PuSH - Publikationsserver des Helmholtz Zentrums München

Müller, P.* ; Meissen, F.* ; Kaissis, G. ; Rueckert, D.*

Weakly supervised object detection in chest X-rays with differentiable ROI proposal networks and soft ROI pooling.

IEEE Trans. Med. Imaging, DOI: 10.1109/TMI.2024.3435015 (2024)
Postprint DOI
Open Access Green
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 the fly using a specialized region of interest-attention (ROI-attention) module. WSRPN integrates well with classic backbone-head classification algorithms and is end-to-end trainable with only image-label supervision. We experimentally demonstrate that our new method outperforms existing methods in the challenging task of disease localization in chest X-ray images. Code: https://anonymous.4open.science/r/WSRPN-DCA1.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Korrespondenzautor
Schlagwörter Biomedical Imaging ; Chest X-ray ; Image Edge Detection ; Location Awareness ; Object Detection ; Object Detection ; Pathology Detection ; Proposals ; Task Analysis ; Weak Supervision ; X-ray Imaging
ISSN (print) / ISBN 0278-0062
e-ISSN 1558-254X
Zeitschrift IEEE Transactions on Medical Imaging
Verlag Institute of Electrical and Electronics Engineers (IEEE)
Verlagsort New York, NY [u.a.]
Nichtpatentliteratur Publikationen
Begutachtungsstatus Peer reviewed
Institut(e) Institute for Machine Learning in Biomed Imaging (IML)