Can Unsupervised Methods Outperform Supervised Deep Learning When Ground Truth Is Sparse? A Case Study of Bronchovascular Bundle Segmentation in Low-Dose CT

2026-08-17

AI Summary

This study addresses the challenge of missed pulmonary nodule detection caused by difficult bronchovascular bundle segmentation in low-dose CT. We propose RONALD, a multi-stage pipeline incorporating lung lobe and mediastinum preprocessing alongside independent vessel and bronchus segmentation strategies. Notably, this approach demonstrates that unsupervised methods outperform supervised learning in ground-truth-sparse scenarios. Experimental results indicate that RONALD significantly enhances early lung cancer screening efficacy, achieving nodule retention rates of 100% and 99.92% on the DLCS and Pomeranian datasets, respectively. Consequently, this framework effectively resolves precise segmentation difficulties within complex anatomical structures, ensuring robust nodule preservation during automated analysis.

Abstract

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. However, the growing number of patients and the limited number of radiologists lead to prolonged diagnostic waiting times. In very early stage lung cancer, nodule visibility is further reduced by adjacent blood vessels and airway walls, because 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 To assess the efficacy of the proposed method, we used series from widely utilized LDCT datasets, including the Duke Lung Cancer Screening (DLCS) dataset and the Pilot Pomeranian Lung Cancer Screening Program. The proposed bronchovascular bundle segmentation pipeline, RONALD, operates on computed tomography images and returns binary masks of vessels and bronchi located in the lung parenchyma. The method includes a preprocessing stage with lung, lobe, and mediastinum segmentation, followed by separate vessel and bronchial tree segmentation. Results The proposed pipeline segmented the bronchovascular bundle in low-dose computed tomography scans while improving nodule retention compared with other segmentation methods: from 93.98% and 90.36% to 100% in DLCS, and from 83.16% and 62.36% to 99.92% in the Pomeranian dataset. Conclusion The resulting segmentations can improve lung nodule detection in the very early stages of lung cancer.

Problem

• Bronchovascular Bundle Segmentation
• Low-Dose CT
• Lung Nodule Detection
• Sparse Ground Truth
• Early Lung Cancer Screening

Innovation

• Unsupervised Segmentation
• Bronchovascular Bundle
• Low-Dose CT
• Nodule Retention
• RONALD