Breast cancer detection is automated using traditional and new-age mathematical and computational technologies. This article explicates a novel strategy termed Statistical Measure-based kNN Classification (SMkC) for breast cancer detection from digital mammograms. This method uses the mechanism of automated thresholding to extract the RoI from digital mammogram images examined for to breast cancer diagnosis. This technique constructs a feature vector based on the statistical features of the extracted RoI. The SMkC is experimented with digital mammogram images from MIAS and DDSM for the extraction of RoI and classification. The performance of SMkC is validated using the Specificity and Confusion Matrix. The classifier locates the optimal results based on its iteration and results, it gives an outcome to consider either benign or malignant, based on the classification output as either zero or one. The results were validated along with the statistical feature extraction, out of RoI from the input image.