C-3D可变形卷积神经网络模型的肺结节检测

阮宏洋; 陈志澜; 程英升; 杨凯

doi:doi:10.3788/LOP57.041013

激光与光电子学进展, 2020, 57 (4): 041013, 网络出版: 2020-02-20

C-3D可变形卷积神经网络模型的肺结节检测下载： 1104次

Detection of Pulmonary Nodules Based on C-3D Deformable Convolutional Neural Network Model

阮宏洋 ¹陈志澜 ^2,*程英升 ³杨凯 ³

作者单位

¹ 上海海洋大学工程学院, 上海 210306

² 上海建桥学院机电学院, 上海 210306

³ 上海市第六人民医院东院放射介入科, 上海 210306

图 & 表

图 1. 肺部CT扫描图

Fig. 1. CT images of lung

下载图片查看原文

图 2. C-3D卷积神经网络模型结构

Fig. 2. Structure of C-3D convolutional neural network model

下载图片查看原文

图 3. 三维可变形卷积与池化结构。(a)三维可变形卷积结构;(b)三维可变形池化结构

Fig. 3. Structures of 3D deformable convolution and pooling. (a) 3D deformable convolution; (b) 3D deformable pooling

下载图片查看原文

图 4. C-3D可变形卷积神经网络模型结构

Fig. 4. Structure of C-3D deformable convolutional neural network model

下载图片查看原文

图 5. 不同学习率和优化函数下的分类正确率。(a)学习率实验对比;(b)优化函数实验对比,

Fig. 5. Classification accuracy for different learning rates and optimization functions. (a) Experimental comparison of learning rate; (b) experimental comparison of optimization function

下载图片查看原文

图 6. 不同模型的ROC曲线图和PRC曲线图。(a) ROC曲线;(b) PRC曲线

Fig. 6. ROC curves and PRC curves of different models. (a) ROC curves; (b) PRC curves

下载图片查看原文

图 7. 可变形卷积层中不同特征图数量的箱型图。(a) A_UC指标箱型图;(b) F₁指标箱型图;(c) P指标箱型图;(d) Recall指标箱型图

Fig. 7. Boxes of deformable convolution layers with different numbers of features. (a) Box of A_UC; (b) box of F₁; (c) box of P; (d) box of R

下载图片查看原文

图 8. 卷积窗口像素采样可视化结果。(a)原始的肺结节标注图片;(b)原C-3D卷积神经网络模型;(c)改进后的C-3D卷积神经网络模型

Fig. 8. Visualization results of convolution window pixel sampling. (a) Original labeled lung images; (b) original C-3D convolutional neural network; (c) improved C-3D convolutional neural network

下载图片查看原文

表 1C-3D可变形卷积神经网络模型中卷积层与池化层的具体参数设置

Table1. Setting of parameters of convolution layer and pooling layer in C-3D deformable convolutional neural network

Layer	F (number of convolutionalfeature maps)×S (kernal size)	Stride	Activation function	Output
3D conv1	16×(3×3×3)	1×1×1	ReLU	32×32×32
3D conv2	64×(3×3×3)	2×1×1	ReLU	16×32×32
3D pool1	64×(1×2×2)	1×2×2	—	16×16×16
3D conv3	128×(3×3×3)	1×1×1	ReLU	16×16×16
3D pool2	128×(2×2×2)	2×2×2	—	8×8×8
3D conv4	256×(3×3×3)	1×1×1	ReLU	8×8×8
3D pool3	256×(2×2×2)	2×2×2	—	4×4×4
3D conv5	512×(3×3×3)	1×1×1	ReLU	4×4×4
3D pool4	512×(2×2×2)	2×2×2	—	2×2×2
3D conv6	64×(3×3×3)	1×1×1	ReLU	1×1×1
3D conv7	1×(1×1×1)	1×1×1	Sigmoid	1×1×1
F_c (fully connected layer)	—	—	—	1

