•  
  •  
 

AI-POWERED IMAGE PROCESSING AND TUMOR DETECTION IN DIGITAL MAMMOGRAPHY

Abstract

Breast cancer remains one of the leading causes of mortality among women worldwide, emphasizing the need for early and accurate detection. Digital mammograms are commonly used for breast cancer screening, but challenges like image noise, low contrast, and dense breast tissue can sometimes make small abnormalities difficult to detect. This study investigates the use of artificial intelligence (AI) and deep learning–based image processing techniques to enhance tumor detection and reduce diagnostic uncertainty. Image preprocessing, segmentation, and classification are explored with emphasis on improved mammographic image analysis. Classical image enhancement algorithms such as Gaussian, median, and contrast-limited adaptive histogram equalization (CLAHE) are compared with advanced deep learning architectures while exploring how they influence accuracy and lesion classification performance. The results aim to identify optimized AI-driven workflows that improve tumor visibility, enhance classification accuracy, and support more reliable computer-aided diagnosis in digital mammography.

Acknowledgements

Clark Atlanta University, Title III

This document is currently not available here.

Share

COinS