% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Chatterjee:286092,
author = {Chatterjee, Soumick and Yassin, Hadya and Dubost, Florian
and Nürnberger, Andreas and Speck, Oliver},
title = {{W}eakly-supervised segmentation using
inherently-explainable classification models and their
application to brain tumour classification},
journal = {Neurocomputing},
volume = {682},
issn = {0925-2312},
address = {Amsterdam},
publisher = {Elsevier},
reportid = {DZNE-2026-00388},
pages = {133460},
year = {2026},
abstract = {Deep learning has demonstrated significant potential in
medical imaging; however, the opacity of “black-box”
models hinders clinical trust, while segmentation tasks
typically necessitate laborious, hard-to-obtain pixel-wise
annotations. To address these challenges simultaneously,
this paper introduces a framework for three inherently
explainable classifiers (GP-UNet, GP-ShuffleUNet, and
GP-ReconResNet). By integrating a global pooling mechanism,
these networks generate localisation heatmaps that directly
influence classification decisions, offering inherent
interpretability without relying on potentially unreliable
post-hoc methods. These heatmaps are subsequently
thresholded to achieve weakly-supervised segmentation,
requiring only image-level classification labels for
training. Validated on two datasets for multi-class brain
tumour classification, the proposed models achieved a peak
F1-score of 0.93. For the weakly-supervised segmentation
task, a median Dice score of 0.728 $(95\%$ CI:
0.715–0.739) was recorded. Notably, on a subset of
tumour-only images, the best model achieved an accuracy of
$98.7\%,$ outperforming state-of-the-art glioma grading
binary classifiers. Furthermore, comparative
Precision-Recall analysis validated the framework’s
robustness against severe class imbalance, establishing a
direct correlation between diagnostic confidence and
segmentation fidelity. These results demonstrate that the
proposed framework successfully combines high diagnostic
accuracy with essential transparency, offering a promising
direction for trustworthy clinical decision support.},
cin = {AG Speck},
ddc = {610},
cid = {I:(DE-2719)1340009},
pnm = {353 - Clinical and Health Care Research (POF4-353)},
pid = {G:(DE-HGF)POF4-353},
typ = {PUB:(DE-HGF)16},
doi = {10.1016/j.neucom.2026.133460},
url = {https://pub.dzne.de/record/286092},
}