<div class="csl-bib-body">
<div class="csl-entry">Zhang, H., Xu, Z., Yao, D., Zhang, S., Chen, J., & Thomas Lukasiewicz. (2023). Multi-Head Feature Pyramid Networks for Breast Mass Detection. In <i>ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes, Greece. IEEE. https://doi.org/10.1109/ICASSP49357.2023.10095967</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/192513
-
dc.description.abstract
Analysis of X-ray images is one of the main tools to diagnose breast cancer. The ability to quickly and accurately detect the location of masses from the huge amount of image data is the key to reducing the morbidity and mortality of breast cancer. Currently, the main factor limiting the accuracy of breast mass detection is the unequal focus on the mass boxes, leading the network to focus too much on larger masses at the expense of smaller ones. In the paper, we propose the multi-head feature pyramid module (MHFPN) to solve the problem of unbalanced focus of target boxes during feature map fusion and design a multi-head breast mass detection network (MBMDnet). Experimental studies show that, comparing to the SOTA detection baselines, our method improves by 6.58% (in AP@50) and 5.4% (in TPR@50) on the commonly used IN-breast dataset, while about 6-8% improvements (in AP@20) are also observed on the public MIAS and BCS-DBT datasets.
en
dc.language.iso
en
-
dc.subject
Breast Mass Detection
en
dc.subject
Feature Pyramid Networks
en
dc.subject
Multi-head Integration
en
dc.subject
Faster RCNN
en
dc.title
Multi-Head Feature Pyramid Networks for Breast Mass Detection
en
dc.type
Inproceedings
en
dc.type
Konferenzbeitrag
de
dc.relation.publication
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
-
dc.contributor.affiliation
Hebei University of Technology, China
-
dc.contributor.affiliation
Hebei University of Technology, China
-
dc.contributor.affiliation
Hebei University of Technology, China
-
dc.contributor.affiliation
Hebei University of Technology, China
-
dc.contributor.affiliation
Shenzhen University, China
-
dc.relation.isbn
978-1-7281-6327-7
-
dc.relation.doi
10.1109/ICASSP49357.2023
-
dc.relation.issn
1520-6149
-
dc.type.category
Full-Paper Contribution
-
dc.relation.eissn
2379-190X
-
tuw.booktitle
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)