Breast Cancer Recognition Algorithm Based on Convolution Neural Network
Most of the preliminary attempts of deep learning in medical images focus on replacing natural images with medical images into convolutional neural networks. In doing so, however, the particularity of medical images and the basic differences between the two types of images are ignored.
This difference makes it impossible to directly use the network architecture developed for natural images. This paper therefore uses medical data sets for migration learning. Moreover, the reason why deep learning is difficult to apply in medicine is that it can easily lead to medical disputes
because of its unexplainability. In this paper, the deep learning model is explained and implemented by using the theory of fuzzy logic. This paper tests the accuracy and stability of the original model and the new model in classification prediction. Our results show that the model implemented
by fuzzy logic improves the accuracy, and makes the prediction more stable as well.
Keywords: Convolution Neural Network; Fuzzy Logic; Medical Image Classification; Transfer Learning
Document Type: Research Article
Affiliations: 1: Institute of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha 410076, China 2: Liberal Arts & Convergence Studies, Honam University, Gwangju 62399, Republic of Korea
Publication date: 01 March 2021
- Journal of Medical Imaging and Health Informatics (JMIHI) is a medium to disseminate novel experimental and theoretical research results in the field of biomedicine, biology, clinical, rehabilitation engineering, medical image processing, bio-computing, D2H2, and other health related areas.
- Editorial Board
- Information for Authors
- Subscribe to this Title
- Ingenta Connect is not responsible for the content or availability of external websites
- Access Key
- Free content
- Partial Free content
- New content
- Open access content
- Partial Open access content
- Subscribed content
- Partial Subscribed content
- Free trial content