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

Journals >Laser & Optoelectronics Progress >Volume 57 >Issue 22 >Page 221021 > Article

Laser & Optoelectronics Progress
Vol. 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

Author Affiliations

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

DOI: 10.3788/LOP57.221021 Cite this Article Set citation alerts

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 Copy Citation Text

show less

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

	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 1. Image-level confusion matrix of ResNeXt

	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 2. Image-level confusion matrix of ResNeXt+OctConv 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 3. Image-level confusion matrix of ResNeXt +OctConv+HetConv model

	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 4. Image level confusion matrix of Ref. [4]

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 5. Recall,precision and accuracy of two methods 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 6. Recognition rate of different models 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

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

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information