查看原文

表 2数据集信息

Table2. Dataset information

Number	Name	Number ofsamples	Number ofpulmonarynodules
1	LIDC-IDIR	888	1186
2	East Hospital of ShanghaiSixth People's Hospital	300	346
3	Hospital of KanghuaHaining Zhejiang	200	212

查看原文

表 3不同卷积神经网络模型的结果对比

Table3. Comparison of results of different convolutional neural network models

Model	A_UC	R	P	F₁
C-3D	0.9422±0.0105	0.9125±0.0131	0.9335±0.0135	0.8846±0.0036
C-3D±DC	0.9513±0.0127	0.9228±0.0158	0.9387±0.0101	0.8978±0.0097
C-3D±DP	0.9326±0.0241	0.8997±0.0179	0.9254±0.0157	0.8797±0.0103
C-3D±DCP	0.9575±0.0098	0.9183±0.0096	0.9413±0.0075	0.9067±0.0058

查看原文

表 4C-3D可变形卷积神经网络中不同输出特征图结果对比

Table4. Results comparison of different output features in C-3D deformable convolutional neural network

Model	R	P	F₁	A_UC
C-3D+DCP,F:8	0.9131±0.0125	0.9226±0.0048	0.8948±0.0107	0.9394±0.0117
C-3D±DCP,F:16	0.9183±0.0096	0.9413±0.0075	0.9067±0.0058	0.9575±0.0098
C-3D±DCP,F:32	0.9253±0.0164	0.9534±0.0104	0.9286±0.0083	0.9617±0.0131
C-3D±DCP,F:64	0.8957±0.0063	0.9113±0.0243	0.9024±0.0096	0.9339±0.0164

查看原文

表 5各个卷积神经网络算法比较

Table5. Comparison of different convolutional neural networks

Model	A_UC	P	R	F₁	Data
Ref. [6]	0.8434	0.7444	0.7916	0.7673	LIDC-IDRI
Ref. [7]	0.9387	0.8750	0.9243	0.8990	LIDC-IDRI
Ref. [8]	0.8523	0.9045	0.9162	0.9103	LIDC-IDRI
Proposed method	0.9617	0.9534	0.9239	0.9286	LIDC-IDRI
Proposed method	0.9661	0.9613	0.9253	0.9378	LIDC-IDIR+Local data

查看原文

阮宏洋, 陈志澜, 程英升, 杨凯. C-3D可变形卷积神经网络模型的肺结节检测[J]. 激光与光电子学进展, 2020, 57(4): 041013. Hongyang Ruan, Zhilan Chen, Yingsheng Cheng, Kai Yang. Detection of Pulmonary Nodules Based on C-3D Deformable Convolutional Neural Network Model[J]. Laser & Optoelectronics Progress, 2020, 57(4): 041013.

C-3D可变形卷积神经网络模型的肺结节检测下载： 1104次

图 1. 肺部CT扫描图

Fig. 1. CT images of lung

图 2. C-3D卷积神经网络模型结构

Fig. 2. Structure of C-3D convolutional neural network model

图 3. 三维可变形卷积与池化结构。(a)三维可变形卷积结构;(b)三维可变形池化结构

Fig. 3. Structures of 3D deformable convolution and pooling. (a) 3D deformable convolution; (b) 3D deformable pooling

图 4. C-3D可变形卷积神经网络模型结构

Fig. 4. Structure of C-3D deformable convolutional neural network model

图 5. 不同学习率和优化函数下的分类正确率。(a)学习率实验对比;(b)优化函数实验对比,

Fig. 5. Classification accuracy for different learning rates and optimization functions. (a) Experimental comparison of learning rate; (b) experimental comparison of optimization function

图 6. 不同模型的ROC曲线图和PRC曲线图。(a) ROC曲线;(b) PRC曲线

Fig. 6. ROC curves and PRC curves of different models. (a) ROC curves; (b) PRC curves

图 7. 可变形卷积层中不同特征图数量的箱型图。(a) A_UC指标箱型图;(b) F₁指标箱型图;(c) P指标箱型图;(d) Recall指标箱型图

Fig. 7. Boxes of deformable convolution layers with different numbers of features. (a) Box of A_UC; (b) box of F₁; (c) box of P; (d) box of R

