MRI to predict nipple‐areola complex (NAC) involvement: An automatic method to compute the 3D distance between the NAC and tumor. Issue 8 (4th October 2017)

• Record Type: Journal Article
• Authors: Giannini, Valentina; Bianchi, Veronica; Carabalona, Silvia; Mazzetti, Simone; Maggiorotto, Furio; Kubatzki, Franziska; Regge, Daniele; Ponzone, Riccardo; Martincich, Laura
• Is Part Of: Journal of surgical oncology. Volume 116:Issue 8(2017)
• Page Start: 1069
• Page End: 1078
• Publication Date: 2017-10-04
• Subjects: 3D automatic distance -- breast cancer -- mastectomy -- magnetic resonance imaging -- nipple‐areola sparing -- tumor segmentation; Cancer -- Surgery -- Periodicals; Neoplasms -- Periodicals; 616
• DOI: 10.1002/jso.24788
• Languages: English
• ISSNs: 0022-4790

Abstract

Abstract : Objectives: To assess the role in predicting nipple‐areola complex (NAC) involvement of a newly developed automatic method which computes the 3D tumor‐NAC distance. Patients and Methods: Ninety‐nine patients scheduled to nipple sparing mastectomy (NSM) underwent magnetic resonance (MR) examination at 1.5 T, including sagittal T2w and dynamic contrast enhanced (DCE)‐MR imaging. An automatic method was developed to segment the NAC and the tumor and to compute the 3D distance between them. The automatic measurement was compared with manual axial and sagittal 2D measurements. NAC involvement was defined by the presence of invasive ductal or lobular carcinoma and/or ductal carcinoma in situ or ductal intraepithelial neoplasia (DIN1c − DIN3). Results: Tumor‐NAC distance was computed on 95/99 patients (25 NAC+), as three tumors were not correctly segmented (sensitivity = 97%), and 1 NAC was not detected (sensitivity = 99%). The automatic 3D distance reached the highest area under the receiver operating characteristic (ROC) curve (0.830) with respect to the manual axial (0.676), sagittal (0.664), and minimum distances (0.664). At the best cut‐off point of 21 mm, the 3D distance obtained sensitivity = 72%, specificity = 80%, positive predictive value = 56%, and negative predictive value = 89%. Conclusions: This method could provide a reproducible biomarker to preoperatively select breast cancer patients candidates to NSM, thus helping surgical planning and intraoperative management of patients.