002 Learning rate based on Jacobian determinant and modified U-net for medical brain image segmentation 2017SK077).Ĭorrespondence Author: Teng Fei, School of Information Engineering, Tianjin University of Commerce, Tianjin, China. 201810069133) and Scientific Research from the Education Commission of Tianjin (Grant No. From the comparison between the prediction results of the test set and the real results, it can be seen that the correct prediction is 28 out of 30 samples, and the prediction accuracy is 93.33%.Ĭonclusions: Using machine learning to evaluate the prognosis of breast cancer can evaluate the staged treatment effect of breast cancer patients, provide basis for subsequent treatment, help to find a more suitable treatment method for individual patients, enhance treatment, and achieve the aims of prolonging survival time, improving survival quality and reducing mortality.Īcknowledgements: This work was supported by Innovative Training Program for College Students (Grant No. RBF kernel function was used for training. Results: Using the breast cancer data set of the University of Wisconsin Hospital, 100 samples were randomly selected as training sets and 30 samples as test sets. If the model performance is not ideal, the model is reestablished by adjusting the kernel function and model parameters until the model meets the performance requirements. The diagnostic model is objectively analyzed and evaluated by the accuracy rate of experimental detection. The breast cancer data set is applied to the established model for experimental detection. Before training, the data set is normalized, and then it is trained to establish a breast cancer detection and diagnosis model based on support vector machine. Methods: The electrical impedance characteristics of the breast tissue are used as a training set. This project takes breast cancer as the research object and proposes to use machine learning algorithm to assist diagnosis. Objectives: With the development of machine learning and big data, a large amount of medical data provides a prerequisite for designing diagnosis assistant decision system using machine learning algorithm.
School of Information Engineering, Tianjin University of Commerce, Tianjin, China 001 Diagnosis methods of breast cancer based on machine learning
0 kommentar(er)
