Automatic Detection of Simulated Motion Blur in Digital Mammograms Open Access
Downloadable ContentDownload PDF
Motion blur is a known phenomenon in full-field digital mammography that arises during image acquisition. It has been reported to reduce lesion detection performance and mask small microcalcifications, resulting in failure to detect smaller abnormalities until they reach more advanced stages. It is estimated that 20% of screening mammograms show elements of blur. Not only does patient movement cause motion blur, but also the compression paddle during the clamping phase of the mammography exam has been found to move slightly in the vertical direction, resulting in tissue motion during image acquisition (up to 1.5 mm of motion). We propose using machine-learning algorithms to automatically detect motion blur, which could support the clinical decision-making process during the mammography exam by allowing for an immediate retake, thereby preventing unnecessary expense, time, and patient anxiety. Blur was simulated mathematically to mimic the real blur seen in clinical practice. The blur point-spread-function mask is generated by distributing pixel intensity of an image pixel moving under random motion within the range of blur effect (the maximum amount of tissue motion allowed). The random motion trajectory vector is generated on a super-sampled image frame to accommodate smaller substeps; the vector was then sampled on a regular pixel grid using subpixel linear interpolation to generate the blur point-spread-function (PSF) mask. This randomly-generated motion trajectory is constrained by several factors: the effects of variations in tissue elasticity, imaging exposure time, and size of blur effect (motion boundary in millimeters) were examined. The blur mask is convolved with a mammogram to create blur. Five motion blur magnitudes (0.1, 0.25, 0.5, 1.0, and 1.5 mm) were simulated on 244 and 428 mammograms from INbreast and DDSM databases, respectively. Blur was quantified using 28 blur measure operators for each mammogram and at each blur level. The data were assigned to training (70%) and testing (30%) datasets to train three machine-learning classifiers: Ensemble Bagged Trees, Fine Gaussian SVM, and Weighted KNN, to distinguish five levels of blurred from unblurred mammograms, using six-way classification. For INbreast, the average classification accuracies were 87.7%, 85.66% and 85.68% for Ensemble Bagged Trees, Fine Gaussian SVM, and Weighted KNN, respectively, and the average classification accuracies for DDSM were 93.50%, 93.64%, and 92.70% for Ensemble Bagged Trees, Fine Gaussian SVM, and Weighted KNN, respectively.As of this date, no other study has investigated the ability of machine-learning classifiers and blur measure operators to detect motion blur in mammograms yet. Our preliminary results show the potential to detect simulated blur automatically using those methods. Although limited work has been done to quantify the effects of motion blur on radiologists’ performance, there is evidence that motion blur might not be detected visually by a human observer, which potentially can reduce diagnostic performance.