Breast MRI and Computer Aided Diagnosis

Recently, there has been rapid increase per year in the number of breast MR studies performed in Korea. Dynamic contrast enhanced magnetic resonance mammography is a well-established method in the diagnosis of invasive breast cancer with a sensitivity near 100%. Distinction between benign and malignant lesions in MRI is possible by evaluating their morphology and enhancement pattern. A strong initial signal increase followed by a plateau or washout curve is regarded as indicative of malignancy, whereas a slow initial enhancement and a persistent curve type are thought to be associated with benign lesions. However, overlapping enhancement features exist, corroborating the need for additional morphological descriptors for differential diagnosis of breast lesions. The overlap of kinetic features with benign lesions is especially distinct in less aggressive, noninvasive cancers. Furthermore, the number of acquired image is 700-1,000 per one breast. Reading the large number of acquired MR images in a reasonable amount of time also becomes more important as the number of studies increases. Computer-aided image management and analysis have the potential to impact each of these obstacles, providing tools to improve the diagnostic accuracy (particularly through improved specificity), consistency, and efficiency of breast MR image interpretation.