BC-MRI-SEG: A Breast Cancer MRI Tumor Segmentation Benchmark
This provides a standardized tool for researchers in medical imaging to evaluate segmentation models, though it is incremental as it compiles existing datasets.
The authors tackled the difficulty of comparing deep learning approaches for breast cancer MRI tumor segmentation by creating a public benchmark (BC-MRI-SEG) from four datasets, including supervised and zero-shot evaluation, and compared state-of-the-art methods on it.
Binary breast cancer tumor segmentation with Magnetic Resonance Imaging (MRI) data is typically trained and evaluated on private medical data, which makes comparing deep learning approaches difficult. We propose a benchmark (BC-MRI-SEG) for binary breast cancer tumor segmentation based on publicly available MRI datasets. The benchmark consists of four datasets in total, where two datasets are used for supervised training and evaluation, and two are used for zero-shot evaluation. Additionally we compare state-of-the-art (SOTA) approaches on our benchmark and provide an exhaustive list of available public breast cancer MRI datasets. The source code has been made available at https://irulenot.github.io/BC_MRI_SEG_Benchmark.