Mammography Image Abnormalities Detection and Classification by Deep Learning with Extreme Learner

Breast cancer has emerged as a leading killer of women worldwide in recent decades. Mammography is a useful tool for detecting abnormalities and doing screenings. The primary factors in the early identification of breast cancer are the quality of mammogram image and the radiologist’s appraisal of the mammography. The extensive use of deep learning (DL) as well as other image-processing technologies in recent times has tremendously aided in the categorization of breast cancer images. Image processing and classification methods may help us find breast cancer earlier, increasing the likelihood of a positive outcome from therapy and the likelihood of survival. employ picture segmentation methods on the datasets to draw attention to the area of interest, and then classify the findings as malignant or benign. In an effort to minimize the mortality rate from breast cancer among females, this research seeks to discover novel approaches to illness classification and detection, as well as new strategies for preventing the disease. In order to correctly categorize the results, the best possible feature optimization is carried out utilizing deep learning technology. The Proposed deep CNN (Convolutional Neural Network) is improved using two classification models such as SVM (Support Vector Machine) and ELM (Extreme Learning Machine). In the proposed deep learning model, the feature extraction with AlexNet is accomplished using deep CNN. Subsequently, different parameters are fine-tuned to enhance accuracy with various optimizers and learning rates.

@article{Saruchi2023,
  title     = {Mammography Image Abnormalities Detection and Classification by Deep Learning with Extreme Learner},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {14},
  number    = {3},
  year      = {2023},
  publisher = {The Science and Information Organization},
  author    = {Saruchi and Jaspreet Singh},
  doi       = {10.14569/IJACSA.2023.01403107},
  url       = {https://doi.org/10.14569/IJACSA.2023.01403107}
}