Keywords:
Artificial Intelligence and Machine Learning, Artificial Intelligence, Breast, MR, CAD, Computer Applications-3D, Cancer, Not applicable
Authors:
D. Della Latta1, N. Martini1, S. Atzori2, V. Piagneri3, T. Trapuzzano4, D. Chiappino1, C. Iacconi3; 1Massa/IT, 2Pisa/IT, 3Carrara/IT, 4Marina Di Carrara /IT
DOI:
10.26044/ecr2020/C-11630
Purpose
FGT is the volumetric ratio between the fibroglandular tissue and the total breast volume. Its evaluation is a part of the standard breast MR reporting system (BI-RADS). As it is related with mammographic density, it has been recognised as a further risk factor for breast cancer development [1]. Since the MRI is a 3D imaging modality while mammography is 2D, a more accurate evaluation of the volumetric FGT can be performed.
However, breast MR images are characterized by variable contrast depending on the scanner manufacturer, the patient's breast tissue composition and the acquisition modality (T1- and T2-weighting, fat saturation). Breast imaging radiologist is able to segment the breast but the task is very time consuming and challenging in images with poor contrast between tissues.
The purpose of this work is to implement a 3D-CNN (Convolutional Neural Network) able to automate the breast segmentation task for the FGT (FibroGlandular Tissue) estimation from MRI.