Analyzing the effect of Artifacts Removal and Pre-processing Techniques on Mammographic Image Quality

Pre-processing of mammography images is important for enhancing their quality and diagnostic accuracy thus greatly improving the performance of subsequent image analysis tasks, such as segmentation and classification. In the present work, the authors worked on mammographic images taken from the publicly available Mammographic Image Analysis Society (MIAS) database and proposed an efficient process to remove the artifacts before application of pre-processing methods. The authors evaluated the performance of filtering techniques for noise removal, contrast enhancement techniques and their combinations. Image quality assessment metrics such as Structural Similarity Index (SSIM) and Beta metric (β) were analyzed to evaluate the performance of applied techniques. The findings indicate that effective noise removal, contrast enhancement and artifacts removal significantly improve the quality of mammography images, facilitating more accurate and reliable diagnostic outcomes.