University of Manitoba Breast Microwave Imaging Dataset (UM-BMID)
Microwave-based breast cancer detection is a growing field that has been investigated as a potential novel method for breast cancer detection. Breast microwave sensing (BMS) systems use low-powered, non-ionizing microwave signals to interrogate the breast tissues. While some BMS systems have been evaluated in clinical trials, many challenges remain before these systems can be used as a viable clinical option, and breast phantoms (breast models) allow for rigorous and controlled experimental investigations. This dataset, the University of Manitoba Breast Microwave Imaging Dataset (UM-BMID), contains S-parameter measurements from experimental scans of MRI-derived breast phantoms, obtained with a pre-clinical breast microwave sensing system operating over 1-8 GHz. The dataset consists of measurements from over 1250 scans of a diverse array of phantoms. The phantom array consists of phantoms of various sizes and breast densities. The .stl files used to produce the 3D-printed phantoms are also included in the dataset. We hope that this dataset can serve as a resource for researchers in breast microwave sensing to evaluate signal processing, image reconstruction, and tumour detection methods.
The University of Manitoba Breast Microwave Imaging Dataset (UM-BMID) isan open-access dataset available to all researchers. The dataset containsdata from experimental scans of MRI-derived breast phantoms.The dataset itself can be found at https://bit.ly/UM-bmid. The complete documentation for the dataset is also available at this link.
A GitHub page associated with the dataset can be found here: https://github.com/UManitoba-BMS/UM-BMID.The dataset is described in an accepted manuscript:T. Reimer, J. Krenkevich, and S. Pistorius, "An open-access experimentaldataset for breast microwave imaging,", in _2020 European Conference onAntennas and Propagation (EuCAP 2020)_, Copenhagen, Denmark, Mar. 2020,pp. 1-5, doi:10.23919/EuCAP48036.2020.9135659.This GitHub repository (https://github.com/UManitoba-BMS/UM-BMID) contains the code used to produce the resultspresented in that paper and supportive scripts for the UM-BMID dataset.