Diagnosis of Breast Cancer Based on Modern Mammography using Hybrid Transfer Learning
This is an incremental improvement for radiologists to potentially reduce false rates in mammography analysis.
The paper tackled breast cancer detection from mammograms using a hybrid transfer learning model combining modified VGG16 and ImageNet, achieving an accuracy of 88.3%, which outperformed single architectures like MVGG16 (80.8%) and MobileNet (77.2%).
Breast cancer is a common cancer for women. Early detection of breast cancer can considerably increase the survival rate of women. This paper mainly focuses on transfer learning process to detect breast cancer. Modified VGG (MVGG), residual network, mobile network is proposed and implemented in this paper. DDSM dataset is used in this paper. Experimental results show that our proposed hybrid transfers learning model (Fusion of MVGG16 and ImageNet) provides an accuracy of 88.3% where the number of epoch is 15. On the other hand, only modified VGG 16 architecture (MVGG 16) provides an accuracy 80.8% and MobileNet provides an accuracy of 77.2%. So, it is clearly stated that the proposed hybrid pre-trained network outperforms well compared to single architecture. This architecture can be considered as an effective tool for the radiologists in order to reduce the false negative and false positive rate. Therefore, the efficiency of mammography analysis will be improved.