图 8. 卷积窗口像素采样可视化结果。(a)原始的肺结节标注图片;(b)原C-3D卷积神经网络模型;(c)改进后的C-3D卷积神经网络模型

Fig. 8. Visualization results of convolution window pixel sampling. (a) Original labeled lung images; (b) original C-3D convolutional neural network; (c) improved C-3D convolutional neural network

表 1C-3D可变形卷积神经网络模型中卷积层与池化层的具体参数设置

Table1. Setting of parameters of convolution layer and pooling layer in C-3D deformable convolutional neural network

表 2数据集信息

Table2. Dataset information

表 3不同卷积神经网络模型的结果对比

Table3. Comparison of results of different convolutional neural network models

表 4C-3D可变形卷积神经网络中不同输出特征图结果对比

Table4. Results comparison of different output features in C-3D deformable convolutional neural network

表 5各个卷积神经网络算法比较

Table5. Comparison of different convolutional neural networks

关于本站 Cookie 的使用提示

全站搜索

C-3D可变形卷积神经网络模型的肺结节检测 下载： 1104次

图 1. 肺部CT扫描图

Fig. 1. CT images of lung

图 2. C-3D卷积神经网络模型结构

Fig. 2. Structure of C-3D convolutional neural network model

图 3. 三维可变形卷积与池化结构。(a)三维可变形卷积结构;(b)三维可变形池化结构

Fig. 3. Structures of 3D deformable convolution and pooling. (a) 3D deformable convolution; (b) 3D deformable pooling

图 4. C-3D可变形卷积神经网络模型结构

Fig. 4. Structure of C-3D deformable convolutional neural network model

图 5. 不同学习率和优化函数下的分类正确率。(a)学习率实验对比;(b)优化函数实验对比,

Fig. 5. Classification accuracy for different learning rates and optimization functions. (a) Experimental comparison of learning rate; (b) experimental comparison of optimization function

图 6. 不同模型的ROC曲线图和PRC曲线图。(a) ROC曲线;(b) PRC曲线

Fig. 6. ROC curves and PRC curves of different models. (a) ROC curves; (b) PRC curves

图 7. 可变形卷积层中不同特征图数量的箱型图。(a) AUC指标箱型图;(b) F1指标箱型图;(c) P指标箱型图;(d) Recall指标箱型图

Fig. 7. Boxes of deformable convolution layers with different numbers of features. (a) Box of AUC; (b) box of F1; (c) box of P; (d) box of R

图 8. 卷积窗口像素采样可视化结果。(a)原始的肺结节标注图片;(b)原C-3D卷积神经网络模型;(c)改进后的C-3D卷积神经网络模型

Fig. 8. Visualization results of convolution window pixel sampling. (a) Original labeled lung images; (b) original C-3D convolutional neural network; (c) improved C-3D convolutional neural network

表 1C-3D可变形卷积神经网络模型中卷积层与池化层的具体参数设置

Table1. Setting of parameters of convolution layer and pooling layer in C-3D deformable convolutional neural network

表 2数据集信息

Table2. Dataset information

表 3不同卷积神经网络模型的结果对比

Table3. Comparison of results of different convolutional neural network models

表 4C-3D可变形卷积神经网络中不同输出特征图结果对比

Table4. Results comparison of different output features in C-3D deformable convolutional neural network

表 5各个卷积神经网络算法比较

Table5. Comparison of different convolutional neural networks

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索

C-3D可变形卷积神经网络模型的肺结节检测下载： 1104次

图 7. 可变形卷积层中不同特征图数量的箱型图。(a) A_UC指标箱型图;(b) F₁指标箱型图;(c) P指标箱型图;(d) Recall指标箱型图

Fig. 7. Boxes of deformable convolution layers with different numbers of features. (a) Box of A_UC; (b) box of F₁; (c) box of P; (d) box of R