• T. SATHYA PRIYA
• DR. T. RAMAPRABHA

Breast cancer is one of the most serious diseases, with the highest occurrence worldwide, where early identification and diagnosis, obtained by imaging techniques such as mammography, play a vital role in preventing the disease. For mammography diagnostics, radiologists have a high false positive rate and an accuracy of roughly 82 percent. Deep learning (DL) approaches have demonstrated promising results in developing computer-aided diagnostic (CAD) systems for early identification of breast cancer.Using mammogram images, this research develops a new deep segmentation with residual network (DS-RN) based breast cancer diagnosis model. Pre-processing, Faster Region based Convolution Neural Network (R-CNN) (Faster R-CNN), and Inception v2 model based segmentation, feature extraction, and classification are all part of the described DS-RN model. Random forest (RF) classifier model is used to classify mammogram images. To ensure that the provided model performs better on the Mini-MIAS dataset, a rigorous simulation process is used. The DS-RN model achieved maximum classification performance with sensitivity, specificity, accuracy, and F-Measure of 96.36%, 100 %, 97.75%, and 98.15%, respectively, according to the collected experimental values.

Breast cancer, Classification, Segmentation, Feature extraction, Mammogram

"Deep Segmentation and Classification for Breast Cancer Detection in Mammogram Images", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 4, page no.d513-d523, April-2022, Available :http://www.jetir.org/papers/JETIR2204365.pdf

"Deep Segmentation and Classification for Breast Cancer Detection in Mammogram Images", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 4, page no. ppd513-d523, April-2022, Available at : http://www.jetir.org/papers/JETIR2204365.pdf