In this paper, a new method for automatic detection of microcalcifications in digitized mammograms is proposed. Based on mathematical morphology theory to deal with the problem of low contrast between microcalcifications and their surrounding pixels, it uses various structuring elements of different sizes to reduce the sensibility to microcalcification diversity sizes. The obtained morphological results are converted to a suspicion map based on an image quality assessment metric called structural similarity index (SSIM). This continuous map is, then, locally analyzed using superpixels to automatically estimate threshold values and finally detect potential microcalcification areas. The proposed method was evaluated using the publicly-available INBreast dataset. Experimental results show the benefits gained in terms of improving microcalcification detection performances compared to state-of-the-art methods.

本文提出了一种自动检测数字化乳腺X线照片中微钙化的新方法。基于数学形态学理论来解决微钙化与其周围像素之间对比度低的问题，它使用大小不同的各种结构元素来降低对微钙化多样性大小的敏感性。基于称为结构相似性指数（SSIM）的图像质量评估指标，将获得的形态学结果转换为可疑图。然后，使用超像素对该连续图进行局部分析，以自动估计阈值并最终检测潜在的微钙化区域。使用公开可用的INBreast数据集对提出的方法进行了评估。