Study on Target Detection of Breast Tumor Based on Improved Mask R-CNN

Yuejun Sun; Zhaoyan Qu; Yihong Li

doi:10.3788/AOS202141.0212004

Acta Optica Sinica, Volume. 41, Issue 2, 0212004(2021)

Study on Target Detection of Breast Tumor Based on Improved Mask R-CNN

Yuejun Sun¹, Zhaoyan Qu^1、*, and Yihong Li²

Author Affiliations

¹Shanxi Key Laboratory of Signal Capturing & Processing, North University of China, Taiyuan, Shanxi 0 30051, China;

²School of Science, North University of China, Taiyuan, Shanxi 0 30051, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(18)

Fig. 1. Normal and diseased breast images. (a) Normal breast image; (b) diseased breast image

Download full size

Fig. 2. Images of four types of breast. (a) LCC; (b) LMLO; (c) RCC; (d) RMLO

Download full size

Fig. 3. Original image and image with background elimination. (a) Original image; (b) image with background elimination

Download full size

Fig. 4. Lesion grade. (a) Lesion grade 2; (b) lesion grade 3; (c) lesion grade 4a; (d) lesion grade 4b; (e) lesion grade 4c; (f) lesion grade 5

Download full size

Fig. 5. Images of diseased and healthy areas and their fusion image. (a) Image of diseased area; (b) image of healthy area; (c) fusion image

Download full size

Fig. 6. Mask R-CNN network structure

Download full size

Fig. 7. Schematic of Dense Block in DenseNet

Download full size

Fig. 8. Schematic of DenseNet structure

Download full size

Fig. 9. Schematic of Channel Shuffle. (a) Grouped convolution; (b) Shuffle process; (c) effect after applying Shuffle

Download full size

Fig. 10. Accuracy curves of original data set and data set with background elimination

Download full size

Fig. 11. Loss curves of original data set and data set with background elimination

Download full size

Fig. 12. Accuracy of D-ShuffleNet network in pretraining

Download full size

Fig. 13. Loss of D-ShuffleNet network in pretraining

Download full size

Fig. 14. ROC curves of each model

Download full size

Table 1. Number of lesion areas of each grade and their corresponding proportions to the total number of lesion areas
View table
Table 1. Number of lesion areas of each grade and their corresponding proportions to the total number of lesion areas
Grade Number Proportion /%
2 463 24
3 406 21
4a 348 18
4b 289 15
4c 251 13
5 175 9

Table 2. Classification results confusion matrix
View table
Table 2. Classification results confusion matrix
Real Forecast
P N
P TP FN
N FP TN

Table 3. Training results of each model

View table

Table 3. Training results of each model

Model	Average precision						mAP
Model	2	3	4a	4b	4c	5	mAP
Mask R-CNN-II	0.94	0.93	0.85	0.93	0.85	0.94	0.907
Mask R-CNN	0.92	0.93	0.85	0.87	0.84	0.95	0.893
YOLO-V3	0.93	0.91	0.82	0.87	0.81	0.95	0.881
SSD	0.89	0.87	0.81	0.87	0.82	0.93	0.865
Faster R-CNN	0.91	0.90	0.83	0.85	0.82	0.92	0.871

Table 4. Experimental results of models with and without pretraining
View table
Table 4. Experimental results of models with and without pretraining
Model Average precision mAP
2 3 4a 4b 4c 5
Pre-T+Mask R-CNN-II 0.97 0.94 0.87 0.94 0.86 0.98 0.927
Pre+Mask R-CNN-II 0.96 0.95 0.86 0.93 0.85 0.98 0.921
Mask R-CNN-II 0.94 0.93 0.85 0.93 0.85 0.94 0.907

Tools

Get Citation

Copy Citation Text

Yuejun Sun, Zhaoyan Qu, Yihong Li. Study on Target Detection of Breast Tumor Based on Improved Mask R-CNN[J]. Acta Optica Sinica, 2021, 41(2): 0212004

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites