LA-Breast DCE-MRI Dataset

Images were selected from retrospective studies corresponding to Latin American patients. Studies were selected according to the acquisition parameters with the aim to preserve diversity but ensure homogeneity among them. Each study was anonymized following the convention “MRI\_N” where N represents the integer number of the patient (between 1 and 200). Each study contains 15 imaging sequences: pre-contrast T1 fat saturated Dynamic (d0), five postcontrast T1 fat saturated dynamics (d1 to d5), T1 with no fat saturation (t1), T2 with no fat saturation (t2), the apparent diffusion coefficient image (ADC) and the diffusion image (Diff). All image sequences were obtained and stored using the standard DICOM 3.0. Besides, all studies were acquired using multiple 1.5T scanners and all contrast agents were gadolinium-based with dosages between 0.014 and 0.016 l/mol as they were obtained retrospectively. Each patient data was filtered according to their available clinical finding, were benign and malignant lesions were prioritized to ensure at least one relevant clinical finding across all images. Thereupon, the data contains balanced train, test and validation sets in terms of benign/malignant lesions, as well as non-dense/dense tissue. Additionally, annotations per image are provided with lesion location (x and y coordinates) BIRADS and tissue density. This data can be used for multiple purposes, including image synthesis, image characterization, lesion classification, tissue segmentation, among others. This dataset can be used for multiple purposes, such image synthesis, image characterization, lesion classification, tissue segmentation, among others.