
| Zugehörige Links: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum