Malmö University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A topology-aware visual fusion framework for patient-level emphysema classification from chest CT images
Department of Radiology, Firat University Faculty of Medicine, Elazıg, Türkiye.
Department of Artificial Intelligence and Data Engineering, Firat University, Elazig, Türkiye.
Department of Software Engineering, Technology Faculty, Firat University, Elazig, Türkiye.
Department of Radiology, Firat University Faculty of Medicine, Elazig, Türkiye.
Show others and affiliations
2026 (English)In: Array, E-ISSN 2590-0056, Vol. 32, article id 101372Article in journal (Refereed) Published
Abstract [en]

Emphysema classification from chest computed tomography (CT) remains challenging because disease-related abnormalities involve both visual appearance and structural disruption of the lung parenchyma. We propose a patient-level visual-topological deep learning framework for emphysema classification from a single 2D chest CT image per patient. A newly curated single-center dataset of 1108 anonymized chest CT images was collected in collaboration with expert radiologists. Each image corresponded to a unique patient and was labeled as normal, panlobular emphysema, paraseptal emphysema, or centroacinar emphysema. The framework integrates DINOv2-derived visual embeddings with persistent-homology-derived Betti-curve descriptors using a topology-guided cross-attention fusion module. On the held-out patient-level test set, the model achieved a macro F1-score of 0.9269 and a one-vs-rest ROC-AUC of 0.9830 for four-class classification. In the binary normal-vs-emphysema task, it achieved an ROC-AUC of 0.9942 and a PR-AUC of 0.9976. Stratified ten-fold patient-level cross-validation further confirmed the robustness of the proposed framework, yielding a mean macro F1-score of 0.9217 ± 0.0360 and a mean one-vs-rest ROC-AUC of 0.9917 ± 0.0054 for four-class emphysema classification. Ablation experiments showed that Betti-curve features were independently discriminative and that their integration with a topology encoder and cross-attention fusion improved performance over the DINOv2 image-only baseline on the same patient-level split. These results indicate that combining DINOv2 embeddings with Betti-curve descriptors yields complementary gains for patient-level emphysema subtype recognition. The anonymized dataset and source code are available at: https: //github.com/muhammedtalo/Emphysema.

Place, publisher, year, edition, pages
Elsevier B.V. , 2026. Vol. 32, article id 101372
Keywords [en]
Betti curves, Deep learning, Emphysema, Topological data analysis, Visual–topological fusion
National Category
Radiology and Medical Imaging
Identifiers
URN: urn:nbn:se:mau:diva-88847DOI: 10.1016/j.array.2026.101372ISI: 001917305800001Scopus ID: 2-s2.0-105054138914OAI: oai:DiVA.org:mau-88847DiVA, id: diva2:2115240
Available from: 2026-11-04 Created: 2026-11-04 Last updated: 2026-11-09Bibliographically approved

Open Access in DiVA

fulltext(15873 kB)35 downloads
File information
File name FULLTEXT01.pdfFile size 15873 kBChecksum SHA-512
03391bd171ac84a0b9e1660717b52014abadf4dd222c66d9939dfcda858d973702af5a64e2ad2bb7752875071afab779a27f9201928ce34afb75cf435af0f5a2
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Akin, Erdal

Search in DiVA

By author/editor
Karaduman, MucahitTumen, VedatAkin, Erdal
By organisation
Department of Computer Science and Media Technology (DVMT)Sustainable Digitalisation Research Centre (SDRC)Biofilms Research Centre for Biointerfaces (BRCB)
In the same journal
Array
Radiology and Medical Imaging

Search outside of DiVA

GoogleGoogle Scholar
Total: 35 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 123 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf