基于改进3D U-Net模型的肺结节分割方法研究
Research on Lung Nodule Segmentation Method Based on Improved 3D U-Net Model
石征锦 1李文慧 1高天1
作者信息
- 1. 沈阳理工大学,辽宁 沈阳 110159
- 折叠
摘要
由于肺部CT图像的特征信息复杂度较高,经典 3D U-Net网络在肺结节分割方面准确率较低,存在误分割等问题.基于此,提出一种基于改进 3D U-Net的网络模型.通过将加入了密集块的 3D U-Net网络和双向特征网络(Bi-FPN)融合,提高了模型分割精度.同时采用深度监督训练机制,进一步提高了网络性能.在公开数据集LUNA-16 上对模型进行比较实验和评估,结果显示,改进后的 3D U-Net网络,Dice相似系数较原模型提高 4%,分割精度为93.9%,敏感度为94.3%,证明该模型在肺结节分割精度及准确率方面具有一定的应用价值.
Abstract
Due to the high complexity of feature information in lung CT images,the classic 3D U-Net network exhibits low accuracy in lung nodule segmentation,leading to issues such as miss segmentation.To address this,a network model based on improved 3D U-Net is proposed.This model integrates 3D U-Net network with dense blocks with the Bidirectional Feature Pyramid Network(Bi-FPN)to improve the model's segmentation accuracy.The adoption of deep supervision training mechanism further enhances network performance.Comparative experiments and evaluations are conducted on the public dataset LUNA-16,and the results show that the improved 3D U-Net network has a 4%increase in Dice similarity coefficient,a segmentation accuracy of 93.9%,and a sensitivity of 94.3%compared to the original model.This proves that the model has certain application value in the accuracy and precision of lung nodule segmentation.
关键词
肺结节分割/CT/3D/U-Net/双向特征网络/深度监督Key words
lung nodule segmentation/CT/3D U-Net/bi-directional feature network/Deep Supervision引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
万方数据