Motion Corruption Detection in Dynamic Contrast-Enhanced MRI of the Breast

Motion corruption can result in difficulty identifying lesions, and incorrect diagnoses by radiologists in cases of breast cancer screening using DCE-MRI. Although registration techniques can be used to correct for motion artifacts, their use has a computational cost and can lead to a reduction in diagnostic quality rather than the desired improvement. In a clinical system it would be beneficial to identify automatically which studies have severe motion corruption and poor diagnostic quality and which studies have acceptable diagnostic quality. We have developed an automated method of estimating the degree of mis-alignment presents in a DCE-MRI study of breast screening. Two predictive models were investigated in this study and validated on a labeled dataset from radiologists denoting cases suffering from motion artifacts that affected image interpretability. We have managed to identify motion corrupted cases on our clinical dataset with an area under the AUC curve of 88%.M.Sc