Breast Tumor Segmentation using U-NET
Mirya Robin, Jisha John, Aswathy Ravikumar
Abstract
Cancer stands in second leading cause of death worldwide, an average of one in six deaths is due to cancer. The occurrence of breast cancer is more in women compared to men. Breast cancer signs are of a breast lump, differences in the nipples or breasts form or texture etc. Its therapy based on the cancer stages. Early detection of cancer will reduce the death risk for patients. The paper's target is to detect the breast cancer area. To give accurate treatment for the patients, symptoms should be observed properly, and a prediction automatic system is needed that will classify the tumor into benign or malignant. As a general convolutional neural network its role focuses on the classification of images, where input is an image and output are one label, but in biomedical cases, not only does it enable us to discern whether a disease occurs, but also to locate the region of abnormality. U-Net is devoted to solving this problem. This research work has proposed a UNET based architecture for segmentation of tumor region in histopathological images. The network is depending on a fully convolutional network and its design is updated and expanded to operate with less pictures of training and to create more accurate segmentations. The proposed method gives an overall accuracy of 94.2 with very less dataset.