EUVIMEDDécouvrir EUVIMED
Open access · CC BY 4.0

A topology-aware visual fusion framework for patient-level emphysema classification from chest CT images

Yesim Eroglu, Muhammed Yildirim, Oguzhan Katar, Esra Yildirim, Mucahit Karaduman, Vedat Tumen, Muhammed Talo, Erdal Akin, Ozal Yildirim, U. Rajendra Acharya

Array · 2026-12 · 32 · 101372

DOI: 10.1016/j.array.2026.101372 ↗

At a glance

Journal article in Array, 2026-12. Written by Yesim Eroglu and 9 co-authors. 39 references. The full text is freely available (open access, CC BY 4.0).

RésuméRéférences bibliographiquesCiteRelated studies

Abstract (original language)

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 .

Cite

APA

Eroglu, Y., Yildirim, M., Katar, O., Yildirim, E., Karaduman, M., Tumen, V., Talo, M., Akin, E., Yildirim, O., & Acharya, U. R. (2026). A topology-aware visual fusion framework for patient-level emphysema classification from chest CT images. Array, 32, 101372. https://doi.org/10.1016/j.array.2026.101372

Vancouver

Eroglu Y, Yildirim M, Katar O, Yildirim E, Karaduman M, Tumen V, et al. A topology-aware visual fusion framework for patient-level emphysema classification from chest CT images. Array. 2026;32:101372. doi:10.1016/j.array.2026.101372

BibTeX
@article{Eroglu2026,
  author = {Eroglu, Yesim and Yildirim, Muhammed and Katar, Oguzhan and Yildirim, Esra and Karaduman, Mucahit and Tumen, Vedat and Talo, Muhammed and Akin, Erdal and Yildirim, Ozal and Acharya, U. Rajendra},
  title = {A topology-aware visual fusion framework for patient-level emphysema classification from chest CT images},
  journal = {Array},
  year = {2026},
  volume = {32},
  pages = {101372},
  doi = {10.1016/j.array.2026.101372}
}
Start for free →