Classification Method of Breast Tissue OCT Images Based on a Double Filtering Residual Network

Table 1. Detailed system parameters
View table
View in Article
Table 1. Detailed system parameters
Name Indicator
System Windows 11
Memory 32 GB
Central processing unit AMD Ryzen 7 5800H（3.20 GHz）
Graphics processing unit NVIDIA RTX3070 GPU

Table 2. Comparison of performance among three models

View table

View in Article

Table 2. Comparison of performance among three models

Method	Images	Sen	Spe	PPV	NNP	Accuracy
ResNet-28	F_B	0.987 5	0.995 3	0.990 6	0.993 8	0.938 5
	S	0.878 1	0.971 9	0.939 8	0.941 0
	T	0.950 0	0.940 6	0.888 9	0.974 1
Oct_ResNet-28	F_B	0.987 5	0.987 5	0.975 3	0.993 7	0.954 2
	S	0.915 6	0.976 6	0.951 3	0.958 6
	T	0.959 4	0.967 2	0.936 0	0.979 4
DF-ResNet	F_B	0.990 6	0.992 2	0.984 5	0.995 3	0.968 8
	S	0.946 9	0.981 3	0.961 9	0.973 6
	T	0.968 8	0.979 7	0.959 8	0.984 3

Table 3. The recognition and classification performance of DF-ResNet on a new dataset
View table
View in Article
Table 3. The recognition and classification performance of DF-ResNet on a new dataset
Method Images Sen Spe PPV NNP Accuracy
DF-ResNet F_B 1.000 1.000 1.000 1.000 0.941 2
S 0.882 0 0.971 0 0.938 0 0.943 0
T 0.941 0 0.941 0 0.889 0 0.970 0

Table 4. model parameter quantity and classification accuracy
View table
View in Article
Table 4. model parameter quantity and classification accuracy
Method Accuracy Parameter quantity/MiB
VGG-19 0.793 9 143.7
EfficientNet 0.916 7 5.290
ResNet-28 0.938 5 19.14
DenseNet-169 0.957 2 14.15
Oct_ResNet-28 0.954 2 15.99
DF-ResNet 0.968 8 16.52

Tools

Get Citation

Copy Citation Text

Lihao DING, Zhishan GAO, Dan ZHU, Qun YUAN, Zhenyan GUO. Classification Method of Breast Tissue OCT Images Based on a Double Filtering Residual Network[J]. Acta Photonica Sinica, 2023, 52(12): 1210001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites