Breast Cancer Localization and Classification in Mammograms Using YoloV5

Mammography screening is the main examination for breast cancer early detection, and has shown important benefits in reducing advanced and fatal disease rates. In this paper a YoloV5 model for simulta- neous breast cancer localization and classification in mammograms is proposed. Two public dataset were used for training and test. The CBIS-DDSM dataset, composed of scanned film mammograms, was used as a source dataset to implement the Transfer Learning tech- nique on the target INbreast dataset, composed of Full-Field Digital mammograms. The Small YoloV5 model combined with a large data- augmentation strategy was the best developed solution. A improvement of 0.103 mAP was found when Transfer Learning technique was imple- mented on the INbreast dataset. The performance was encouraging, resulting in a mAP of 0.838 ± 0.042, Recall of 0.722 ± 0.096, and Precision of 0.917 ± 0.077, calculated using the 5-Fold CV. The recog- nition rate achieved with the Transfer Learning on Full-Field Digital mammograms, encouraging future analysis on a proprietary dataset.