Breast Cancer Histopathological Image Classification Based on Improved ResNeXt

Xuemeng Niu; Xiaoqi Lü; Yu Gu; Baohua Zhang; Ming Zhang; Guoyin Ren; Jing Li

doi:10.3788/LOP57.221021

Laser & Optoelectronics Progress, Volume. 57, Issue 22, 221021(2020)

Breast Cancer Histopathological Image Classification Based on Improved ResNeXt

Xuemeng Niu¹, Xiaoqi Lü^1,2、*, Yu Gu^1,3, Baohua Zhang¹, Ming Zhang^1,4, Guoyin Ren¹, and Jing Li¹

¹Key Laboratory of Pattern Recognition and Intelligent Image Processing, College of Information Engineering, Inner Mongolia University of Science and Technology, Baotou, Inner Mongolia 0 14010, China

²Institute of Information Engineering, Inner Mongolia University of Technology, Hohhot, Inner Mongolia 0 10051, China

³College of Computer Engineering and Science, Shanghai University, Shanghai 200444, China

⁴College of Information Science and Technology, Dalian Maritime University, Dalian, Liaoning 116026, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(19)

Fig. 1. Flow chart of our algorithm

Download full size

Fig. 2. Working principle of OctConv transition layer

Download full size

Fig. 3. Convolution with different structures. (a) Traditional convolution; (b) HetConv

Download full size

Fig. 4. Flow chart of HetConv algorithm

Download full size

Fig. 5. Structure of ResNeXt module

Download full size

Fig. 6. Image of the Benign class in the verification set. (a) Whole image; (b) small patches

Download full size

Fig. 7. Principle of the majority voting algorithm

Download full size

Fig. 8. Training accuracy and verification accuracy of the ResNeXt model

Download full size

Fig. 9. Image of partially judged wrong. (a) Invasive; (b) InSitu1; (c) InSitu2

Download full size

Fig. 10. Training accuracy and verification accuracy of the ResNeXt+OctConv model

Download full size

Fig. 11. Image of the Normal class

Download full size

Fig. 12. Training accuracy and verification accuracy of the ResNeXt+OctConv+HetConv model

Download full size

Table 1. Image-level confusion matrix of ResNeXt
View table
Table 1. Image-level confusion matrix of ResNeXt
Benign InSitu Invasive Normal
Benign 18 1 1 3
InSitu 1 18 4 0
Invasive 0 1 14 1
Normal 1 0 1 16

Table 2. Image-level confusion matrix of ResNeXt+OctConv model
View table
Table 2. Image-level confusion matrix of ResNeXt+OctConv model
Benign InSitu Invasive Normal
Benign 18 1 0 1
InSitu 1 18 3 0
Invasive 0 0 17 0
Normal 1 1 0 19

Table 3. Image-level confusion matrix of ResNeXt +OctConv+HetConv model
View table
Table 3. Image-level confusion matrix of ResNeXt +OctConv+HetConv model
Benign InSitu Invasive Normal
Benign 18 1 0 1
InSitu 0 18 2 0
Invasive 0 0 18 0
Normal 2 1 0 19

Table 4. Image level confusion matrix of Ref. [4]
View table
Table 4. Image level confusion matrix of Ref. [4]
Benign InSitu Invasive Normal
Benign 23 1 1 4
InSitu 1 20 2 1
Invasive 0 1 22 0
Normal 1 3 0 20

Table 5. Recall,precision and accuracy of two methods unit: %
View table
Table 5. Recall,precision and accuracy of two methods unit: %
Method Recall Precision Accuracy
Ourmethod Benign 90.00 90.00 91.25
InSitu 90.00 90.00
Invasive 90.00 100.00
Normal 95.00 86.36
Ref. [4] Benign 92.00 79.31 85.00
InSitu 80.00 83.33
Invasive 88.00 95.65
Normal 80.00 83.33

Table 6. Recognition rate of different models unit: %
View table
Table 6. Recognition rate of different models unit: %
Method ResNeXt ResNeXt+OctConv ResNeXt+OctConv+HetConv P=2(P=4) Ref.[4]
Patch-accuracy 71.92 81.73 83.04(78.12) 79.00
Image-accuracy 82.50 90.00 91.25(88.75) 85.00

Table 7. Experimental results obtained by different methods unit: %

View table

Table 7. Experimental results obtained by different methods unit: %

Method	Accuracy
Traditional machine learning^[1]	80.00-85.00
AlexNet^[2]	89.60
CNN+SVM^[3]	77.80
Inception-Transfer learning^[4]	85.00
LightGBM^[5]	87.20
Hierarchical ResNeXt^[6]	99.00
The contestants (ICIAR2018)	80.00-91.00
Our method	91.25

Tools

Get Citation

Copy Citation Text

Xuemeng Niu, Xiaoqi Lü, Yu Gu, Baohua Zhang, Ming Zhang, Guoyin Ren, Jing Li. Breast Cancer Histopathological Image Classification Based on Improved ResNeXt[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221021

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites