Node-U-Net: A Lightweight Attention-Guided Network for Pulmonary Nodule Segmentation.
Authors
Affiliations (3)
Affiliations (3)
- Biruni University Faculty of Engineering and Natural Sciences, Department of Biomedical Engineering, Istanbul, Turkey. [email protected].
- Beykent University Faculty of Architecture and Engineering, Department of Biomedical Engineering, Istanbul, Turkey.
- Biruni University Faculty of Engineering and Natural Sciences, Department of Computer Engineering, Istanbul, Turkey.
Abstract
Lung cancer survival relies heavily on early nodule detection via computed tomography (CT), yet manual segmentation remains labor-intensive and unscalable for large clinical workflows. While existing deep learning models achieve high accuracy, they face a critical trade-off with computational efficiency and frequently lack cross-dataset generalization. To overcome these barriers, we introduce Node-U-Net, an ultra-lightweight attention-guided encoder-decoder architecture. This framework integrates a MobileNetV2 backbone with Residual Dilated Blocks and Light Atrous Spatial Pyramid Pooling (Light-ASPP) to expand multi-scale contextual awareness without inflating computational costs. Additionally, spatio-channel attention mechanisms and skip-connection attention gates adaptively suppress irrelevant background noise, while deep supervision ensures precise small nodule detection. Evaluated on the LIDC-IDRI dataset, Node-U-Net achieves a 94.34% Dice similarity coefficient, 94.20% Intersection over Union, and 98.31% precision ( <math xmlns="http://www.w3.org/1998/Math/MathML"><mrow><mi>p</mi> <mo><</mo> <mn>0.001</mn></mrow> </math> , 92% win rate). Crucially, the model demonstrates robust zero-shot cross-domain generalization, maintaining a 91.49% Dice score on the unseen, independent UniToChest dataset. Notably, Node-U-Net achieves this with only 4.56 million parameters and 7.94 GFLOPs-representing a <math xmlns="http://www.w3.org/1998/Math/MathML"><mrow><mn>34.8</mn> <mo>×</mo></mrow> </math> computational reduction compared to U-Net++. These results position Node-U-Net as a highly scalable solution for real-time AI-assisted lung cancer screening, making it viable for integration into resource-constrained clinical environments and edge devices.