Back to Search Start Over

Breast Cancer Detection Using Deep Learning Technique Based On Ultrasound Image

Authors :
Mohammed, Abdulqader
Razek, Mohammed Abdel
El-dosuky, Mohamed
Sobhi, Ahmed
Publication Year :
2023

Abstract

Breast cancer ranks as the most prevalent form of cancer diagnosed in women, and diagnosis faces several challenges, a change in the size, shape and appearance of breasts, dense breast tissue, lumps or thickening in the breast especially if in only one breast, lumps and nodules in the breast. The major challenge that faces deep learning diagnosis of breast cancer was its shape, size and position non-uniformity especially malignant cancer. This work proposed a deep learning system that increased the accuracy of classification of breast cancer types from ultrasound images. It reaches 99.29% accuracy, exceeding other previous work. First, image processing was applied to in enhance the quality of input images. Second, the image segmentation was performed using U-Net architecture. Third, many features are extracted using Mobilenet. Finally, the accuracy of proposed system was evaluated.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2312.05261
Document Type :
Working Paper