An exact segmentation of affected part in breast cancer using spider monkey optimization and recurrent neural network

• Published in: Multimedia tools and applications 2024-01, Vol.83 (23), p.62773-62791
• Main Authors: Naidu, M. S. R., Anilkumar, B., Yugandhar, Dasari
• Format: Article
• Language: English
• Subjects: Accuracy; Breast cancer; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Datasets; Image segmentation; Mammography; Medical imaging; Monkeys; Multimedia Information Systems; Recurrent neural networks; Special Purpose and Application-Based Systems
• ISSN: 1573-7721; 1380-7501; 1573-7721
• DOI: 10.1007/s11042-023-18069-9

The most common and rapidly spreading disease in the world is breast cancer. Most cases of breast cancer are observed in females. Breast cancer is controlled with early detection. Therefore, early detection and categorization of breast cancer are essential to enable patients to take the right course of treatment. Early discovery helps to manage many cases and lower the death rate. In this study, a brand-new Spider Monkey-based Recurrent Neural System (SMbRNS) is created for predicting breast cancer cells in an early stage. Breast mammography images are used in this instance as the dataset for the system. The breast dataset is also analyzed using the established SMbRNS function to detect and segregate the breast cancer-afflicted region efficiently. The developed model aims to enhance the segmented breast cancer results using spider monkey fitness. The developed method computes the chance of breast cancer using the dataset; segmented images are used for monitoring. Additionally, the Python code used to perform this strategy allows for evaluating the created model parameters against earlier research. The experimental results are validated with other prevailing models regarding the accuracy, precision, sensitivity, specificity, and F1-score to prove the efficiency. The designed model gained 99.82% accuracy and 99.12% precision for segmenting breast cancer. The current study model produces mammography with better accuracy for the segmentation of breast cancer.