Skip to main content
QUICK REVIEW

[论文解读] Dual-branch residual network for lung nodule segmentation

Haichao Cao, Hong Liu|arXiv (Cornell University)|May 21, 2019
Lung Cancer Diagnosis and Treatment参考文献 50被引用 10
一句话总结

本文提出了一种用于CT扫描中肺结节精确分割的双分支残差网络(DB-ResNet),通过双分支结构融合强度特征与卷积特征,结合中心强度池化层,利用多视角和多尺度特征提升性能。该方法在LIDC数据集上实现了82.74%的平均Dice分数,优于四位放射科医生0.49个百分点。

ABSTRACT

An accurate segmentation of lung nodules in computed tomography (CT) images is critical to lung cancer analysis and diagnosis. However, due to the variety of lung nodules and the similarity of visual characteristics between nodules and their surroundings, a robust segmentation of nodules becomes a challenging problem. In this study, we propose the Dual-branch Residual Network (DB-ResNet) which is a data-driven model. Our approach integrates two new schemes to improve the generalization capability of the model: 1) the proposed model can simultaneously capture multi-view and multi-scale features of different nodules in CT images; 2) we combine the features of the intensity and the convolution neural networks (CNN). We propose a pooling method, called the central intensity-pooling layer (CIP), to extract the intensity features of the center voxel of the block, and then use the CNN to obtain the convolutional features of the center voxel of the block. In addition, we designed a weighted sampling strategy based on the boundary of nodules for the selection of those voxels using the weighting score, to increase the accuracy of the model. The proposed method has been extensively evaluated on the LIDC dataset containing 986 nodules. Experimental results show that the DB-ResNet achieves superior segmentation performance with an average dice score of 82.74% on the dataset. Moreover, we compared our results with those of four radiologists on the same dataset. The comparison showed that our average dice score was 0.49% higher than that of human experts. This proves that our proposed method is as good as the experienced radiologist.

研究动机与目标

  • 为解决由于形态可变性和组织相似性导致的CT图像中肺结节分割难题。
  • 通过捕捉肺结节的多尺度和多视角特征,提升模型泛化能力。
  • 通过融合基于强度的特征与深层卷积特征,增强特征表示能力。
  • 通过基于边界置信度分数的加权采样策略,减少结节边界区域的误分类。

提出的方法

  • DB-ResNet采用两条并行分支:一条通过中心强度池化层(CIP)从每个块的中心体素提取强度特征,另一条通过CNN学习空间特征。
  • CIP层从3D体素块的中心区域计算统计强度特征(如均值、方差),以保留局部纹理信息。
  • 加权采样策略为靠近结节边界的体素分配更高得分,从而提升对难以分类的边缘区域的学习效果。
  • 两条分支的特征经拼接后,通过残差块处理,利用恒等捷径实现深层网络的稳定训练。
  • 模型采用交叉熵损失并结合类别平衡策略进行端到端训练,以应对结节与背景比例失衡的问题。
  • 测试阶段采用多尺度推理策略,聚合不同感受野的预测结果,提升模型鲁棒性。

实验结果

研究问题

  • RQ1双分支结构能否有效结合强度特征与深层卷积特征,从而提升结节分割性能?
  • RQ2多尺度与多视角特征学习在多样化肺结节上的分割性能提升机制是什么?
  • RQ3基于边界的感知采样策略能否降低结节边缘区域的误分类?
  • RQ4所提方法是否在标准基准上超越人类放射科医生的分割精度?
  • RQ5CIP层在保留3D结节中局部纹理与强度模式方面,其贡献程度如何?

主要发现

  • DB-ResNet在包含986个肺结节的LIDC-IDRI数据集上实现了82.74%的平均Dice分数。
  • 该模型在平均Dice分数上优于四位经验丰富的放射科医生0.49个百分点,表现出更优的性能。
  • 消融实验表明,双分支特征融合与加权采样策略均对性能提升有显著贡献。
  • CIP层通过捕捉局部强度模式,提升了特征表示能力,尤其在异质性结节区域表现突出。
  • 多尺度推理策略增强了模型鲁棒性,尤其对小尺寸和不规则形状结节效果显著。
  • 该模型在不同大小、形状与纹理的结节上均表现出强泛化能力,显示出高度适应性。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。