No abstract

No abstract

Breast cancer is the second most common type of cancer among Brazilian women, globally recognized as a major public health problem. Dense breasts increase the risk of developing breast cancer, mainly due to the difficulty of the lesion visualization, hampering the probability of early detection. In order to enhance the overall quality of mammographic images, digital image processing techniques could improve the visualization of lesions, providing an increase in contrast among breast structures. The goal of this paper is to evaluate the use of the Contrast Limited Adaptive Histogram Equalization (CLAHE) technique for contrast enhancement in mammographic dense breast images. By computing the signal to noise ratio (SNR) and variance, comparing the original images to the processed ones using CLAHE. In this paper, 28 dense breast images were used and separated in mediolateral oblique (MLO) and craniocaudal (CC) views. All the images were processed after the background removal, using CLAHE with seven different window sizes. The results showed that small window sizes decrease the SNR. However, by decreasing window size, an increase in variance was observed, therefore increasing contrast. This increase in contrast was visually observed, on which processed images using small window size performed better enhancement for breast structures, thus resulting in greater contrast. According to these results, we concluded that the CLAHE technique performed better using small window size. In future works, we should apply this algorithm in a greater dense breast image database, as well as preprocessing the images by digital filters for reducing noise.

No abstract