Ultrasound based breast cancer recognition using Mask RCNN
Pradeep Kumar, K. Venkata Sumandar, G. V. Swaroop Das, G. Kavya Reddy, Subodh P. Srivastava, A. Kuamar · IET conference proceedings. · 2023
As breast cancer is the leading cause of death in women globally, effective treatment is dependent on early identification. This paper presents a design for the Computer-Aided Diagnostic (CAD) system of Ultrasound based Breast Cancer Recognition using mask regional convolutional neural network (Mask RCNN). The dataset used in the proposed model consists of three classes benign, malignant, and normal. The paper includes a detailed description of the dataset used, implementation of the proposed model, and performance evaluation of the model. To get better efficacy, the dataset is pre-processed. The results of the experiment show that the proposed method detects breast cancer in all three classes, i.e., benign, malignant, and normal with an average accuracy of 97.93%. The annotated dataset used in this paper can also be used for future research in this area. Overall, the proposed method provides a promising solution for early breast cancer detection and may help improve patient outcomes.