OpenCC – An Open Benchmark Dataset for Corpus Callosum Segmentation and Evaluation

Neuroimaging studies have revealed that the structural changes of the corpus cal-losum (CC) are evident in a variety of neurological diseases, such as epilepsy and autism. Segmentation of the CC from magnetic resonance images (MRI) of the brain is a crucial step in the diagnosis of various brain disorders. However, the lack of open benchmark CC datasets has hindered development of CC segmenta-tion techniques. In this work, we present an open benchmark dataset – OpenCC – for CC segmentation and evaluation. The dataset was built through alternative ap-plication of automatic segmentation and manual refinement. The automatic seg-mentation is based on recent advances in deep learning – fully convolutional net-works, specifically U-Net, while the manual refinement is done by domain radi-ologists. The resulting dataset consists of 4643 mid-sagittal (or near mid-sagittal) slices and their corresponding CC masks. Furthermore, we provided some base-line segmentation results on the OpenCC dataset by using two latest deep learning segmentation approaches. The OpenCC dataset can be used for compari-son and evaluation of newly developed CC segmentation algorithms. We endeav-or that, through the publishing of the OpenCC dataset and baseline segmentation results, we could promote further development of CC segmentation techniques