Contrast-enhanced spectral mammography (CESM) is done using the standard digital mammography equipment, with additional software that performs dual-energy image acquisition. The dataset is a collection of 2006 CESM images all high resolution with an average of 2355 x 1315 pixels. Each image with its corresponding manual annotation (breast composition, mass shape, mass margin, mass density, architectural distortion, asymmetries, calcification type, calcification distribution, mass enhancement pattern, non-mass enhancement pattern, non-mass enhancement distribution, and overall BIRADS assessment) is compiled into 1 CSV file. Moreover, full medical reports are provided for each case (PDF format) along with manual segmentation annotation for the abnormal findings in each image (CSV file).

Deep learning (DL) has a promising potential in helping radiologists provide a more accurate diagnosis. However, fully annotated and large-sized datasets are required. In the past couple of years, a few public mammography datasets were released. These datasets contain digital mammography images only, and none include CESM images.

Acquisition protocol: 

CESM is done using the standard DM equipment but with additional software that performs dual-energy image acquisition. Two minutes after intravenously injecting the patient with non-ionic low-osmolar iodinated contrast material (dose: 1.5 mL/kg), craniocaudal (CC) and mediolateral oblique (MLO) views are obtained. Each view comprises two exposures, one with low energy (peak kilo-voltage values ranging from 26 to 31kVp) and one with high energy (45 to 49 kVp). A complete examination is carried out in about 5-6 minutes.

Image preprocessing:

The images were converted from DICOM to JPEG using RadiAnt with best 100% image quality (lossless).