Mammogram image
modalities utilizing novelty of fuzzy segmentation for image enhancement of breast
cancer identification
Jeevitha V. and Laurence Aroquiaraj I.
Res. J. Biotech.; Vol. 20(11); 249-257;
doi: https://doi.org/10.25303/2011rjbt2490257; (2025)
Abstract
Breast Cancer is one of the most dangerous and deadly diseases. It is related to
early identification of a mammogram X-ray tool diagnostic, the breast cancerous,
non-cancerous and normal tissue identification with radiologist findings. It uses
a Mammogram Image Analysis of Society (MIAS) database utilizing benchmark dataset
to identify breast cancer with enhancing images. The main methodology of image segmentation
utilizing the heart of the methods is K-Means (KMs) based on clustering and classification.
There are also findings about image enhancement for multi-models such as the performance
of KMs, KM++, GMM, FKM, FCM and FRR. These methods are evaluated for image enhancement.
Image segmentation of machine learning approaches is one of the methods: K-Means
based image segments to various methods enhancing statistical measurements of PSNR,
SNR, MSE, IoU, DSC, JI. These metrics are image quality metrics. The classification
and prediction-based result findings are precision, accuracy, specificity, sensitivity
and F-measures. Finally, performance computing with python uses better results for
image quality metrics and image segmentation of breast cancer identification.
