EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Diagnosis of Lung Cancer Using Endobronchial Ultrasonography Image Based on Multi-Scale Image and Multi-Feature Fusion Framework

Huitao Wang iD, Takahiro Nakajima iD, Kohei Shikano iD, Yukihiro Nomura iD, Toshiya Nakaguchi iD

Tomography · 2025

DOI: 10.3390/tomography11030024 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Tomography, 2025. Verfasst von Huitao Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Engineering, Graduate School of Science and Engineering, Chiba University, Chiba 263-8522, Japan. Hauptthemen laut MEDLINE: Lung Neoplasms, Endosonography, Diagnosis, Computer-Assisted, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Lung cancer is the leading cause of cancer-related deaths globally and ranks among the most common cancer types. Given its low overall five-year survival rate, early diagnosis and timely treatment are essential to improving patient outcomes. In recent years, advances in computer technology have enabled artificial intelligence to make groundbreaking progress in imaging-based lung cancer diagnosis. The primary aim of this study is to develop a computer-aided diagnosis (CAD) system for lung cancer using endobronchial ultrasonography (EBUS) images and deep learning algorithms to facilitate early detection and improve patient survival rates. We propose M3-Net, which is a multi-branch framework that integrates multiple features through an attention-based mechanism, enhancing diagnostic performance by providing more comprehensive information for lung cancer assessment. The framework was validated on a dataset of 95 patient cases, including 13 benign and 82 malignant cases. The dataset comprises 1140 EBUS images, with 540 images used for training, and 300 images each for the validation and test sets. The evaluation yielded the following results: accuracy of 0.76, F1-score of 0.75, AUC of 0.83, PPV of 0.80, NPV of 0.75, sensitivity of 0.72, and specificity of 0.80. These findings indicate that the proposed attention-based multi-feature fusion framework holds significant potential in assisting with lung cancer diagnosis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Lung NeoplasmsEndosonographyDiagnosis, Computer-AssistedImage Interpretation, Computer-AssistedHumansMaleFemaleDeep LearningMiddle AgedSensitivity and SpecificityAgedAlgorithmsLungEarly Detection of Cancer

Stichwörter der Autor:innen

convolutional neural networkdeep learningendobronchial ultrasonography (EBUS)lung cancermulti-feature fusionmulti-scale image

Autor:innen und Institutionen

  • Department of Medical Engineering, Graduate School of Science and Engineering, Chiba University, Chiba 263-8522, Japan.
  • Department of General Thoracic Surgery, Dokkyo Medical University, Mibu 321-0293, Japan.
  • Department of Respirology, Graduate School of Medicine, Chiba University, Chiba 260-8670, Japan.
  • Center for Frontier Medical Engineering, Chiba University, Chiba 263-8522, Japan.

ORCID-Profile: Huitao Wang, Takahiro Nakajima, Kohei Shikano, Yukihiro Nomura, Toshiya Nakaguchi

Zitieren

APA

Wang, H., Nakajima, T., Shikano, K., Nomura, Y., & Nakaguchi, T. (2025). Diagnosis of Lung Cancer Using Endobronchial Ultrasonography Image Based on Multi-Scale Image and Multi-Feature Fusion Framework. Tomography. https://doi.org/10.3390/tomography11030024

Vancouver

Wang H, Nakajima T, Shikano K, Nomura Y, Nakaguchi T. Diagnosis of Lung Cancer Using Endobronchial Ultrasonography Image Based on Multi-Scale Image and Multi-Feature Fusion Framework. Tomography. 2025. doi:10.3390/tomography11030024

BibTeX
@article{Wang2025,
  author = {Wang, Huitao and Nakajima, Takahiro and Shikano, Kohei and Nomura, Yukihiro and Nakaguchi, Toshiya},
  title = {Diagnosis of Lung Cancer Using Endobronchial Ultrasonography Image Based on Multi-Scale Image and Multi-Feature Fusion Framework},
  journal = {Tomography},
  year = {2025},
  doi = {10.3390/tomography11030024}
}
Kostenlos starten →