EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Deep Learning‐Based Classification of Pulmonary Hypertension Using Early‐Fused CTPA and Pulmonary Artery Segmentation Maps

Shoubo Hu iD, Mengyuan Li, Mu Li, Chi Zhang iD, Sheng Xie iD, Yue Lin iD, Deyu Li, Jin She

Pulmonary Circulation · 2026-10 · 16 (4)

DOI: 10.1002/pul2.70456 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pulmonary Circulation, online erschienen am 15.11.2026. Verfasst von Shoubo Hu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Beijing Advanced Innovation Center for Biomedical Engineering School of Biological Science and Medical Engineering, Beihang University Beijing China. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: State Key Laboratory of Virtual Reality Technology and Systems.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Computed tomography pulmonary angiography (CTPA) is vital for diagnosing pulmonary hypertension (PH), especially thromboembolic pulmonary hypertension (CTEPH). However, manual image interpretation of CTPA often leads to misdiagnosis. This study aims to automatically segment the pulmonary artery from CTPA images and develop a deep learning model by fusing CTPA images with pulmonary artery segmentation results to distinguish pulmonary hypertension (PH vs. subjects without PH (no‐PH)) and its PH subtype, CTEPH (CTEPH, other PH vs. no‐PH). The study included 92 patients with CTEPH, 85 patients with other types of PH, and 140 no‐PH. We completed the image preprocessing and segmentation of the pulmonary arterial tree of all the sample data. Based on four deep learning model classifiers—ResNet50, DenseNet, SENet, and Swin Transformer, we respectively developed four distinct network architectures: Single input channel for CTPA images, as well as early, middle, and late fusion strategies that combine CTPA images with their corresponding pulmonary vascular segmentation maps. The performance of the testing experiments has shown that the DenseNet (CTPA‐seg) early fusion model achieves optimal performance in the binary classification task of pulmonary hypertension (PH vs. no‐PH), with an area under the curve (AUC) of 0.927. Meanwhile, the Swin Transformer (CTPA‐seg) early fusion model shows the best performance in the ternary classification of pulmonary hypertension subtypes (CTEPH, other PH vs. no‐PH), achieving an AUC of 0.855. Compared with models that only use clinical images, the early feature fusion strategy shows significantly higher accuracy in classifying and diagnosing PH, which is beneficial for the differential diagnosis of CTEPH.

Schlagwörter

Stichwörter der Autor:innen

CTEPHCTPAdeep learningpulmonary hypertensionpulmonary vascular segmentation

Autor:innen und Institutionen

  • Beijing Advanced Innovation Center for Biomedical Engineering School of Biological Science and Medical Engineering, Beihang University Beijing China.
  • State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China.
  • Department of Radiology China-Japan Friendship Hospital Beijing China.
  • The First College of Clinical Medical Science China Three Gorges University & Yichang Central People's Hospital Yichang China.

ORCID-Profile: Shoubo Hu, Chi Zhang, Sheng Xie, Yue Lin

Förderung

  • State Key Laboratory of Virtual Reality Technology and Systems

Zitieren

APA

Hu, S., Li, M., Li, M., Zhang, C., Xie, S., Lin, Y., Li, D., & She, J. (2026). Deep Learning‐Based Classification of Pulmonary Hypertension Using Early‐Fused CTPA and Pulmonary Artery Segmentation Maps. Pulmonary Circulation, 16(4). https://doi.org/10.1002/pul2.70456

Vancouver

Hu S, Li M, Li M, Zhang C, Xie S, Lin Y, et al. Deep Learning‐Based Classification of Pulmonary Hypertension Using Early‐Fused CTPA and Pulmonary Artery Segmentation Maps. Pulmonary Circulation. 2026;16(4). doi:10.1002/pul2.70456

BibTeX
@article{Hu2026,
  author = {Hu, Shoubo and Li, Mengyuan and Li, Mu and Zhang, Chi and Xie, Sheng and Lin, Yue and Li, Deyu and She, Jin},
  title = {Deep Learning‐Based Classification of Pulmonary Hypertension Using Early‐Fused CTPA and Pulmonary Artery Segmentation Maps},
  journal = {Pulmonary Circulation},
  year = {2026},
  volume = {16},
  number = {4},
  doi = {10.1002/pul2.70456}
}
Kostenlos starten →