González, Camila ; Harder, Christian L. ; Ranem, Amin ; Fischbach, Ricarda ; Kaltenborn, Isabel J. ; Dadras, Armin ; Bucher, Andreas M. ; Mukhopadhyay, Anirban (2022)
Quality Monitoring of Federated Covid-19 Lesion Segmentation.
Bildverarbeitung für die Medizin 2022. Heidelberg, Germany (26.-28.06.2022)
doi: 10.1007/978-3-658-36932-3_8
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Federated Learning is the most promising way to train robust Deep Learning models for the segmentation of Covid-19-related findings in chest CTs. By learning in a decentralized fashion, heterogeneous data can be leveraged from a variety of sources and acquisition protocols whilst ensuring patient privacy. It is, however, crucial to continuously monitor the performance of the model. Yet when it comes to the segmentation of diffuse lung lesions, a quick visual inspection is not enough to assess the quality, and thorough monitoring of all network outputs by expert radiologists is not feasible. In this work, we present an array of lightweight metrics that can be calculated locally in each hospital and then aggregated for central monitoring of a federated system. Our linear model detects over 70% of low-quality segmentations on an out-of-distribution dataset and thus reliably signals a decline in model performance.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | González, Camila ; Harder, Christian L. ; Ranem, Amin ; Fischbach, Ricarda ; Kaltenborn, Isabel J. ; Dadras, Armin ; Bucher, Andreas M. ; Mukhopadhyay, Anirban |
| Art des Eintrags: | Bibliographie |
| Titel: | Quality Monitoring of Federated Covid-19 Lesion Segmentation |
| Sprache: | Englisch |
| Publikationsjahr: | 5 April 2022 |
| Verlag: | Springer |
| Buchtitel: | Bildverarbeitung für die Medizin 2022: Proceedings, German Workshop on Medical Image Computing |
| Reihe: | Informatik aktuell |
| Veranstaltungstitel: | Bildverarbeitung für die Medizin 2022 |
| Veranstaltungsort: | Heidelberg, Germany |
| Veranstaltungsdatum: | 26.-28.06.2022 |
| DOI: | 10.1007/978-3-658-36932-3_8 |
| Kurzbeschreibung (Abstract): | Federated Learning is the most promising way to train robust Deep Learning models for the segmentation of Covid-19-related findings in chest CTs. By learning in a decentralized fashion, heterogeneous data can be leveraged from a variety of sources and acquisition protocols whilst ensuring patient privacy. It is, however, crucial to continuously monitor the performance of the model. Yet when it comes to the segmentation of diffuse lung lesions, a quick visual inspection is not enough to assess the quality, and thorough monitoring of all network outputs by expert radiologists is not feasible. In this work, we present an array of lightweight metrics that can be calculated locally in each hospital and then aggregated for central monitoring of a federated system. Our linear model detects over 70% of low-quality segmentations on an out-of-distribution dataset and thus reliably signals a decline in model performance. |
| Zusätzliche Informationen: | German Workshop on Medical Image Computing |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Graphisch-Interaktive Systeme |
| Hinterlegungsdatum: | 15 Jun 2023 07:49 |
| Letzte Änderung: | 05 Mär 2024 10:09 |
| PPN: | 516005979 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum