RONALD Pipeline: Unsupervised Bronchovascular Bundle Segmentation Outperforms Supervised Deep Learning for Lung Nodule Detection

Paper Overview

• Field: Computer Vision (CV)
• Authors: Anna Mrukwa, Marek Socha, Aleksandra Suwalska et al. (12 authors)
• Published: 2026-08-17
• arXiv: 2608.16855

Key Points

Background

• Lung cancer remains the deadliest cancer worldwide because it is often diagnosed too late; effective treatment depends on detection at an early screening stage.
• Growing patient numbers and a limited radiologist workforce lead to prolonged diagnostic waiting times.
• In very early-stage lung cancer, nodule visibility is further reduced by adjacent blood vessels and airway walls, since nodules are often connected to or supplied by these structures.
• Task-specific analysis of the bronchovascular bundle is therefore important for efficient nodule detection, and its removal can increase the diagnostic potential of lung cancer screening.

Materials and Methods

• The authors evaluated the proposed method on series from widely utilized LDCT datasets, including the Duke Lung Cancer Screening (DLCS) dataset and the Pomeranian lung cancer screening pilot project.
• The proposed RONALD pipeline runs on CT images and returns binary masks of vessels and bronchi located within the lung parenchyma.

Results

• The pipeline segments the bronchovascular bundle in LDCT scans while improving nodule retention rates:
• DLCS: improved from 93.98% and 90.36% to 100%
• Pomeranian dataset: improved from 83.16% and 62.36% to 99.92%

Conclusion

• The resulting segmentations can improve pulmonary nodule detection in very early-stage lung cancer, and the title suggests unsupervised methods can outperform supervised deep learning when ground-truth constraints are absent.

*Auto-collected on 2026-08-19*