Magnetic resonance in mammography: a quantitative evaluation tool of contrast-enhanced magnetic resonance of the breast

摘要

Our aim had been to develop a tool for the quantitative evaluation of contrast-enhanced magnetic resonance imaging (MRI) of the breast, in order to improve the early detection of breast cancer. Our goal was to implement a Web-based tool for the reliable automatic diagnosis of breast MRI, to allow remote diagnosis using a PC workstation. Our tool is able to read MRI DICOM3 files: the images acquired by the MRI console are sent in DICOM format to the PC platform where our computer-aided diagnosis (CAD) system is implemented. Because of the promising results we have achieved, we are thinking about an improvement of the automatic tool by using neural architectures. Once the tool has been improved by using neural networks, statistics would be able to be performed on the relations between curve morphologies, image enhancement values and lesions.