Universität zu Köln

Naji, Hussein ORCID: 0009-0008-0665-233X, Hahn, Paul ORCID: 0009-0009-7708-8040, Pisula, Juan I. ORCID: 0000-0002-6131-8528, Ugliano, Stefano ORCID: 0009-0002-5013-3971, Simon, Adrian ORCID: 0000-0002-2709-863X, Büttner, Reinhard ORCID: 0000-0001-8806-4786 and Bozek, Katarzyna ORCID: 0000-0002-0917-6876 (2025). Deep learning-based interpretable prediction of recurrence of diffuse large B-cell lymphoma. BJC Reports, 3 (1). Springer Nature. ISSN 2731-9377

PDF s44276-025-00147-0.pdf Bereitstellung unter der CC-Lizenz: Creative Commons Attribution. Download (993kB)

Abstract

[Artikel-Nr.: 34] Background: The heterogeneous and aggressive nature of diffuse large B-cell lymphoma (DLBCL) presents significant treatment challenges as up to 50% of patients experience recurrence of disease after chemotherapy. Upfront detection of recurring patients could offer alternative treatments. Deep learning has shown potential in predicting recurrence of various cancer types but suffers from lack of interpretability. Particularly in prediction of recurrence, an understanding of the model’s decision could eventually result in novel treatments. Methods: We developed a deep learning-based pipeline to predict recurrence of DLBCL based on histological images of a publicly available cohort. We utilized attention-based classification to highlight areas within the images that were of high relevance for the model’s classification. Subsequently, we segmented the nuclei within these areas, calculated morphological features, and statistically analyzed them to find differences between recurred and non-recurred patients. Results: We achieved an f1 score of 0.88 indicating that our model can distinguish non-recurred from recurred patients. Additionally, we found that features that are the most predictive of recurrence include large and irregularly shaped tumor cell nuclei. Discussion: Our work underlines the value of histological images in predicting treatment outcomes and enhances our understanding of complex biological processes in aggressive, heterogeneous cancers like DLBCL.

Item Type:	Article
Creators:	Creators Email ORCID ORCID Put Code Naji, Hussein UNSPECIFIED https://orcid.org/0009-0008-0665-233X UNSPECIFIED Hahn, Paul UNSPECIFIED https://orcid.org/0009-0009-7708-8040 UNSPECIFIED Pisula, Juan I. UNSPECIFIED https://orcid.org/0000-0002-6131-8528 UNSPECIFIED Ugliano, Stefano UNSPECIFIED https://orcid.org/0009-0002-5013-3971 UNSPECIFIED Simon, Adrian UNSPECIFIED https://orcid.org/0000-0002-2709-863X UNSPECIFIED Büttner, Reinhard UNSPECIFIED https://orcid.org/0000-0001-8806-4786 UNSPECIFIED Bozek, Katarzyna UNSPECIFIED https://orcid.org/0000-0002-0917-6876 UNSPECIFIED
URN:	urn:nbn:de:hbz:38-801129
Identification Number:	10.1038/s44276-025-00147-0
Journal or Publication Title:	BJC Reports
Volume:	3
Number:	1
Number of Pages:	6
Date:	20 May 2025
Publisher:	Springer Nature
ISSN:	2731-9377
Language:	English
Faculty:	Faculty of Medicine
Divisions:	CECAD - Cluster of Excellence Cellular Stress Responses in Aging-Associated Diseases Faculty of Medicine > Pathologie und Neuropathologie > Institut für Pathologie Faculty of Medicine > Weitere > Institut für Biomedizinische Informatik Zentrum für Molekulare Medizin
Subjects:	Medical sciences Medicine
['eprint_fieldname_oa_funders' not defined]:	Publikationsfonds UzK
Refereed:	Yes
URI:	http://kups.ub.uni-koeln.de/id/eprint/80112