基于深度学习的癌变组织显微高光谱图像分类
Classification of Microscopic Hyperspectral Images of Cancerous Tissue Based on Deep Learning
张勇 1黄丹飞 1张乐超 1张丽丽 1周尧 1唐鸿宇1
作者信息
- 1. 长春理工大学光电工程学院,吉林 长春 130022;长春理工大学中山研究院,广东 中山 528400
- 折叠
摘要
在因式分解卷积神经网络和残差结构的思想下,利用膨胀卷积,并添加注意力机制,提出了一种融合混合注意力机制模块的残差分解卷积神经网络(CBAM-RFNet).该网络主要是把传统3×3的二维卷积因式分解为3×1和1×3的两个一维卷积串联,不仅增加了网络模型的深度,还减少了参数,是一种轻量级的网络模型.在显微高光谱成像系统采集的甲状腺癌显微高光谱图像上的实验结果显示,与其他深层的神经网络相比,提出的网络能有效提升显微高光谱图像的分类精度,其分类的总体准确率为98.23%,F1值为98.66%,Kappa系数为0.909.
Abstract
Based on the idea of factorization neural network and residual structure,a convolutional block attention module for residual factorized of convolutional neural networks(CBAM-RFNet)is proposed by expansive convolution and adding attention mechanism.In this network,the traditional 3×3 two-dimensional convolution is decomposed into two one-dimensional convolution of 3×1 and 1×3 and connect them in series,which not only increases the depth of the network model,but also reduces the parameters,the network is a lightweight network model.The experimental results on thyroid cancer images collected by microhyperspectral imaging system show that,compared with other deep neural networks,the proposed network can effectively improve the classification accuracy of microhyperspectral images,with the overall accuracy of 98.23%,F1 value of 98.66%,and Kappa coefficient of 0.909.
关键词
显微高光谱图像分类/因式分解卷积/膨胀卷积/注意力机制/轻量级网络Key words
microhyperspectral image classification/factorization convolution/expansive convolution/attention mechanism/lightweight network引用本文复制引用
基金项目
国家自然科学基金(61893096014)
出版年
2024
NETL
NSTL
万方数据