Benutzer: Gast  Login
Titel:

Deep Quality Estimation: Creating Surrogate Models for Human Quality Ratings

Dokumenttyp:
Proceedings Paper
Autor(en):
Kofler, Florian; Ezhov, Ivan; Fidon, Lucas; Horvath, Izabela; de la Rosa, Ezequiel; LaMaster, John; Li, Hongwei; Finck, Tom; Shit, Suprosanna; Paetzold, Johannes; Bakas, Spyridon; Piraud, Marie; Kirschke, Jan; Vercauteren, Tom; Zimmer, Claus; Wiestler, Benedikt; Menze, Bjoern
Abstract:
Human ratings are abstract representations of segmentation quality. To approximate human quality ratings on scarce expert data, we train surrogate quality estimation models. We evaluate on a complex multi-class segmentation problem, specifically glioma segmentation, following the BraTS annotation protocol. The training data features quality ratings from 15 expert neuroradiologists on a scale ranging from 1 to 6 stars for various computer-generated and manual 3D annotations. Even though the netwo...     »
Zeitschriftentitel:
Med Image Comput Comput Assist Interv Int Conf Med Image Comput Comput Assist Interv
Jahr:
2023
Band / Volume:
13769
Seitenangaben Beitrag:
3-13
Volltext / DOI:
doi:10.1007/978-3-031-33842-7_1
Print-ISSN:
0302-9743
TUM Einrichtung:
Professur für AI for Image-Guided Diagnosis and Therapy (Prof. Wiestler)
 BibTeX