Benutzer: Gast  Login
Titel:

Weakly Supervised Object Detection in Chest X-Rays with Differentiable ROI Proposal Networks and Soft ROI Pooling.

Dokumenttyp:
Journal Article
Autor(en):
Muller, Philip; Meissen, Felix; Kaissis, Georgios; Rueckert, Daniel
Abstract:
Weakly supervised object detection (WSup-OD) increases the usefulness and interpretability of image classification algorithms without requiring additional supervision. The successes of multiple instance learning in this task for natural images, however, do not translate well to medical images due to the very different characteristics of their objects (i.e. pathologies). In this work, we propose Weakly Supervised ROI Proposal Networks (WSRPN), a new method for generating bounding box proposals on...     »
Zeitschriftentitel:
IEEE Trans Med Imaging
Jahr:
2024
Band / Volume:
PP
Volltext / DOI:
doi:10.1109/TMI.2024.3435015
PubMed:
http://view.ncbi.nlm.nih.gov/pubmed/39073999
Print-ISSN:
0278-0062
TUM Einrichtung:
Institut für Diagnostische und Interventionelle Radiologie (Prof. Makowski); Institut für KI und Informatik in der Medizin (Prof. Rückert)
 BibTeX