Automated Detection and Segmentation of Nonmass-Enhancing Breast Tumors with Dynamic Contrast-Enhanced Magnetic Resonance Imaging
MetadataShow full item record
AuthorÁlvarez Illán, Ignacio; Ramírez Pérez De Inestrosa, Javier; Gorriz Sáez, Juan Manuel; Marino, Maria Adele; Avendano, Daly; Helbich, Thomas; Baltzer, Pascal; Pinker, Katja; Meyer-Baese, Anke
CONTRAST MEDIA & MOLECULAR IMAGING
COMPUTER-AIDED DIAGNOSISDCE-MRI DATALESION SEGMENTATIONCOMPONENT ANALYSISCáncer
Illan, I. A., Ramirez, J., Gorriz, J. M., Marino, M. A., Avendano, D., Helbich, T., ... & Meyer-Baese, A. (2018). Automated Detection and Segmentation of Nonmass-Enhancing Breast Tumors with Dynamic Contrast-Enhanced Magnetic Resonance Imaging. Contrast media & molecular imaging, 2018.
SponsorshipEuropean Unions Horizon 2020 Research and Innovation Programme under the Marie Skodowska-Curie grant agreement No. 656886; Austrian National Bank "Jubilaeumsfond" Project 16219; 2020-Research and Innovation Framework Programme PHC-11-2015 667211-2; Siemens Austria; Novomed; Guerbet, France; NIH/NCI Cancer Center Support Grant P30CA008748
Nonmass-enhancing (NME) lesions constitute a diagnostic challenge in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) of the breast. Computer-aided diagnosis (CAD) systems provide physicians with advanced tools for analysis, assessment, and evaluation that have a significant impact on the diagnostic performance. Here, we propose a new approach to address the challenge of NME lesion detection and segmentation, taking advantage of independent component analysis (ICA) to extract data-driven dynamic lesion characterizations. A set of independent sources was obtained from the DCE-MRI dataset of breast cancer patients, and the dynamic behavior of the different tissues was described by multiple dynamic curves, together with a set of eigenimages describing the scores for each voxel. A new test image is projected onto the independent source space using the unmixing matrix, and each voxel is classified by a support vector machine (SVM) that has already been trained with manually delineated data. A solution to the high false-positive rate problem is proposed by controlling the SVM hyperplane location, outperforming previously published approaches.