BLADeS: Breast Lesion Automatic Diagnosis System

A Comprehensive Computer-Aided Diagnosis forBreast T1w DCE-MRI via Quantitative DynamicalFeatures and Spatio-Temporal Local BinaryPattern
Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) is a valid complementary diagnostic method for early detection and diagnosis of breast cancer.
However, due to the amount of data, the examination is difficult without the support of a Computer Aided Diagnosis (CAD) system.
Since MRI data includes different tissues and patient movements (i.e. breathing) may introduce artifacts during acquisition, any CAD needs some stages aimed to identify breast parenchyma and to reduce motion artifacts.
Among the major issues in developing a fully automated CAD, there are the accurate segmentation of lesions in Regions Of Interest (ROIs) and their consequent staging (classification).
This work introduces BLADeS (Breast Lesion Automatic Diagnosis System), a comprehensive fully automated breast CAD aimed to support the radiologist during the patient diagnosis.
We propose a hierarchical architecture that implements modules for breast, attenuation of motion artifacts, accurate localization of the lesions and, finally, classification according to their malignancy.
Performance were evaluated on 42 patients with histopathologically proven lesions, performing cross-validation to ensure a fair comparison. Results show that BLADeS can be successfully used to perform a fully automated breast lesion diagnosis starting from T1w DCE-MR images, without requiring any operator interaction in any of the processing stages.
Download: AVAILABLE SOON