Title :
Segmentation and classification of triple negative breast cancers using DCE-MRI
Author :
Agner, Shannon C. ; Xu, Jun ; Fatakdawala, Hussain ; Ganesan, Shridar ; Madabhushi, Anant ; Englander, Sarah ; Rosen, Mark ; Thomas, Kathleen ; Schnall, Mitchell ; Feldman, Michael ; Tomaszewski, John
Author_Institution :
Dept. of Biomed. Eng., State Univeristy of New Jersey, Piscataway, NJ, USA
fDate :
June 28 2009-July 1 2009
Abstract :
Triple-negative (TN) breast cancer has gained much interest recently due to its lack of response to receptor-targeted therapies and its aggressive clinical nature. In this study, we evaluate the ability of a computer-aided diagnosis (CAD) system to not only distinguish benign from malignant lesions on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), but also to quantitatively distinguish triple negative breast cancers from other molecular subtypes of breast cancer. 41 breast lesions (24 malignant, 17 benign) as imaged on DCE-MRI were included in the dataset. Of the 24 malignant cases, 13 were of the TN phenotype. Using the dynamic signal intensity information from the DCE-MRIs, an Expectation Maximization-driven active contours scheme is used to automatically segment the breast lesions. Following quantitative morphological, textural, and kinetic feature extraction, a support vector machine classifier was employed to distinguish (a) benign from malignant lesions and (b) TN from non-TN cancers. In the former case, the classifier yielded an accuracy of 83%, sensitivity of 79%, and specificity of 88%. In distinguishing TN from non-TN cases, the classifier had an accuracy of 92%, sensitivity of 92%, and specificity of 91%. The results suggest that the TN phenotype has distinct and quantifiable signatures on DCE-MRI that will be instrumental in the early detection of this aggressive breast cancer subtype.
Keywords :
biomedical MRI; cancer; expectation-maximisation algorithm; feature extraction; image classification; image segmentation; mammography; medical image processing; support vector machines; DCE-MRI; SVM classifier; TN phenotype; aggressive breast cancer subtype; automatic image segmentation; benign lesion; breast cancer classification; breast cancer segmentation; computer aided diagnosis system; dynamic contrast enhanced MRI; expectation-maximization driven active contours scheme; magnetic resonance imaging; malignant lesion; quantitative kinetic feature extraction; quantitative morphological feature extraction; quantitative textural feature extraction; support vector machine; triple negative breast cancer; Active contours; Breast cancer; Computer aided diagnosis; Feature extraction; Image segmentation; Kinetic theory; Lesions; Magnetic resonance imaging; Medical treatment; Support vector machines; CAD; breast cancer; classification; image analysis; kinetic texture curves; molecular subtypes; triple negative;
Conference_Titel :
Biomedical Imaging: From Nano to Macro, 2009. ISBI '09. IEEE International Symposium on
Conference_Location :
Boston, MA
Print_ISBN :
978-1-4244-3931-7
Electronic_ISBN :
1945-7928
DOI :
10.1109/ISBI.2009.5193283