ParaU-Net: An improved UNet parallel coding network for lung nodule segmentation

Accurate segmentation of lung nodules is crucial for the early detection of lung cancer and other pulmonary diseases. Traditional segmentation methods face several challenges, such as the overlap between nodules and surrounding anatomical structures like blood vessels and bronchi, as well as the variability in nodule size and shape, which complicates the segmentation algorithms. Existing methods often inadequately address these issues, highlighting the need for a more effective solution. To address these challenges, this paper proposes an improved multi-scale parallel fusion encoding network, ParaU-Net. ParaU-Net enhances the segmentation accuracy and model performance by optimizing the encoding process, improving feature extraction, preserving down-sampling information, and expanding the receptive field. Specifically, the multi-scale parallel fusion mechanism introduced in ParaU-Net better captures the fine features of nodules and reduces interference from other structures. Experiments conducted on the LIDC (The Lung Image Database Consortium) public dataset demonstrate the excellent performance of ParaU-Net in segmentation tasks, with results showing an IoU of 87.15%, Dice of 92.16%, F1-score of 92.24%, F2-score of 92.33%, and F0.5-score of 92.69%. These results significantly outperform other advanced segmentation methods, validating the effectiveness and accuracy of the proposed model in lung nodule CT image analysis. The code is available at https://github.com/XiaoBai-Lyq/ParaU-Net . • We propose MPEM (Multi-Scale Parallel Encoding Module) to enhance lung nodule feature capture. • We introduce CFFM (Coordinate Feature Fusion Module) for better global and positional information. • We use the Trans-conv module in layers to combine CNN and Transformer, optimizing features. • Based on UNet, we tested on LIDC to find the optimal learning rate using cosine annealing. • Our ParaU-Net shows superior performance in lung nodule segmentation on the LIDC dataset.