提出FusionLungNet模型，提升肺部CT图像分割精度。
FusionLungNet: Multi-scale Fusion Convolution with Refinement Network for Lung CT Image Segmentation
- 多尺度特征融合+注意力机制，捕捉复杂解剖结构
- 在新数据集上达98.04%交并比，显著优于现有方法
- 适合医学影像分析、肺病诊断研究者参考
早期发现肺癌至关重要，可提高治疗成功率。自动肺部图像分割有助于医生识别肺癌、COVID-19及呼吸系统疾病。但肺部分割面临血管与支气管结构重叠、亮度、颜色和纹理的像素级融合等挑战。现有方法难以建模图像组件间的长距离关系，过度依赖卷积操作，且肺部结构复杂。此外，特征图间语义差异阻碍信息整合，跳过连接也限制解码器获取完整信息，导致编码过程中的信息丢失。为此，我们提出FusionLungNet，采用混合架构：以ResNet-50为编码器，集成通道注意力（CAA）、多尺度特征融合（MFF）块、自精炼（SR）模块及多个解码器。精炼子网络使用卷积神经网络进行图像后处理以提升质量。结合SSIM、IOU与焦点损失的组合损失函数优化重建效果。我们构建并公开了新数据集LungSegDB，包含1800张来自LIDC-IDRI（版本1）的CT图像与700张来自Kaggle胸部癌症图像数据集（版本2）的图像。实验显示，该方法在分割任务中取得98.04%的交并比，显著超越现有方法。
原文摘要 · Abstract (English)
Early detection of lung cancer is crucial as it increases the chances of successful treatment. Automatic lung image segmentation assists doctors in identifying diseases such as lung cancer, COVID-19, and respiratory disorders. However, lung segmentation is challenging due to overlapping features like vascular and bronchial structures, along with pixel-level fusion of brightness, color, and texture. New lung segmentation methods face difficulties in identifying long-range relationships between image components, reliance on convolution operations that may not capture all critical features, and the complex structures of the lungs. Furthermore, semantic gaps between feature maps can hinder the integration of relevant information, reducing model accuracy. Skip connections can also limit the decoder's access to complete information, resulting in partial information loss during encoding. To overcome these challenges, we propose a hybrid approach using the FusionLungNet network, which has a multi-level structure with key components, including the ResNet-50 encoder, Channel-wise Aggregation Attention (CAA) module, Multi-scale Feature Fusion (MFF) block, self refinement (SR) module, and multiple decoders. The refinement sub-network uses convolutional neural networks for image post-processing to improve quality. Our method employs a combination of loss functions, including SSIM, IOU, and focal loss, to optimize image reconstruction quality. We created and publicly released a new dataset for lung segmentation called LungSegDB, including 1800 CT images from the LIDC-IDRI dataset (dataset version 1) and 700 images from the Chest CT Cancer Images from Kaggle dataset (dataset version 2). Our method achieved an IOU score of 98.04, outperforming existing methods and demonstrating significant improvements in segmentation accuracy. https://github.com/sadjadrz/FusionLungNet
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。