|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
Breast cancer is the cancer which forms in the breast cells. After skin cancer, breast cancer is the most commonly diagnosed cancer in women. It is deadly if not recognized and treated early. Early detection of these diseases helps prevent cancer. If cancer is detected early, the chances of survival are very high. Especially in the medical industry, where such methods are often used in higher process diagnostics. The article presents a machine learning model for the automatic diagnosis of breast cancer. The proposed method is breast cancer prediction using machine learning techniques such as deep neural networks and random forest classification algorithms used to collect image and text data. We discuss the types of breast cancer and the challenges of early detection to prevent further damage. The ultrasound image is used as input for the neural network prediction. Random Forest (RF) classifiers are used to handle multidimensional noise data in text classification. The RF model consists of a series of decision trees, each built from subsets of random functions. For the most efficient machine learning model, the BUI and Wisconsin data set is used. Datasets are trained, pre-processed, and then classified for final prediction. This approach is particularly interesting because it fits into the growing trend of personalized predictive medicine.
Keyword
Healthcare system, Breast cancer, Machine learning Prediction, Deep Neural Network, Cancer diagnosis, Random Forest Algorithm
PDF Download (click here)
|
|
|
|
|