Characterization of breast masses for simulation purposes

Abstract

Simulation of radiographic lesions is an important prerequisite for several research applications in medical imaging, including hardware and software design and optimization. For mammography, breast masses are an important class of lesions to be considered. In this study, we first characterized both benign and malignant breast masses with example mammograms from the Digital Database for Screening Mammography (DDSM). The measured properties of each of these mass types were then used to create a simulation routine that was capable of creating example masses from each category. A preliminary observer experiment was conducted to determine whether a mammographer could distinguish between the simulated and true masses. An ROC analysis indicated A z values of 0.59 and 0.61 for benign and malignant lesions, respectively, suggesting very similar appearance for the simulated and real lesions. A larger observer performance experiment with multiple mammographers is underway to validate these results. (This work was supported by a grant from the NIH, R21-CA95308.)

Analyzing the effect of dose reduction on the detection of mammographic lesions using mathematical observer models

“…This included the signal (lesion)-absent set of backgrounds which were used for training the observer models. Another set of signal-present images were generated by digitally inserting realistic simulated masses and microcalcifications in signal-absent backgrounds by a routine previously published (11,12). This routine relied on the measured characteristics of real lesions to create simulated lesions with a realistic appearance.…”

Evaluation of an improved method of simulating lung nodules in chest tomosynthesis

“…A common approach is to conduct observer performance experiments, in which both real and simulated lesions are included (21)(22)(23)(24)(25)(26)(27). For example, Saunders et al (23,24) presented a method of simulating mammographic lesions. The visual appearance of the simulated lesions was validated by conducting an observer performance experiment using 200 mammographic images containing either real or simulated pathology.…”

Mass detection on mammograms: influence of signal shape uncertainty on human and model observers

“…Later, they have been further optimized [8] (second-generation CLB) to reproduce visual and statistical properties of mammograms. On the signal front, Saunders et al [17,18] recently developed an algorithm capable of generating benign or malignant breast mass signals based on the analysis of real masses' characteristics.…”