Multi-scale and multi-view network for lung tumor segmentation

• Published in: Computers in biology and medicine 2024-04, Vol.172, p.108250-108250, Article 108250
• Main Authors: Liu, Caiqi, Liu, Han, Zhang, Xuehui, Guo, Jierui, Lv, Pengju
• Format: Article
• Language: English
• Subjects: Ablation; Biology; Computed tomography; Datasets; Deep learning; Deep supervision; Feature extraction; Image enhancement; Image segmentation; Lung cancer; Lung tumor segmentation; Medical imaging; Multi-scale and multi-view; Oncology; Segmentation; Supervision; Tomography; Tumors
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.108250

Lung tumor segmentation in medical imaging is a critical step in the diagnosis and treatment planning for lung cancer. Accurate segmentation, however, is challenging due to the variability in tumor size, shape, and contrast against surrounding tissues. In this work, we present MSMV-Net, a novel deep learning architecture that integrates multi-scale multi-view (MSMV) learning modules and multi-scale uncertainty-based deep supervision (MUDS) for enhanced segmentation of lung tumors in computed tomography images. MSMV-Net capitalizes on the strengths of multi-view analysis and multi-scale feature extraction to address the limitations posed by small 3D lung tumors. The results indicate that MSMV-Net achieves state-of-the-art performance in lung tumor segmentation, recording a global Dice score of 55.60% on the LUNA dataset and 59.94% on the MSD dataset. Ablation studies conducted on the MSD dataset further validate that our method enhances segmentation accuracy. •A novel multi-scale and multi-view network for lung tumor segmentation.•The proposed MSMV and MUDS modules show powerful abilities in learning.•Comprehensive evaluation on the wide range of public 3D lung tumor datasets.