Journal Article

DZNE-2026-00388

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Weakly-supervised segmentation using inherently-explainable classification models and their application to brain tumour classification

Chatterjee, S. ; Yassin, H. ; Dubost, F. ; Nürnberger, A. ; Speck, O. (Last author)DZNE*

2026
Elsevier Amsterdam

This record in other databases:  

Please use a persistent id in citations: doi:10.1016/j.neucom.2026.133460

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.

---

Contributing Institute(s):

1. Linking Imaging Projects (AG Speck)

Research Program(s):

1. 353 - Clinical and Health Care Research (POF4-353) (POF4-353)

---

Database coverage:
; Clarivate Analytics Master Journal List ; Current Contents - Engineering, Computing and Technology ; Ebsco Academic Search ; Essential Science Indicators ; IF >= 5 ; JCR ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection

---