(1) Background: According to Taiwan’s ministry of health statistics, the rate of breast cancer in women is increasing annually. Each year, more than 10,000 women suffer from breast cancer, and over 2000 die of the disease. The mortality rate is annually increasing, but if breast cancer tumors are detected earlier, and appropriate treatment is provided immediately, the survival rate of patients will increase enormously. (2) Methods: This research aimed to develop a stepwise breast cancer model architecture to improve diagnostic accuracy and reduce the misdiagnosis rate of breast cancer. In the first stage, a breast cancer risk factor dataset was utilized. After pre-processing, Artificial Neural Network (ANN) and the support vector machine (SVM) were applied to the dataset to classify breast cancer tumors and compare their performances. The ANN achieved 76.6% classification accuracy, and the SVM using radial functions achieved the best classification accuracy of 91.6%. Therefore, SVM was utilized in the determination of results concerning the relevant breast cancer risk factors. In the second stage, we trained AlexNet, ResNet101, and InceptionV3 networks using transfer learning. The networks were studied using Adaptive Moment Estimation (ADAM) and Stochastic Gradient Descent with Momentum (SGDM) based optimization algorithm to diagnose benign and malignant tumors, and the results were evaluated; (3) Results: According to the results, AlexNet obtained 81.16%, ResNet101 85.51%, and InceptionV3 achieved a remarkable accuracy of 91.3%. The results of the three models were utilized in establishing a voting combination, and the soft-voting method was applied to average the prediction result for which a test accuracy of 94.20% was obtained; (4) Conclusions: Despite the small number of images in this study, the accuracy is higher compared to other literature. The proposed method has demonstrated the need for an additional productive tool in clinical settings when radiologists are evaluating mammography images of patients.
(1) Background: Breast cancer (BC)—a leading cause of mortality in women globally—accounts for more than two million cases annually. BC was the most common cancer in Taiwan in 2015 and ranks among the top 10 malignancies in Taiwan. (2) Methods: We established a collection of BC survival and metastasis analyses using the Kaplan–Meier, logarithmic test, and Cox proportional hazard models to investigate the association among BC stages, different treatment modalities, and survival rate of patients with BC at various follow-up intervals. We also evaluated whether clinical prognostic factors had univariate and multivariate effects on the survival of patients with BC. Finally, we performed a metastasis analysis using the survival transition rate values of BC stages to develop a Markov chain and semi-Markov simulation model for BC and BC metastasis analysis, respectively. (3) Results: The Kaplan–Meier survival analysis revealed that the risk of BC treated with surgery was lower than that of those who did not receive surgery and the recommended treatment methods should be ranked by survival as follows: surgery, hormone therapy, chemotherapy, and radiation therapy (in descending order of risk). This is attributed to the predicted survival rate which ranges from 99.6% to 91.2%. Moreover, Cox’s treatment method considered the patient’s attributes and revealed a significant difference (p = 0.001). The Markov chain analyses determined the chance of metastasis at each stage, indicating that the lower the stage of BC, the greater the survival rate. (4) Conclusions: Patients’ treatment is influenced by different BC stages, and earlier detection presents better chances of survival and a greater probability of treatment success.
Background: Breast cancer is the most common cancer among women. Many studies have made significant gains in classifying cancer tumors, emphasizing the best algorithm and highest classification accuracy but with limited interest in correcting misclassified data (Type 1 and Type 2 errors).Objective: This research proposes a novel hybrid integrated system of WEKA (Waikato Environment for Knowledge Analysis) and case-based reasoning (CBR) using myCBR plugin with protégé for the classification of breast cancer tumors and correction of misclassified data (Type 1 and Type 2 errors) of breast cancer tumors. Methods:The Wisconsin breast cancer dataset retrieved from the Wisconsin university repository was used in this research. The dataset contained 699 instances, 2 classes (malignant and benign), and 9 integer-valued attributes. The breast cancer tumors were determined by applying the J48, IBK, LibSVM, JRip, and Multi-Layer Perceptron (MLP) classifiers to classify the breast cancer tumors. Later, the myCBR plugin with protégé was used as an advanced modeling technique to correct the misclassified data and enhance its accuracy. Results:The proposed model performance evaluation was based on sensitivity, specificity, precision, and accuracy. Interestingly, based on the analyses, the IBK classifier had the highest misclassified data and the integrated system improved its classification accuracy from 95.61% to 98.53%. Conclusion:The findings demonstrated that the integrating of WEKA and myCBR plugin with protégé had unprecedented results with misclassified data. Thus, providing accurate diagnostics procedures for distinguishing between benign and malignant.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.