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 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a computer method called RONALD that helps separate blood vessels and airways from lung tissue in CT scans. This makes tiny lung nodules, which are early signs of lung cancer, easier to spot because these nodules are often hidden near vessels and airways. They tested their method on two lung cancer scan datasets and found it kept more nodules visible compared to other methods. Their approach could help doctors detect lung cancer earlier by improving image analysis.
lung cancerlung nodulescomputed tomography (CT)bronchovascular bundlesegmentationlow-dose CT (LDCT)lung parenchymamedical image processingearly cancer detectionradiology
Authors
Anna Mrukwa, Marek Socha, Aleksandra Suwalska, Agata Durawa, Malgorzata Jelitto, Katarzyna Dziadziuszko, Edyta Szurowska, Pawel Bozek, Michal Marczyk, Witold Rzyman, Rafal Dziadziuszko, Joanna Polanska
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.