Grid-Search Integrated Optimized Support Vector Machine Model for Breast Cancer Detection

Partho Ghose, Selina Sharmin, Loveleen Gaur, Zhongming Zhao

Abstract: Breast cancer is a common and highly heterogeneous cancer worldwide. Rapid detection and early diagnosis are essential in its treatment, but it is challenging due to mammogram’s uncertainty. Based on machine learning, operative clinical systems can be implemented to save patients’ lives. This study proposes an optimized support vector machine (SVM) model to predict breast cancer using the grid search method to find the best hyper-parameters. For validation, we offer an in-depth experimental study and we achieve, for Benign|Malignant|Average cases, accuracy of 98.69%|99.72%|99.0%, precision of 96.0%|100.0%|98.0%, recall of 100.0%|98.0%|98.0%, and Fl-score of 98.0%|97.0%|98.0% respectively. Comparison is made between the tuned hyper-parameter and default hyper-parameter performance. SVM performance with default parameters is 96%, while the maximum accuracy is achieved by hyper-parameters tuned. An SVM model is 99%, which can be a better cancer detection system. The results show performance improves when the best hyperparameters are used for SVM training. Thus, the analysis and comparison indicate that our stated system is better than the state-of-the-art ML-based breast cancer detection system.

External IDs:dblp:conf/bibm/GhoseSGZ22